Search

• A SMOTE approach was proposed to handle imbalanced data of hazards levels. • SMOTE was integrated with Gaussian process for the prediction of hazards levels. • A real-world example is used to illustrate and validate the proposed approach. • Results from different data generation approaches are compared with that of SMOTE. • Results from different machine learning methods are compared with that of GP. Cultural soil heritages (CSHs) are artifacts with historical, artistic, and scientific significance; however, they are vulnerable to various hazards, such as weathering, fractures, hollowing, collapses, and gullies. This is especially true for those CSHs exposed to the outdoors. Due to the large number of CSHs sites within China, managing and protecting these heritages with the aid of detailed on-site investigations is time-consuming and expensive. Consequently, evaluating the spatial distribution and degree of hazards developed in all these heritages becomes impractical. To address this issue, this paper developed a Gaussian process classification (GPC) method to predict the spatial distribution of typical hazards (i.e., weathering, fractures, hollowing, collapses, and gullies) and the development level of each hazard from eight environmental factors (e.g., annual relative humidity and annual sunshine time) and a limited number of investigation data. As the number of investigation data for different levels of each hazard is usually imbalanced and sparse, this study proposed a synthetic minority oversampling technique (SMOTE) with GPC to form the SMOTE-GPC method. A real-world example is used to illustrate this approach. Results from real-world data demonstrated that the proposed method achieved an F 1 score, precision, recall, and Cohen's kappa with values greater than 0.93 in both the training and testing datasets, indicating its good performance. [ABSTRACT FROM AUTHOR]

At present, China is facing a relatively serious water security problem, and virtual water trade is an important means to alleviate the shortage of water resources. It is of great practical significance for China to analysis of the multi-scale near-long-distance flow of virtual water between regions. In this paper, the multi-regional input-output model was used to measure the virtual water near-long-range transfer of 17 departments in eight regions in 2012 and 2017 in China. The measured results are further discussed in the context of K-means and structural decomposition analysis (SDA) methods. The results show that from 2012 to 2017, the overall trend of interregional virtual water flow and import and export volume of various regions and departments in China showed a downward trend, and there were significant differences in inflow, outflow, and distribution. In 17 sectors, the agricultural sector has a much higher virtual water flow than other sectors, particularly in the north-west and central regions. In addition, the food and tobacco industry and construction industries in most regions also have the characteristics of high outflows. This paper argues that China should Fully exploit the effect of industrial structure on the suppression of virtual water rise. At the same time, it is necessary to improve the virtual water trade pattern, especially the virtual water trade pattern of the agricultural sector, and then gradually optimize the distribution pattern of regional water resources in China. [ABSTRACT FROM AUTHOR]

• The nexus between FinTech development and inclusive growth is analyzed. • The indicator system for inclusive growth is established. • The spatial econometric approach and machine learning are applied. • The case of an emerging economy is considered. This study investigates the impact of financial technology (FinTech) on inclusive growth (IG) by exploiting a panel of 281 prefecture-level Chinese cities in the years 2011–2020 using the spatial econometric model and machine learning algorithm. The results show that FinTech positively impacts IG, while there is no spatial spillover effect. The evidence from the machine learning algorithms suggests that as FinTech advances to a higher level, its positive impact on IG increases. The mechanism test shows that the latter effect is achieved through entrepreneurial stimulation and human capital enhancement. Moreover, the impact of FinTech on IG is more pronounced in large and medium-sized cities and cities in the eastern region. However, it does not significantly affect small cities or cities in the central region. This paper, therefore, offers new insights on the interaction between FinTech and IG along with the analysis of the effects related to the development of FinTech on IG in China. [Display omitted] [ABSTRACT FROM AUTHOR]

The ionospheric foF2 prediction model GWO-ALSTM is proposed in this paper, which combines the Gray Wolf Optimization (GWO) algorithm and the attention mechanism based on the long short-term memory (LSTM) model. The datasets used in this model were obtained from the oblique ionosondes of the China Ground-based Seismo-ionospheric Monitoring Network. The data from 2010 to 2012 was used for training, and the data of 2013 was used for verification. The input parameters of the model include local time, day number, sunspot number, F10.7 solar flux, Ap index, Dst index, and foF2 at the previous moment, and the output parameter is foF2 at the current moment. The IRI2016 model, GABP model, LSTM model and GWO-ALSTM model were compared with the observed results for analysis. The results show that the GWO-ALSTM model is superior to the LSTM model, the GABP model and the IRI2016 model. Meanwhile, the comparative analyses of the diurnal variations of foF2 show that the curve of the GWO-ALSTM model fits the observed values more closely than the curve of any other model under the geomagnetic quiet and storm conditions. [ABSTRACT FROM AUTHOR]

• An improved singular spectrum decomposition is proposed. • High complexity components are secondarily decomposed to reduce its complexity. • An improved prediction model of optimization algorithm is proposed. • Intelligent weighting strategy is introduced to overcome traditional weighting problem. • A combined prediction model for carbon emission is proposed. Accurate prediction of carbon emission is critical for the development of low-carbon economy. However, most carbon emission prediction studies use a single model with low prediction accuracy, and do not consider the instability of carbon emission. Therefore, this paper proposes a combined prediction model of carbon emission. Firstly, the original data is decomposed by singular spectrum decomposition to obtain a limited amount of singular spectrum components. Secondly, high complexity components are secondarily decomposed by variational mode decomposition. Then, chameleon swarm algorithm and carnivorous plant algorithm are used to train the regularization coefficients and kernel parameters of kernel extreme learning machine and least squares support vector machine respectively, and the trained model is used to predict the decomposition components. Finally, induced ordered weighted averaging operator is used to calculate the weight of single model, and error correction is introduced to further promote the prediction accuracy. The carbon emission data of China and the United States is used to make a prediction experiment. The results indicate that the proposed model is superior to other comparative models in different indexes, which provides a new idea for carbon emission prediction. [ABSTRACT FROM AUTHOR]

Hydrogen, as a clean and efficient energy source, is important in achieving zero-CO 2 targets. This paper explores the potential of hydrogen geologic storage (HGS) in China for large-scale energy storage, crucial for stabilizing intermittent renewable energy sources and managing peak demand. Despite its promise, HGS faces challenges due to hydrogen's low density and viscosity, and its complex interactions with geological formations and microorganisms. This review offers a comprehensive overview of the current research status for HGS, with a particular focus on highlighting the main challenges confronting China. These difficulties and challenges primarily arise from complex geological conditions and the absence of fundamental parameters within potential reservoirs, including depleted oil/gas fields, salt caverns, and brine aquifers. Additionally, we have synthesized the current applications of machine learning (ML)as a potential solution. Key challenges are examined, such as the effects of operational parameters (e.g., cyclical injection-production and injection rates) on HGS efficiency, which can influence phenomena such as hydrogen fingering and caprock integrity. This review also looks into the insufficiently understood hydrogen-water-rock geochemical reactions under diverse temperatures and pressures, a gap that hampers the development of predictive numerical simulations and raises concerns about hydrogen leakage due to changes in porosity and permeability. Additionally, the paper addresses the limited knowledge about the metabolic mechanisms of subsurface microorganisms under extreme conditions, highlighting potential risks of hydrogen leakage and groundwater contamination. These microorganisms can metabolize hydrogen, producing gases such as CH 4 and H 2 S, which may cause steel corrosion. Furthermore, the study assesses the distribution and prospects of three primary methods for pure hydrogen storage in China, considering the current state of hydrogen development and relevant government policies. The role of ML in advancing HGS is also discussed, offering insights into future research directions. This review not only scrutinizes the scientific challenges of HGS but also underscores its potential, guiding future simulation and practical engineering applications in this field. • HGS is feasibility in China through policy examination and potential site analysis. • Geochemical and microbial reactions jeopardize to reservoir integrity and H 2 quality. • Elucidating the present application and future prospective for ML in HGS. • Summarizing the key challenges associated with achieving large-scale HGS. [ABSTRACT FROM AUTHOR]

Carbon lock-in has become a major obstacle to green development in all countries, and carbon unlocking (CUL) is of great significance in accelerating the process of carbon neutrality worldwide. Based on the panel data of 292 prefecture-level cities in China from 2006 to 2020, this paper constructs a PSM-DID model based on machine learning to empirically test the impact of LCCP policy on urban CUL. The regression result shows that the low carbon city pilot (LCCP) policy significantly increases the level of CUL by 1.25 % in the pilot cities, which is still valid after range of robustness tests, and the mechanism analysis shows that green innovation and green habits are important ways for the policy to affect CUL. Based on the generalized random forest (GRF) algorithm, we further find that the policy can increase the CUL level by 0.6 %, and the average treatment effect (ATE) of the sample is concentrated between 0.004 and 0.006, which exhibits obvious heterogeneity. This paper chooses population quality, openness level and industrial structure as heterogeneous factors, which are finally found to have a U-shaped or inverted U-shaped relationship with ATE. This study provides useful insights for China and other countries to break the carbon lock-in and realize green development. • Low-carbon city pilot policy can effectively promote urban carbon unlocking. • Causal forest model is used for causal inference based on generalized random forests algorithm. • The propensity score is calculated by machine learning. • Generalized random forest is used for heterogeneity analysis. • Low-carbon city pilot policy transmits policy effects through green innovation and green habits. [ABSTRACT FROM AUTHOR]

• The paper proposes a methodology for a hybrid model that can capture complex non-linear relationships and help understand the interactions between input and output features. • The model overcomes the limitation of traditional neural network models in predicting across different spaces. • The proposed model is an intelligent water quality prediction model that can provide decision support for predicting COD Mn concentration and managing watershed risks in the Changdang Lake basin, with good application prospects and practical value. The organic pollution of lake water can cause a tremendous threat to the water ecosystem and human health. The COD Mn is one of the crucial indicators of lake water quality and is commonly utilized to gauge the extent of organic pollution in lake water. Therefore, this paper selected COD Mn as the research object and used the water quality monitoring data of Changdang Lake in China and its upstream and downstream to predict the COD Mn concentration in the lake. In order to study the spatial relationship between the lake and upstream and downstream water quality, reflect the joint action of multiple water quality factors in prediction and the interaction between different feature factors. This study combined the XGBoost feature filtering algorithm, maximum mutual information coefficient (MIC), and improved recurrent neural network (GRU) and proposes a hybrid model called XGB-MIC-GRU. The model first used XGBoost to screen and extract the relative importance of water quality characteristics and used the Shapley addition extension (SHAP) method to explain XGBoost feature extraction. Then, the correlation between the lake and the upstream and downstream water quality is calculated through MIC analysis. Finally, the selected water quality factor characteristics and spatial characteristics are input into the GRU model for prediction. The experimental results showed that water temperature, total phosphorus, and total nitrogen are the most important to COD Mn , and the upstream US1 and downstream DS1 and DS2 stations are the most closely related to the concentration of COD Mn in the lake. By comparing the prediction effect of the model in different time steps, the best 16-time steps related data were selected to predict the value of the next time. MAE, RMSE, and R2 of the model are 0.10, 0.13, and 0.96, respectively. The model has better prediction accuracy and correlation error than the traditional SVR and GPR. The proposed mixed model can accurately predict the concentration of COD Mn in the lake. It can assist decision-makers in timely implementation of effective measures to safeguard the lake ecosystem. [ABSTRACT FROM AUTHOR]

The relationship between government and enterprise has attracted extensive attention. Under the increasingly severe requirement of sustainable development, there is still a lack of research on the economic effect of political acuity from the perspective of enterprise's positive party value creation. We built a dictionary of political acuity and demonstrated reliability through machine learning algorithms such as K-Nearest Neighbor (KNN). Then, based on the annual reports of China's listed companies from 2013 to 2020, the relationship between political acuity, ESG atmosphere, and corporate performance is empirically discussed. Examination through the formal institutional perspective of informal institutionalization shows that the positive acuity of the Communist Party of China(CPC) and the democratic parties(DPC) will improve corporate performance, while the negative acuity will have an early warning effect on performance. Furthermore, the stronger ESG atmosphere synergized this relationship. The CPC's negative acuity has supervision effect on non-state-owned companies, and this supervisory effect still exists in the ESG atmosphere. However, whether the moderating effect is considered or not, the positive political acuity of state-owned enterprises doesn't significantly improve performance. We found that the CPC's embedding in corporate governance will lead to both economic and political benefits, and have thresholds. We constructed a political acuity dictionary and introduced text analysis and nonparametric estimation method in this paper, which provided a basis and reference for future research on political acuity at the enterprise level. Our findings also enrich the institutional theory and the embeddedness theory. Meanwhile, our research broadened the boundary of political parties, ESG, and enterprises, the integration of ideological values and formal institutions, and had practical implications for the green transformation of firms and the precise positioning of political party functions. • We build a dictionary of political acuity for the first time. This dictionary provides a new measurement perspective for the study of corporate political sentiment and sustainable development. • From the perspective of positive value creation, we examine the impact path of a company's party acuity, ESG atmosphere, and financial performance. This paper helps to expand the governance boundaries of ideology and formal institutions, political concepts, and corporate behavior. • We explored the accounting consequences of political acuity for different types of firms, and measured the economic and political effects thresholds. • We introduced machine learning, python crawler, text analysis, and nonparametric estimation methods into this paper, which helped to expand the technical approach to corporate governance and green transformation. [ABSTRACT FROM AUTHOR]

The reasonable setting of the slurry pressure is very important for the safety of shield tunnel construction. In view of the common geological problems of high water pressure and multiple fracture zones in water conveyance tunnels in China, the instability mechanism of the shield excavation face in these formations remains unclear. In this paper, based on the Pearl River Delta Water Resources Allocation Project, various machine learning algorithms are introduced, and the predicted values of the slurry pressure obtained with different machine learning algorithms are evaluated and compared. The optimal machine learning algorithm suitable for this project is determined. Then, using this algorithm, considering the influence of the fault fracture zone, the concept of the formation influence coefficient is proposed, which is used as the input of the prediction model. The influences of the formation coefficient distribution and the influence width of the fracture zone on the accuracy of slurry pressure prediction are examined. Finally, based on this model, the slurry pressure of nearly 100 groups is predicted and verified. The results show that (1) if the influence of the fault fracture zone is considered and a reasonable influence width of the fault fracture zone can be determined, the mean absolute error (MAE) of the predicted slurry pressure is much higher than that of the predictions without considering the fault fracture zone, and the prediction accuracy can be improved by approximately 25%; (2) when the formation influence coefficient is obtained via the method of the theoretical distribution and the influence width of the fault fracture zone is 17 rings, the prediction accuracy of the slurry pressure reaches the optimal value; and (3) through on-site refined investigation, it can be determined that the influence width of the fault fracture zone is 19 rings. The research results of this paper can provide an effective method for setting the shield slurry pressure under high-water pressure conditions in the fault fracture zone. [ABSTRACT FROM AUTHOR]

Due to the inherent uncertainty and the mismatch between renewable energy output and load demand, renewable energy-based system optimization is increasingly important in China. Therefore, electricity demand response (EDR) is critical to the stability and efficiency of an integrated renewable energy system (IRES). The customers' demand response under the time-of-use (TOU) mechanism is the key to the entire process. However, how to optimize integrated renewable energy system based on accurately identifying the electricity demand response participation of customers is one of the main issues at this stage. To solve the problem, this paper presents a novel approach for integrated renewable energy system optimization considering electricity demand response management and multistage energy storage systems from the perspective of Fujian Province, China. To enable large-scale renewable energy integration, the original output is processed using the Hampel identifier (HI)-Savitzky-Golay filter (SGF) technology. A machine learning (ML)-based identification model is developed for EDR to determine whether the customers are participating or not. Driven by the time-of-use mechanism, customers can make dynamic adjustments based on the Logistics function. After that, an integrated renewable energy system model optimization strategy is proposed based on satisfying customers' electricity demand response. Throughout the optimization process, the multistage energy storage system plays a vital role in the residual fluctuation absorption for renewable energy filtering, the dynamic adjustment process of the demand response, and the integrated renewable energy system optimization. Through extensive case studies and discussions, it is demonstrated that random forest (RF) and support vector machine (SVM) reach 80 % identification accuracy with a 20 % testing ratio. According to the optimization approach proposed in this paper, the minimum operation cost can be calculated to be 9.336*106 CNY. The methodology presented in this paper establishes a special relationship between electricity demand response identification and dynamic adjustments, and provides an optimization model for Fujian Province, China, which is a reliable reference for future work. [ABSTRACT FROM AUTHOR]

To achieve carbon neutrality, China must grasp the intricate factors driving coal market, as it addresses coal consumption and reduces the carbon footprint. While previous studies have identified certain factors, they have largely overlooked the impact of the overall industry sector on the coal market. In this paper, a hybrid causal machine learning model was proposed that combine with least absolute shrinkage and selection operator (LASSO), multiple linear regression (MLR), peter and clark momentary conditional independence (PCMCI) and interpretable machine learning. The approach employed a complex network perspective to identify 10 key factors in China's coal market from three dimensions: industrial sector, foreign trade and energy market. The hierarchical pattern of these factors is classified into two levels: direct factors, primarily encompassing crude oil futures, exchange rates and architectural decoration, and intermediary factors, mainly including the chemical industry and building material. Interestingly, this paper reaffirms the roles of crude oil futures and exchange rates in the coal market, as identified in prior studies. Additionally, it uncovers new influential factors primarily driven by the chemical industry and architectural decoration, previously unexplored. Furthermore, this paper found a significant contemporaneous relationship between crude oil futures and coal price index (0.151) as well as coal consumption (0.102), and the strong relationship between coal consumption and the Indonesian Rupiah to Chinese Yuan exchange rate (0.063) was also confirmed. Among the emerging dominant factors, the coal price index and the chemical industry (0.145), along with coal consumption and building materials (0.250), also exhibit a strong contemporaneous relationship. These findings highlight the importance of considering the entire industry sector while analyzing the coal market and promoting a cleaner transformation of the industry in China, and the paradigm presented not only applicable to the coal market, but can be extended to other industries. [Display omitted] • Better grasping key factors in China's coal market critical to carbon neutrality. • A comprehensive study encompassing industrial sector, foreign trade and energy market. • A novel hybrid machine learning models and industry-wide features are introduced. • Identification and categorization of direct and intermediary factors. • Findings offer a new paradigm for decision-making, driving cleaner production reforms. [ABSTRACT FROM AUTHOR]

The complex and varied urban road conditions have always been a difficult and a pivotal component in the study of driverless technology especially at intersections. In China, it is necessary for driverless cars to understand the gestures of traffic police. To identify the traffic police gesture at the intersection, the key step is to detect the traffic police at the intersection. At present, the research on traffic police detection is still in its infancy, there exists common problems such as slow detection speed and other real time problems in this method, and there is not a standardized traffic police data set ether. For the real time problems, this paper introduces the attention mechanism, and proposes a new real-time detection method of traffic police based on attention mechanism. The method proposed in this paper has strong robustness and can quickly complete the target detection task. For the data set problem, this paper analyzes and discloses similar data sets published through research. In the meanwhile, this paper collects 24,530 video data on the actual road, and it extracts and saves 12,000 pictures containing traffic police at frame rate of 30FPS as traffic police detection training and validated data set. [ABSTRACT FROM AUTHOR]

Energy piles have attracted much attention in recent years because they provide a profitable solution for efficient shallow geothermal energy utilization in different climatic regions. However, the long-term performance design of energy piles under different thermal scenarios currently relies on time-consuming and computationally expensive methods such as numerical simulations, which seriously hinders the further engineering application of energy piles. To this end, this paper provides a high-precision and computationally efficient model for predicting the long-term performance of energy pile design through an artificial neural network machine learning process. First, experimentally validated numerical models are developed. Then, they are utilized to generate the training and evaluate datasets for the proposed model by inputting sixty typical thermal load distributions in different regions of China. Finally, the performance of the proposed model is evaluated by comparing its calculations with those obtained using numerical models. The results show that the proposed model can predict the long-term performance of energy piles and enrich the current methods for the long-term design of energy piles. Furthermore, its features that tremendously reduce the computational time and minimum required resources make it an excellent supplement compared with numerical simulations. [ABSTRACT FROM AUTHOR]

• Using hyperspectral imaging combined with machine learning to detect the maturity of individual maize seeds. • Partial least square-linear discriminant analysis (PLS-LDA), the transfer learning algorithm transfer component analysis (TCA), and manifold embedded distribution alignment (MEDA) were proposed. • Transfer learning algorithms were applied to construct transferable maturity detection models between different varieties of maize seeds. • The method used in this paper has the advantages of being fast, simple, low-cost, and accurate. Seed maturity is closely related to seed germination, seed storage and the yield of the next generation of crops and it is an important indicator of seed quality. Maize is an important food, feed, and industrial raw material crop in China. Hyperspectral imaging technology has the advantages of spectral technology and machine vision technology and it can obtain information inside and outside the seed without damaging it. On the basis of hyperspectral imaging technology, transfer learning algorithms were used in this study to explore the transfer feasibility of maize seed maturity models amongst different varieties. Three transfer tasks were designed between different varieties on the basis of the model established for the Xianyu 335 variety. Cross-variety detection models were constructed using the classical machine-learning algorithm partial least square-linear discriminant analysis (PLS-LDA), the transfer learning algorithm transfer component analysis (TCA), and manifold embedded distribution alignment (MEDA). Results showed that the PLS-DA direct transfer model had varying degrees of model failure in all three transfer tasks. However, the average recognition accuracies of the TCA migration model and the MEDA migration model were 89.3% and 91.2%, respectively. Both of the two Transfer learning models can effectively solve the problem of different data feature distributions amongst different varieties, making the model more universal. It solves the problem of transferring the single-grain maize seed maturity detection model amongst different varieties, providing effective, stable and universal technical support for maize seed detection, which is conducive to the promotion of single-grain sowing technology and the improvement of agricultural automation level. [ABSTRACT FROM AUTHOR]

Tunnel structure are often subjected to continuous deformation caused by the creep effect of soft rock, leading to posing significant long-term operational risks. This paper focuses on ensuring the safe operation of a typical soft rock tunnel in the complex and dangerous mountainous area of western China. On the basis of studying the structural mechanic characteristics of the tunnel under the influence of soft rock creep, the VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) model based on Analytic Hierarchy Process (AHP) and Entropy Weight Method (EWM) to determine subjective and objective weights, and game theory (GT) to obtain comprehensive weights was established. Additionally, the differential evolution-grey wolf optimization (DE-GWO) improved extreme learning machine (ELM) model was also constructed. By comparing the safety evaluation results of the two models on typical monitoring sections of soft rock tunnel structure, it is demonstrated that the proposed knowledge-based decision-making and data-driven models effectively and accurately evaluated the long-term safety of typical monitoring sections. Ulteriorly, to address the issue of structure safety evaluation caused by the inability to comprehensively monitor the entire tunnel (missing monitoring data), the DE-GWO improved ELM model was further adopted, and the structure safety status of the entire tunnel was precisely deduced. [ABSTRACT FROM AUTHOR]

Underground tunnel excavation using the drill-and-blast method often results in underbreak occurrences due to improper blasting parameters and complex geological environment. This underbreak phenomenon has a profound impact on tunnel safety, stability and construction costs. Traditional approaches for predicting underbreak extent (UE) through field measurements and theoretical models exhibit limitations in terms of accuracy and efficiency. Consequently, it is urgent to develop a novel approach for UE prediction in tunnelling operations. In this paper, extreme gradient boosting (XGBoost) is first applied as the foundational algorithm, and slime mould algorithm (SMA) is implemented for tuning hyper-parameters of XGBoost. Meanwhile, six chaotic maps are integrated with SMA to initialize the population and improve the optimization performance. Subsequently, a dataset of 250 samples is collected from three underground mines in China, involving ten influential factors (RMR , uniaxial compressive strength (UCS), vertical principal stress (σ v), lateral pressure coefficient (λ), excavation area (EA), powder factor (PF), specific charge (SC), advance length (AL), periphery hole burden (HB)and periphery hole spacing (HS)). Additionally, four indices, i.e., coefficient of determination (R 2), variance accounted for (VAF), mean absolute error (MAE) and root mean square error (RMSE), are used to evaluate the comprehensive performance of these proposed COSMA-XGBoost models and four common machine learning models. Finally, a parametric sensitivity analysis is performed, and the optimal intelligent model is applied in practical tunnelling projects. The results indicate that chaotic optimized SMA models have better convergence ability and higher accuracy compared with the original SMA model. Notably, the PSMA-XGBoost model outperforms other models as the R 2, VAF, MAE and RMSE values for the testing set are 0.979, 95.79%, 4.176 and 4.884, respectively, whereas 0.968, 94.25%, 4.274 and 5.012, respectively for training set. EA , RMR and UCS exhibit significant effects on UE. In practical tunneling projects, the engineering application of the PSMA-XGBoost model demonstrates its feasibility and efficiency in predicting UE within underground tunnels. [ABSTRACT FROM AUTHOR]

Accurately predicting wind and photovoltaic power is one of the keys to improving the economy of wind-solar complementary power generation system, reducing scheduling costs and no-load losses, and ensuring grid stability. However, the natural properties of energy result in complex fluctuations in their corresponding power sequences, making accurate predictions difficult. Therefore, this paper proposes an intelligent prediction system that combines decomposition algorithms and deep learning for ultra-short-term prediction of wind and photovoltaic power. First, an improved decomposition algorithm is proposed, based on fuzzy entropy's property that its value increases with the increase of sequence uncertainty, particle swarm optimization (PSO) is used to search for the optimal parameter combinations of variational modal decomposition (VMD), so that it can automatically adjust the parameters for energy data with different characteristics to reduce the human error. Then, a convolutional neural network (CNN) architecture that balances operational efficiency and prediction performance is constructed, and the hyperparameters of the CNN are optimized using the wild horse optimization algorithm (WHO) to improve the stability and accuracy of the prediction model. In this paper, real data from wind power plants and photovoltaic power plants in China are used as experimental objects, and experiments are carried out in three aspects, namely, benchmark model selection, decomposition algorithm comparison and combined model comparison. The results show that selecting CNN as the benchmark model is a good choice; the improved VMD has better decomposition performance than other state-of-the-art decomposition algorithms. The system proposed in this paper is highly generalizable and adaptive, and its prediction performance and accuracy greatly outperform that of other comparative models, with prediction accuracies improved by 72% and 79%, respectively, compared to a single CNN model. • The hyperparameters of VMD are determined by using PSO based on fuzzy entropy. • Optimize convolutional neural network using the wild horse optimization algorithm. • The intelligent prediction system can accurately predict wind power and PV power. • Experiments based on power data from actual wind farms and PV plants. • A deep learning prediction method applied to wind and solar complementary systems. [ABSTRACT FROM AUTHOR]

Faradaic deionization (FDI) is an emerging water treatment technology based on electrodes able to remove ionic species from water by charge transfer reactions. It is a young and promising technology that has attracted much attention due to its large capacity to store ions and the high selectivity of the faradaic electrode materials. This study reviews published papers on FDI from different angles: data mining, bibliometric and machine learning. Metrics such as annual growth rate, most important journals, relevant authors, collaborations maps, sentiment and subjectivity analysis, similarity and clustering analysis were performed. The results indicated that the strong interest in FDI really started in 2016, China is the most active country in FDI, and Desalination is the most important journal publishing FDI articles. The word cloud method showed that the most preferred adopted words are deionization, capacitive, electrode, material. Sentiment analysis results indicated that most of the researchers are optimistic about FDI technology. The title similarity method revealed that FDI researchers were successful in proposing unique and appropriate titles. The clustering approach stressed that FDI literature is concentrated on electrode material production, desalination application, lithium recovery and comparison with CDI. [Display omitted] • Faradaic Deionization (FDI) dataset includes 170 papers downloaded from Scopus. • Annual growth rate of FDI research based on published articles is 55.12 %. • Desalination , J. Mat. Chem. and ACS Appl. Mater. Inter. are the core sources of FDI. • China and the USA are the most active countries on FDI research. • Deionization , capacitive and desalination are frequent words in FDI articles titles. [ABSTRACT FROM AUTHOR]

Continued increases in global population and rising living standards in many countries are driving a surge in demand for energy and protein-rich foods. Wheat, barley, and canola are important crops that are grown and traded globally. However, climate change, geopolitical tensions and competition from other crops threaten the ability to satisfy global demand. Accurate predictions of crop production and its spatial variation can play a significant role in their reliable and efficient production, marketing, and distribution. This review examined recently published models and data used to predict wheat, barley, and canola yield to identify which factors produced the best yield predictions. A literature search was conducted across the Scopus, EBSCOhost and Web of Science databases over seven years between 2015 and 2021. Data extracted from the papers identified by the literature search were investigated using graphical and quantitative analytical techniques to determine if the type of algorithm, input data, prediction timing, output scale or extent and climate variability both in isolation and in combination affected the model's predictive ability. The literature search produced 11,908 results which was reduced to 118 papers after applying the review criteria (peer reviewed papers focussed on models predicting yield at greater than plot scale across extensive areas using accessible data). China produced almost one third of all yield prediction models over the study period and 87% of models were used to predict wheat yield. Statistical models were the most common algorithm in most regions and in total. However, there was a surge in machine learning models after 2018. They were the most common model from 2019 to 2021, with one third developed in China. The review concluded that only the choice of modelling technique and the input data had a significant effect on model performance with the machine learning techniques Random Forest, Boosting algorithms and Deep Learning models as well as process-based Light Use Efficiency models that used a combination of remotely sensed and agrometeorological data performing best. The review showed that matching the model to the available data could improve the ability to predict wheat, barley or canola yield. The use of quantitative statistical techniques in this review, should give modellers trying to predict wheat, barley or canola yield more confidence in matching their approach to the available data than previous reviews that relied on visual interpretation of data. [Display omitted] • Recent advances in models and data used to predict crop yield were examined to identify any patterns and trends. • Statistical models were the most common but there was a surge in the use of machine learning models after 2018. • Quantitative analytical techniques were used to identify factors that affected the model's predictive ability. • Machine learning models were more accurate than process-based models but not statistical models. • Combining agro-meteorological with remotely sensed data was more accurate than using agro-meteorological data only. [ABSTRACT FROM AUTHOR]

Accurate prediction of the rate of penetration (ROP) is a difficult issue in the drilling process, especially under complex formation conditions. Many methods, such as mechanism and machine learning, were introduced to investigate it. However, most of them are offline prediction methods which may not be capable of capturing the online trend of ROP. In this paper, a novel dynamic model for ROP prediction is proposed considering the process characteristics, which consists of three stages. In the first stage, the correlations between ROP and eight drilling parameters are analyzed, and the rotational speed, weight on bit, depth are selected as the model inputs. In the second stage, the drilling data are pre-processed by using the filtering and re-sampling techniques. In the last stage, the moving window strategy, extreme learning machine, and 10-fold cross validation are used to establish the ROP model. Our main idea of online prediction of ROP lies in this last stage. Specifically, two steps (modeling and prediction) are executed alternately in the moving drilling depth windows so as to predict the ROP more accurately. Finally, the proposed ROP prediction model is applied to the drilling well ZK3 in Xiangyang area, Central China. The prediction accuracy is improved by at least 7% compared with seven well-known ROP prediction methods, two online and five offline, which validates the effectiveness of the proposed method. It is believed that the proposed model provides a basis for intelligent optimization control in drilling process. • A novel intelligent dynamic model is proposed for the online prediction of drilling ROP. • The influence of the length of moving window and distance between two windows are investigated thoroughly. • The proposed model can learn autonomously in the drilling process and has a fast computation speed. • The proposed method has a higher prediction accuracy than two online and five offline well-known conventional methods. [ABSTRACT FROM AUTHOR]

• Exploring the effect of locally weighted learning with machine learning model. • Gain ratio are used to select the most important environmental factor. • LWL-RS-ADT appears as an accurate model in assessing landslide susceptibility. Assessing landslide susceptibility and predicting the possibility of landslide event is the foundation and prerequisite for emergency response and management of landslide disaster. The target of current paper is to propose five integration models based on integrating locally weighted learning (LWL) with a radial basis function classifier (RBF), Fisher's linear discriminant (FLDA), quadratic discriminant analysis (QDA), a Credal decision tree (CDT), an alternating decision tree (ADT) and random subspace (RS) and the performance of five integration models were compared for modeling landslide susceptibility. Yongxin County from China was employed as a study area, 364 landslide locations and fifteen environmental factors were applied. The results demonstrate that the proposed LWL-RS-ADT model is more reliable and stable than the other models. Among the fifteen environmental factors, NDVI, lithology, and altitude are the very significant factors in the six models. It is concluded that the proposed integration models provide an effective way to predict the susceptibility of landslides. [ABSTRACT FROM AUTHOR]

• A spatial random forest-based downscaling and merging method (SRF-DM) is proposed. • SRF-DM performs better than the original satellite-based precipitation products. • SRF-DM is more accurate than the classical machine learning-based methods. • Spatial autocorrelation is the most important variable. • SRF-DM has a good performance even when the gauge density is low. Publicly available satellite precipitation products (SPPs) are essential inputs for hydrological models. However, the existing SPPs suffer from coarse resolutions and large uncertainties, which greatly hinder their widespread applications. Thus, to fully utilize the unique characteristics of each individual SPP, a spatial random forest (SRF)-based downscaling and merging (SRF-DM) method is proposed to fuse multiple SPPs and gauge observations in this paper. The proposed method incorporates spatial autocorrelation information between precipitation observations through a covariate. This covariate is estimated using ordinary kriging interpolation on spatial neighbors that have a high correlation with the target location. The proposed method was used to generate 1-km daily precipitation data using the datasets from five satellite precipitation products (IMERG, GSMaP, CHIRPS, MORPH, and PERSIANN) and gauge observations in the period from January 1, 2015 to December 31, 2019 over Sichuan province, China. The performance of SRF-DM was compared with the original SPPs, XGBoost-based downscaling and merging (XGB-DM), two double-layer machine learning (ML) methods, namely RF-RF and RF-artificial neural network (RF-ANN), and three single ML methods, namely RF, ANN, and RF-based Merging Procedure (RF-MEP). The experimental results demonstrate the following findings: (i) SRF-DM is more accurate than the original SPPs across different temporal scales (i.e., daily, monthly, and seasonal) in terms of statistical and categorical accuracy measures, (ii) SRF-DM outperforms the six ML-based methods in estimating high precipitation and capturing spatial precipitation patterns, (iii) the spatial autocorrelation between neighboring precipitation data is the most significant factor in both downscaling and merging, and (iv) the performance of SRF-DM is influenced by gauge density, but it still yields good results even with a limited number of gauges. On the whole, SRF-DM is considered an effective tool for generating daily precipitation products with high accuracy and resolution, which is primarily attributed to its satisfactory performance in regions with diverse precipitation patterns and topography. [ABSTRACT FROM AUTHOR]

Carbon market is the most effective market tool for carbon emission reduction. China, the largest carbon emitter in the world, established the national carbon market in 2021, covering over 2000 key units in the power sector. Therefore, the forecasting of carbon price has profound implications for environmental and energy policies. In this paper, two traditional econometric model and three kinds of machine learning (ML) algorithms are used to predict carbon returns in the Chinese carbon trading market based on carefully selected predictors. Among all forecasting models, the Random Forest (RF) has the best forecasting performance, followed by some GARCH models using various factors. Compared with the traditional benchmark of ARMA model, the BP neural network (BP) and the GA improved BP method (GA-BP) are less competitive in predicting carbon returns in China because of their large forecasting errors. According to the optimal model, social attention to the carbon market, the international crude oil returns and the overall performance of the stock market are the most important predictors. The findings are robust to the change in the sample set. Overall, the ML approach shows an advantage in forecasting carbon returns, but the selection of predictors is also important. • Machine learning and econometric models are used to forecast carbon returns in China. • The selection of predictors is based on economic analysis. • The Random Forest (RF) outperforms the other ML and econometric methods. • The energy market is extremely important for predicting carbon returns. • Social concerns and stock market performance improve forecasting accuracy. [ABSTRACT FROM AUTHOR]

• Sensor technology developments drove advances in biophysical estimation techniques. • CubeSat constellations will increase VHR data accessibility to various users. • Sentinel-2 red-edge bands present prospects for operational crop stress detection. • RF is prominently used in the literature despite new developments in algorithms. • Retrieval models developed in Mediterranean areas do not apply to semi-arid areas. This paper provides an overview of the recent developments in remote sensing technology and machine learning algorithms for estimating important biophysical and biochemical parameters for precision farming. The objectives are (i) to provide an overview of recent advances in remotely sensed retrieval of biophysical and biochemical parameters brought by the developments in sensor technologies and robust machine learning algorithms and (ii) to identify the sources of uncertainty in retrieving biophysical and biochemical parameters and implications for precision agriculture. The review revealed that developments in crop biophysical and biochemical parameters retrieval techniques were mainly driven by announcements and the availability of new sensors. Two ground-breaking events can be identified, i.e., the availability of Sentinel-2 and the SuperDove constellation. The two provide high temporal-high spatial resolution data relevant for site-specific management and super-spectral configuration, enabling retrieval of crop growth and health parameters. The free availability of Sentinel-2 triggered the testing of its spectral configurations and upscaling of retrieval approaches using simulated data from field spectrometers and airborne hyperspectral sensors. SuperDoves will likely reduce the cost of very high-resolution data while providing unprecedented capabilities for detailed, accurate and frequent characterisation of field variability. Studies showed that the red-edge bands and hybrid models coupling Radiative Transfer Model (RTM) and machine learning regression algorithms (MLRA) are promising for operational and accurate monitoring of stress-related crop parameters to aid time-sensitive agronomic decisions. However, such models were tested in Mediterranean climates and performed poorly in African semi-arid areas and China's temperate continental semi-humid monsoon climates. Therefore, locally-calibrated RTM models incorporating crop-type maps and other spatio-temporal constraints may reduce uncertainties when adapted to data-scarce regions. Generally, permanent experimental sites and a lack of systematic calibration data on various crops are some limiting factors to using remote sensing technologies for PA in Sub-Saharan Africa. Other complexities arise from farm configurations, such as small field sizes and mixed cropping practices. Therefore, future studies should develop generic, scalable and transferable models, especially within under-studied areas. [ABSTRACT FROM AUTHOR]

• An improved safety potential field, named the Work-Zone Crash Risk Field (WCRF), is developed for real-time crash risk assessment in highway work zones. • The WCRF performs better than conventional safety surrogate measures in identifying high-risk vehicles in work zones. • The impact of setting up a work zone on the crash risk of each lane at transition areas is analyzed. • Several key traffic features that may contribute to crash risk in transition areas of the work zones are identified. • The heterogeneity in the impact of risk-contributing traffic features over different work zones is discussed. Due to complex traffic conditions, transition areas in highway work zones are associated with a higher crash risk than other highway areas. Understanding risk-contributing features in transition areas is essential for ensuring traffic safety on highways. However, conventional surrogate safety measures (SSMs) are quite limited in identifying the crash risk in transition areas due to the complex traffic environment. To this end, this study proposes an improved safety potential field, named the Work-Zone Crash Risk Field (WCRF). The WCRF force can be used to measure the crash risk of individual vehicles that enter a work zone considering the influence of multiple features, upon which the overall crash risk of the road segment in a specific time window can be estimated. With the overall crash risk used as a label, the time-window-based traffic data are used to train and validate an eXtreme Gradient Boosting (XGBoost) classifier, and the Shapley Additive Explanations (SHAP) method is integrated with the XGBoost classifier to identify the key risk-contributing traffic features. To assess the proposed approach, a case study is conducted using real-time vehicle trajectory data collected in two work zones along a highway in China. The results demonstrate that the WCRF-based SSM outperforms conventional SSMs in identifying crash risks in work zone transition areas on highways. In addition, we perform lane-based analysis regarding the impact of setting up work zones on highway safety and investigate the heterogeneity in risk-contributing features across different work zones. Several interesting findings from the analysis are reported in this paper. Compared to existing SSMs, the WCRF-based SSM offers a more practical and comprehensive way to describe the crash risk in work zones. The approach using the developed WCRF technique offers improved capabilities in identifying key risk-contributing features, which is expected to facilitate the development of safety management strategies for work zones. [ABSTRACT FROM AUTHOR]

The factors influencing residents health have become complex and intertwined with the development of economy and society. Traditional research with a single factor on health will not provide an accurate picture of the situation. This paper collects data on economic, environmental and social factors to estimate their impact on regional health. Considering the data is multi-source and complex, this paper proposes a combined feature importance algorithm, which weighted the feature importance of RF, XGB and SOIL. The algorithm does not depend on the data and adaptively approximates the true results. The results show that economic factors have a significant and direct impact on health, environmental factors have a lag correlation with health level, and social factors have a more complicated effect on health. Finally, we provide policy suggestions for health on economic, environmental, and social development. [ABSTRACT FROM AUTHOR]

To achieve a high penetration of renewable energy integration, an effective solution is to explore the interdependence between numerical weather prediction (NWP) data and historical wind power to improve prediction accuracy. This paper proposes a novel combined approach for wind power prediction. The characteristics of NWP and historical wind power data are extracted by using the feature extraction technique, the predictor is designed based on extreme learning machine (ELM) and least squares support vector machine (LSSVM) model, and then key parameters of the prediction models are optimized by improving cuckoo search (ICS) to obtain a reliable value, which is defined as the pre-combined prediction value (PPA). To obtain a reliable result, a variance strategy is developed to allocate the weights of the pre-combined prediction model to obtain the final predicted values. Four seasons dataset collected from regional wind farms in China is utilized as a benchmark experiment to evaluate the effectiveness of the proposed approach. The results of comprehensive numerical cases with different seasons show that the proposed approach, which considers multiple-error metrics, including error metrics, accuracy rate, qualification rate, and improvement percentages, achieves higher accuracy than other benchmark prediction models. • A novel combined framework is proposed to predict short-term wind power. •Linear and nonlinear feature extraction strategies are applied to analyze the character of NWP data. •A variance combined strategy is used to allocate the optimal weight of the primary combined model. •The wind power prediction error analysis is conducted by multiple-error performance metrics. [ABSTRACT FROM AUTHOR]

China, India, and the USA are the world's biggest energy consumers and CO 2 emitters. Being the leading contributors to climate change, these economies are also at the core of environmental solutions. This paper investigates the causal relationship among solar and wind energy production, coal consumption, economic growth, and CO 2 emissions for these three countries. To do so, we use an advanced methodology in Machine Learning to verify the predictive causal linkages among variables. The Causal Direction from Dependency (D2C) algorithm set CO 2 emissions as the target variable. The obtained results were disaggregated and estimated in a supervised prediction model. The findings, confirmed by three different Machine Learning procedures, showed an interesting output. While a reduction in overall carbon emissions is predicted in China and the US (resulting from the intensive use of renewable sources of energy), India displays critical predictions of a rise in CO 2 emissions. This indicates that curbing CO 2 emissions cannot be achieved without conducting a comprehensive shift from fossil to renewable resources, although China and the U.S. present a more promising path to sustainability than India. Being an emerging renewable energy leader, India should further enhance the use of low-carbon sources in its power supply and limit its dependence on coal. • Renewable energies, coal consumption, economic growth, and CO 2 we examine. • We investigate the causal predicted relationship on China, India, and the USA. • An advanced methodology in Machine Learning is used. • India has a prediction of an increase in emissions of CO 2. • China and the U.S. present a more promising path to sustainability than India. [ABSTRACT FROM AUTHOR]

In recent years, many concealed skarn-type and porphyry-type deposits have been discovered in Chating area, which shows very good prospectivity to host hydrothermal deposits. In this paper, we carried out the 3D mineral prospectivity modeling for porphyry and skarn-type mineralization of the Chating area. During this study, implicit geological modeling and the "total litho-inversion" method were used to build the 3D geological models and optimize the 3D geological models, various 3D predictive maps were generated by multiple 3D methods according to the exploration model. Finally, we use a 3D convolutional neural network (3D CNN) model to integrate all of the 3D predictive maps and delineate the concealed targets. The results show that the high- prospective areas delineated based on the 3DMPM not only include the deposits which are used as training data, but also the deposits that have already been discovered in the study area. It means that the 3DMPM approach used in this paper has good prediction and generalization ability. Compared with the Logistic Regression model (LR), Support Vector Machines (SVM), and Radom Forest (RF) model, the 3D CNN model can efficiently capture the correlation between various deposit types and 3D predictive information, and has better commendable predictive capabilities. The results of this paper can not only provide some new highly prospective areas for further mineral exploration in Chating area but also can promote the research on 3DMPM with deep learning methods. [Display omitted] • 3D Convolutional Neural Network would provide a new and powerful tool for 3D mineral prospectivity modeling. • The "total litho-inversion" method is a viable tool for the optimization of the 3D geological models which can provide more reliable data for 3D mineral prospectivity modeling. • 3D mineral prospectivity modeling can effectively identify not only the known deposits (not training data), but also delineate several new favorable exploration areas within Chating area at depth. The Chating area is situated within the Middle-Lower Yangtze River Metallogenic Belt, China. Several concealed skarn and porphyry-type deposits have been discovered in this area, indicating high potential for hosting hydrothermal deposits. However, due to the complex geological structure, exploration risks significantly increase with increasing depth. To overcome this challenge, three-dimensional mineral prospectivity modeling (3DMPM) has begun to be widely applied for mapping the prospectivity of deep-seated and concealed mineralization. However, most previous studies on 3DMPM were based on shallow supervised machine learning models and dimensionality-reduced 3D predictive maps. Although these models have shown good results, they may lose spatial correlation within the 3D predictive maps and fail to explore nonlinear correlations between the 3D predictive maps and mineralization. Meanwhile, 3D geological models are the most important basis of the 3DMPM, however, in the past, few studies have incorporated the optimization of the 3D geological models into the process of 3DMPM. Therefore, this paper initially builds and optimizes 3D geological models through implicit 3D geological modeling and "total litho-inversion" approach. Subsequently, the 3D predictive maps are generated by employing various 3D methods, which are further integrated using a 3D convolutional neural network (3D CNN) model to identify highly prospective areas for mineralization. The results show that the highly prospective areas identified by the 3DMPM include not only the training data but also other mineral deposits that have previously been discovered within the study area. In addition, compared with the Logistic Regression model (LR), Support Vector Machines (SVM), and Radom Forest (RF), the 3D CNN performs better prediction capabilities due to its enhanced ability to capture the correlations between 3D predictive maps and multiple types of mineral deposits. It suggests that the 3DMPM based on the 3D CNN model has commendable predictive capabilities in identifying prospective mineralization areas, and some new highly prospective areas can be considered as priority areas for future exploration of concealed mineralization within the Chating Area. [ABSTRACT FROM AUTHOR]

As global warming intensifies, the reduction of carbon emissions is imminent. Carbon price is directly related to whether carbon can be effectively reduced. Therefore, accurately forecasting carbon price has important practical significance. Aiming at the nonstationary and nonlinear characteristics of carbon price, this paper proposes a novel hybrid model for forecasting carbon price, which is based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), multiscale fuzzy entropy (MFE), complete ensemble empirical mode decomposition (CEEMD), improved random forest by salp swarm algorithm (SSARF), improved back propagation by cuckoo search (CSBP), improved extreme learning machine by whale optimization algorithm (WOAELM) and error correction (EC), named ICEEMDAN-MFE-CEEMD-SSARF-CSBP-WOAELM-EC. Firstly, carbon price is decomposed by ICEEMDAN, divided into high-, medium-, and low-complexity components by MFE. Secondly, high-complexity components are merged and secondarily decomposed by CEEMD, which are still recorded as high-complexity components. Then, SSARF, CSBP and WOAELM are used to forecast high-, medium-, and low-complexity components, respectively, and forecasting results are reconstructed. Finally, EC is carried out using an extreme learning machine to obtain the final forecasting results, and the Diebold-Mariano test is introduced for a comprehensive evaluation of the model. Taking carbon price in the pilot cities of Shenzhen and Hubei as examples, after 6 aspects and 20 comparative experiments, the results show that the proposed model has higher forecast accuracy, with MAPE, MAE and RMSE up to 0.03131, 0.00089 and 4.02e-06 in Hubei, and its forecasting ability is better than other commonly used international carbon financial price forecasting models, providing a theoretical and data basis for carbon pricing and formulating carbon reduction policies in China. The main contributions of this paper are the improved primary decomposition, the use of secondary decomposition, and the innovative combination of three optimal models to forecast carbon price, but it still needs to be optimized for practice. [Display omitted] • Propose improve CEEMDAN by using Hermite interpolation and calculating residuals first. • High complexity components are secondarily decomposed to reduce its complexity. • Improved RF by SSA, named SSARF, is proposed to solve the dilemmas of RF. • Propose a high-accuracy hybrid model for carbon price forecasting. • Compare multi-faceted experiments to prove the validity of the proposed model. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is an important component for self-driving. Traffic flow is closely related to population distribution, and the traffic flow is not only related to the absolute number of human population but also to their concerns and interests. Accurate spatio-temporal web traffic flow prediction is critical in many applications, such as bandwidth allocation, anomaly detection, congestion control and admission control. Most existing traffic flow prediction methods use models based on time-series analysis and remain inadequate for many real-world applications. Web traffic flow is found to be strongly associated with the spatio-temporal distribution of the population. Increasingly, it is critical to understand and make decisions based on the relationship between population patterns and web traffic flow patterns. It has been proven that different people have different responses to web events. Due to the complexity of spatial data structures and the huge volume of web traffic flow log data, it is difficult to routinely find the relationship between web events and population distributions without an appropriate processing framework. In this paper, we propose an innovative framework named GeoTrafficPredict to support the accurate spatio-temporal prediction of web traffic flow. GeoTrafficPredict provides a machine learning platform to learn the spatio-temporal pattern of traffic flow and use the pattern to predict the trend in both spatial and temporal dimension. Also, GeoTrafficPredict provide data aggregation portal and cloud-based computation function. GeoTrafficPredict deploys a series of computational images in a cloud computing environment, and the implementation on China's CSTNET illustrates the performance of our platform. [ABSTRACT FROM AUTHOR]

In this paper, an improved optimization model is proposed for demand response in a remote off-grid microgrid local on the Dongfushan Island, China to develop the energy dispatch and economic benefits considering different electricity price under different seasonal meteorological conditions. First, the seasonal electricity pricing model is built with the power generation of renewable sources in different seasonal meteorological conditions. Second, satisfaction is evaluated by the seasonal electricity price and the power consumption pattern. Improved Pareto optimum based on a distributed learning algorithm is proposed to maximize the satisfaction so that the electricity bills of consumers are reduced and the profits of the retailer is increased. The performance of the proposed optimization model is validated in the HOMER software and Matlab. Simulation results show that the electricity bills of consumers are lower by using the proposed method. For the retailer, the generation cost saves 1216$, and the utilization of renewable energy increased by 3.9% in January 2011. • Efficiencies and economics of demand response are verified in an off-grid microgrid. • A improve Pareto optimum is proposed to solving the demand response problem. • Electricity price model based on different season meteorological is proposed. • Reasonable control of flexible load to improve the efficiency of demand response. • The economic benefits of retailers and consumers are improved under demand response. [ABSTRACT FROM AUTHOR]

A major difficulty in integrating large scale wind power generation in an electrical power system is that wind generated power appears to be erratic, intermittent, and volatile. In this paper, we demonstrate the efficacies of a novel ultra short term 1-step ahead wind generated power prediction model, by combining two best of breed machine learning models in their respective areas of applications: a deep convolutional neural network (CNN) model, known to be effective in classification problems, and a bi-directional long short term memory (Bi-LSTM) model, known to be effective in 1-step ahead time series prediction problems, using a cross attention (XA) mechanism on three challenging practical datasets: the East-China dataset, the Yalova (Turkey) dataset, and the 16 MW dataset. There are two alternative cross attention models: (1) using the CNN features as the key–value pair, and the Bi-LSTM features as the query, this we called a XA model, and (2) using the Bi-LSTM features as the key–value pair, and the CNN features as the query, this we called a XA_I model; we found empirically for a properly chosen sliding window length, whichever CNN model or Bi-LSTM model performs well in the 1-step ahead prediction, then its features should be used as the query in the cross attention mechanism, thus, the XA achieves better results than XA_I on the East-China dataset, while XA_I achieves better results than XA on the Yalova dataset, and on the 16 MW dataset. Where comparable results using other state-of-the-art models are available on the Yalova dataset and the 16 MW dataset, we found that our XA_I results are superior. Moreover, it is found empirically, that the cross attention mechanism model produces stable k -step ahead predictions, for k ≤ W 2 , where W is the sliding window length. • A novel prediction model for wind generated power based on cross attention mechanism has been proposed. • The proposed method demonstrated on three practical datasets to have superior performance. • The cross attention mechanism based models give a stable multi-step ahead prediction. [ABSTRACT FROM AUTHOR]

How to achieve the "double carbon" goal in energy systems has been the concern of governments. Integrated energy system (IES) is affected by climate change during his operation, in order to study the impact of climate change on IES and achieve the "double carbon" goal in energy systems, this paper proposes an integrated machine learning(IML) to forecast the long-term load, then investigates IES costs and carbon emissions in relation to climate, followed by the establishment of carbon peak energy system(CPES) and carbon neutral energy system(CNES), finally the honey badger algorithm is used to optimize the configuration of CPES and CNES. The results show that: IML can accurately make load forecasts. Under climate change, changes in load reduce the cost and carbon emissions of IES, and changes in equipment efficiency increase the cost and carbon emissions of IES. When both are considered, the cost and carbon emissions of IES increase by 1.18% and 0.92% per decade respectively. The costs of CPES and CNES increase by 0.93% and 1% respectively for every 10 years earlier than the year of achievement. To meet China's "double carbon" goal, CPES and CNES need to increase their costs by 1.97% and 2% respectively. • Integrated machine learning proposed for long-term load forecasting. • Studied the impact of system equipment efficiency and load with climate change. • Proposing carbon peaking energy system to achieve the carbon peak goal. • Proposed carbon-neutral energy system to achieve carbon neutrality goal. • The increased costs of achieving carbon peak and carbon neutral were studied. [ABSTRACT FROM AUTHOR]

Ocean satellites provide accurate and precise data across various scales, making them a vital tool for investigating the association between global change and ocean processes. However, low-quality data creates unavoidable gaps in satellite data, diminishing its usefulness and continuity. These deficiencies can be resolved by implementing machine learning techniques as valuable tools. This paper details a new satellite data prediction tool titled "SatelliteFixer". The SatelliteFixer model, utilizing a custom-built random forest structure, can generate dependable data with enhanced temporal-spatial continuity. This model has demonstrated feasibility with diverse satellite data sources and light bands, and outperforms the basic machine learning approach. The juxtaposition of model data with in-situ cruise sampling results allows for widespread analysis of the movement and dispersion of suspended sediment. The above entails the inversion of long-term events and the observation of short-term events, which enables accurate seasonal analysis using continuous data without the influence of uneven data volume distribution and outliers, and is also the first-time satellite data has tracked the entire process of pulsed artificial flooding. SatelliteFixer provides a fresh outlook for detailing the varying trends on consecutive timescales and successional spaces among ocean processes. • A data-driven model for ocean satellite missing data prediction is established based on a specially designed machine learning structure. • The feasibility and availability of model result are demonstrated with MODIS Aqua and GOCI visible light data. • As an example of application, SatelliteFixer data are used with in-situ cruise data to analyze the transportation and distribution of suspended sediment. • SatelliteFixer data enables the accurate seasonal analysis and the first tracking of the entire process on pulsed artificial flooding. [ABSTRACT FROM AUTHOR]

To accommodate the increased demand for electric vehicle(EV) charging in China, this paper examines electric vehicle charging station(EVCS) location strategies from the perspective of private investors, taking full account of the competitive environment of existing EVCSs in the region. First of all, a three-level location model considering dynamic pricing is developed, which includes user decisions, EVCS pricing, and EVCS location decisions. Then, the soft actor-critic(SAC) reinforcement learning algorithm is used to train the optimal pricing strategy for EVCS to guarantee the maximum cumulative revenue. The proposed methodology is verified through case studies based on an industrial park in China. The results show that the proposed methodology can make more economical and scientific location decisions than the traditional method. The dynamic pricing method based on reinforcement learning can provide a reference for the location and operation of more EVCSs. • A dynamic pricing mechanism for EV charging station is constructed. • The location decision of EV charging station is studied from the perspective of investors. • A three-layer model of EV charging station investment is formulated. • User decision, charging price and location of EV charging station are considered. • SAC reinforcement learning algorithm is used to solve the real-time pricing decision of EV charging stations. [ABSTRACT FROM AUTHOR]

Accurate estimation of ride-hailing travel mobility is significant for demand management, and transportation planning. Although existing intervening opportunities models based on individual destination selection behavior can estimate travel mobility patterns (e.g., commuter flow, and migration flow), they usually ignore the substitutability of candidate destinations. In the context of ride-hailing travel, people tend to have strong destination preferences, and candidate destinations should be related to individual travel needs. Meanwhile, artificial intelligence offers powerful tools to extract complex nonlinear dependencies of mobility data, which are difficult to capture by traditional intervention opportunities models. This paper proposes a novel ensemble model with conditional intervening opportunities to improve the accuracy of ride-hailing travel mobility estimation by considering the substitutability of candidate destinations, that is, only the location related to people's trip purpose will likely affect people's travel behavior. The proposed ensemble model employs a stacking strategy to integrate six advanced machine learning and deep learning algorithms to extract complex nonlinear dependencies from ride-hailing travel mobility data, and achieve accurate mobility estimation. Furthermore, datasets from two major cities in China with more than 25 million ride-hailing trips are used for model training and experimental comparison. The results indicate that the proposed model outperforms other baseline models in ride-hailing travel mobility estimation tasks. It accurately predicts trip flows and the trip distance distribution, and can capture mobility patterns with strong interpretability. The proposed model can be applied to analyze the travel behavior of ride-hailing passengers, as well as the mobility patterns between different regions. • Propose a novel ensemble model for ride-hailing travel mobility estimation. • Develop conditional intervening opportunities model with substitutability of candidate locations. • Extract nonlinear dependencies from ride-hailing data using artificial intelligence algorithm. • Verify the proposed prediction model using over 25-million ride-hailing trips. • Interpret ride-hailing travel mobility patterns using Shapley additive explanations method. [ABSTRACT FROM AUTHOR]

With rapid urbanization and industrialization, the number of light-duty gasoline vehicles (LDGVs) in China has continued to grow rapidly, leading to a significant increase in traffic pollution. Therefore, it is essential to accurately calculate the emission of LDGVs for air quality monitoring and management. Fortunately, Motor Vehicle Emission Simulator (MOVES) is a sophisticated model for estimating mobile source emissions with good prediction accuracy. However, the parameters of MOVES are based on the field tests in the US, which is worth exploring whether MOVES can be applied to other countries. Hence, in this paper, we used the portable emission measurement system (PEMS) to conduct real driving emission (RDE) tests of LDGVs, aiming to explore the possibility of the MOVES application in China. Based on the field tests, we modified basic parameters in the MOVES model, but unsatisfactory prediction performance was obtained. Existing research on improving MOVES performance mainly involved new binning of operating modes, but these methods had limited improvements. Though studies have also used machine learning methods for predicting LDGV emissions, they lacked comparison and integration with the MOVES model. To further improve the prediction accuracy, we proposed a novel road vehicle emission model that integrated the machine learning method and the MOVES to predict the road-level emission rates of NO and CO 2 emissions of LDGVs. In addition, we employed the Boruta algorithm to capture the key influencing factors and promote prediction performance. The enhanced model outperformed MOVES and achieved higher R2 values. On average, the improvement for CO 2 was 0.132, and for NO, it was 0.261. This work will provide references for MOVES improvements in practical scenarios and better predict pollutant emissions for LDGVs using limited resources of field tests in cities outside the US. • Integrating engine characteristics with the MOVES model can improve model performance. • Integrating machine learning with MOVES performs well in prediction of vehicle CO 2 and NO emission. • The proposed emission model provides a possibility for calculation rather than costly an experiment in countries outside the USA. [ABSTRACT FROM AUTHOR]

• Adasyn and t-SNE are used to pre-process the collected rockburst data. • SVM, BP, RBF, RF and ELM optimized by global optimization algorithm are used to predict rockburst intensity. • An improved D-S evidence theory rockburst prediction fusion model based on multiple machine learning algorithms is raised. • The fusion model predicts much better than single algorithm model in engineering application. Accurate prediction of rockburst hazards is an effective means to improve the development and utilization of underground space. When using a single machine learning algorithm for rockburst prediction, the reliability of the classification results can hardly be guaranteed. In this paper, a fusion model for rockburst prediction based on multiple machine learning algorithms is proposed in combination with D-S evidence theory. Six characteristic parameters (σ θ , σ c , σ t , SR , BR and Wet) were statistically analyzed for 304 sets of rockburst cases, and the data had outliers and class imbalances. The box plot method was used to detect replacement of a small number of outliers, and the Adasyn oversampling method eliminated the effect of data class imbalance. The visualization of the data by using the t-SNE method showed improved classifiability. SVM, BP, RBF, RF and ELM rockburst prediction models were developed with the six characteristic parameters as model inputs. In addition, the global optimization algorithms were used to find the optimal hyperparameters of the five machine learning algorithms. The accuracy of the optimized models was improved by 2.63%, 5.27%, 2.63%, 6.58% and 7.5% compared to the unoptimized models. Based on the prediction results, the precision was proposed as the fusion index. Additionally, based on improved D-S evidence theory, a fusion model for rockburst prediction was developed with five optimized machine learning algorithm models as base classifiers. Finally, the fusion model was applied to the rockburst prediction of Jiangbian Hydropower Station and Sanshan Island Gold Mine in China with the accuracy of 92.86%, and the prediction was outperformed by a single base classifier. The fusion model compensated for the uncertainty and poor robustness of the prediction results of the single-base classifier, and improved the accuracy and reliability of rockburst prediction. [ABSTRACT FROM AUTHOR]

Predicting the stock price is challenging because of its volatility, high dimensions, and complex non-linearity. The multitask learning methods can capture the internal relationship among sub-tasks and obtain better prediction effect than the traditional single-task learning methods. However, most multitask learning methods ignore the inherent distribution of the original samples, which fails at achieving good generalization performance. In this paper, we first present an asymmetric squared ɛ -insensitive loss function, which can improve the generalization ability of the regressor by adjusting the asymmetric parameter. Then, an asymmetric proximal support vector regression (a-PSVR) model is proposed, which greatly improves the flexibility of proximal support vector regression (PSVR). Based on different multitask learning assumptions, two multitask learning asymmetric proximal support vector regression algorithms, i.e., MTL-a-PSVR and EMTL-a-PSVR, are advanced. Both multitask learning algorithms can obtain optimal solutions by solving quadratic programming problems. Additionally, a special case of multitask learning proximal support vector regression (MTL-PSVR) is introduced by analyzing the asymmetric squared ɛ -insensitive loss function. To illustrate the merit of the methods, the proposed models are applied to predict the trends of stock market indices in China and the U.S. and stock prices of four Chinese securities companies. The experimental results demonstrate the significant advantages of the proposed algorithms in prediction effect and generalization performance. • An ɛ -insensitive loss function is presented for asymmetrically distributed data. • The a-PSVR has better prediction performance than proximal support vector regression. • A multitask joint learning model is proposed to perform the stock market forecast. • The cross-relations and asymmetry among stock data were considered simultaneously. [ABSTRACT FROM AUTHOR]

Modeling interpretable artificial intelligence (AI) for flood forecasting represents a serious challenge: both accuracy and interpretability are indispensable. Because of the uncertainty and nonlinearity of flood, existing hydrological solutions always achieve low prediction robustness while machine learning (ML) approaches neglect the physical interpretability of models. In this paper, we focus on the need for flood forecasting and propose an interpretable Spatio-Temporal Attention Long Short Term Memory model (STA-LSTM) based on LSTM and attention mechanism. We use dynamic attention mechanism and LSTM to build model, Max-Min method to normalize data, variable control method to select hyperparameters, and Adam algorithm to train the model. Emphasis is placed on the visualization and interpretation of attention weights. Experiment results on three small and medium basins in China suggest that the proposed STA-LSTM model outperforms Historical Average (HA), Fully Connected Network (FCN), Convolutional Neural Networks (CNN), Graph Convolutional Networks (GCN), original LSTM (LSTM), spatial attention LSTM (SA-LSTM), and temporal attention LSTM (TA-LSTM) in most cases. Visualization and interpretation of spatial and temporal attention weights reflect the reasonability of the proposed attention-based model. [ABSTRACT FROM AUTHOR]

• Speed, acceleration and tracking are used to analyzed mixed traffic flow safety. • 3 conflict regions are divided based on Haar-Adaboost algorithm. • Traffic characteristics with and without conflicts in three regions are compared. • New safety factors of mixed traffic flow at intersection are proposed. Mixed traffic is the typical characteristic of urban traffic in China. Especially on the crosswalks at signalized intersection, mixed traffic flow is large, traffic conflicts happen frequently. So, the traffic safety analysis is one of the research directions at signalized intersection. The main conflicts on the pedestrian crosswalk include the conflict among pedestrians and non-motorized vehicles as well as the conflict between the right-turning motor vehicles and pedestrians. Several impacts are imposed on the order of mixed traffic flow on the crosswalk by the above conflicts. In this paper, on the basis of on-the-spot filming and investigation, 3 regions are categorized based on Harr-Adaboost algorithm according to traffic characteristics of mixed traffic flows. Typical parameters such as speed and trajectory of pedestrian, non-motorized vehicle and right-turning motor vehicle as well as the variation of each characteristic results from the traffic conflicts in 3 regions including the pedestrian crosswalk and its vicinity are analyzed. The concluded characters could be used to optimize the intersection design and traffic control and improve the safety of mixed traffic individuals. [ABSTRACT FROM AUTHOR]

• Extended the traditional planned behavior theory. • An elevator safety management evaluation method based on machine learning is proposed. • Provided suggestions for the development of elevator installation in old residential quarters. With the aggravation of China's aging population problem, the elevator renovation in old residential areas has developed rapidly in the field of people's production and life. However, at present, elevator installation in old residential quarters in China shows slow progress. Therefore, due to the problems of poor accuracy of traditional elevator safety evaluation methods, the disadvantages of human factors and the complicated safety management of elevators, this study proposes an elevator safety management evaluation method based on machine learning. Based on this, first of all, aiming at the contradiction that residents' willingness are difficult to be coordinated and unified, based on the theory of planned behavior and from the perspective of equity perception, social justice theory is introduced to construct and expand the TPB model and explore the influence mechanism of various potential variables. Then the precision of elevator safety evaluation method is not high and the complexity of elevator safety management. An elevator safety management evaluation method based on machine learning is proposed. Use safety checklist to collect elevator safety status data and conduct safety inspection. The importance and degree of each factor affecting elevator safety are considered by table analysis method and fuzzy mathematics theory. The machine learning principle is applied to the evaluation results, and the existing maintenance knowledge of the evaluation knowledge base is combined to provide users with comprehensive and effective Suggestions and measures for rectification. The practical application shows that this method can find out the potential vulnerabilities in the elevator system management and operation, and reduce the risks. Finally, based on the empirical results, this paper expounds the ways to improve residents' willingness to install elevators and puts forward specific and effective elevator safety measures, so as to provide decision-making reference for the smooth implementation of the installation of elevators in old residential areas in China. [ABSTRACT FROM AUTHOR]

• A deep learning algorithm is used to build a comprehensive drought monitoring model. • Multi-source remote sensing data is processed as input data. • The comprehensive drought model has good applicability in the monitoring of meteorological drought and agricultural drought. • The model successfully monitored a drought process in Henan Province, China. • This study provides a new method for the comprehensive assessment of regional drought. Drought is a popular scientific issue in global climate change research. Accurate monitoring of drought has important implications for the sustainable development of regional agriculture in the context of increasingly complex global climate change. Deep learning is a widely used technique in the field of artificial intelligence. However, ongoing on drought monitoring using deep learning is relatively scarce. In this paper, the various hazard factors in drought development were comprehensively considered based on satellite data including Moderate Resolution Imaging Spectroradiometer (MODIS) and tropical rainfall measuring mission (TRMM) as multi-source remote sensing data. By using the deep learning technique, a comprehensive drought monitoring model was constructed and tested in Henan Province of China as an example. The results showed that the comprehensive drought model has good applicability in the monitoring of meteorological drought and agricultural drought. There was a significant positive correlation between the drought indicators of the model output and the comprehensive meteorological drought index (CI) measured at the site scale. The consistency rate of the drought grade of the two models was 85.6% and 79.8% for the training set and the test set, respectively. The correlation coefficient between the drought index of the model and the standard precipitation evapotranspiration index (SPEI) was between 0.772 and 0.910 (P < 0.01), which indicated a strong level of significance. The correlation coefficient between the drought index of the model and the soil relative moisture at a 10 cm depth was greater than 0.550 (P < 0.01), and there was a good correlation between them. This study provides a new method for the comprehensive assessment of regional drought. [ABSTRACT FROM AUTHOR]

• Proposed a knowledge transfer method to promote the utilization of emergency experience and get it reused. • Adaptively combined policy distillation with actor-critic structured multi-agent reinforcement learning algorithm. • Developed a fast emergency decision making method for freeway accident optimal onsite disposal. • Established an MDP model to simulate task-level accident disposal, modelled commonality among different freeway accidents. A large number of freeway accident disposals are well-recorded by accident reports and surveillance videos, but it is not easy to get the emergency experience reused from past recorded accidents. To reuse emergency experience for better emergency decision-making, this paper proposed a knowledge-based experience transfer method to transfer task-level freeway accident disposal experience via multi-agent reinforcement learning algorithm with policy distillation. First, the Markov decision process is used to simulate the emergency decision-making process of multi-type freeway accident scene at the task level. Then, an adaptive knowledge transfer method named policy distilled multi-agent deep deterministic policy gradient (PD-MADDPG) algorithm is proposed to reuse experience from past freeway accident records to current accidents for fast decision-making and optimal onsite disposal. The performance of the proposed algorithm is evaluated on instantiated cases of freeway accidents that occurred on the freeway in Shaanxi Province, China. Aside from achieving better emergency decisions performance than various typical decision-making methods, the result shows decision maker with transferred knowledge owns 65.22%, 11.37%, 9.23%, 7.76% and 1.71% higher average reward than those without in the five studied cases, respectively. Indicating that the emergency experience transferred from past accidents contributes to fast emergency decision-making and optimal accident onsite disposal. [ABSTRACT FROM AUTHOR]

• Machine learning was applied to quantify the effects of stand, climate and soil on biomass of mixed forests with good accuracy. • Quantifying the importance of various environmental attribute factor to forest biomass depends on the combination of environmental variables and modeling methods. • Environmental variables including degree-days above 18 °C, bulk density and soil pH were most important predictors. Forest biomass is influenced by multiple environmental factors. Multi-source data on site-specific soil, climate, and stand factors are essential for stand biomass prediction. While previous studies concerning planted forest biomass at stand level highlighted the importance of environmental factors, few have been conducted on the effects of climate and soil on stand biomass estimation, especially for natural mixed forest with complicated stand structure. Machine learning (ML) algorithms provide new tools for examining the effects, but the applications are still limited. Therefore, the objectives of this paper were to develop ML models for stand biomass estimation with stand and multiple environmental predictors, and quantify the relative importance of environmental variables. Tree above- and below-ground biomass at stand level was set as output variable with the random forest (RF) and boosted regression tree (BRT) regression methods. The data were from 286 sample plots from the National Forest Inventory (NFI) in Jilin Province, northeast China. The results showed that models with the inclusion of stand, soil, and climate variables explained > 89% of forest biomass variations. BA (stand basal area) and H (stand average height) were the most important stand variables, DD18 (degree-days above 18 °C) was the most important climate variable, and bdod (bulk density) and pH were the most important soil variables. Relative importance of climate and soil factors was 0.5% to 5.1% and 1.2% to 4.1%, respectively, which were weak but important predictors of stand biomass. In the RF model, climate variables were more important than soil variables, but the opposite in the BRT models. We concluded that above forest stand, climate and soil factors were significant input variables for regional forest biomass mapping using ML. [ABSTRACT FROM AUTHOR]

• Machine learning is used in spatial location choices of solar power plants. • Random Forest model presents the better performance. • Vegetation index and distance to power grid are the dominant predictors. • National-scale solar photovoltaic installations probability map is produced. The optimum site selection of solar photovoltaics power plant across a given geographic space is usually assessed by using the geographic information system based multi-criteria decision making methods with various restriction criteria, while such evaluation results vary with criteria weights and are difficult to be validated in real life practices. To address this issue, this paper uses a national inventory dataset of large-scale solar photovoltaics installations (the land coverage area ≥ 1 hm2) to investigate the spatial location choices of solar power plants with the aids of interpretable machine learning techniques. A total of 21 geospatial conditioning factors of solar energy development are considered. The location choices of solar photovoltaics installation are then modeled with the multi-Layer perceptron, random forest, extreme gradient boosting models for each land cover type (e.g. cropland, forest, grassland, and barren). The SHapley additive explanation and variable importance measure methods are adopted to identify key criteria and their influences on the solar photovoltaics installation location selection. Results indicate that the random forest model presented the better performance among three machine learning models. The relative importance of conditioning factors revealed that the vegetation index and distance to power grid were always the most important predictors of solar photovoltaics installation location. Furthermore, topographical factors and transportation convenience may have a moderate impact on the spatial distribution of solar photovoltaics power stations. Unexpectedly, most of resources endowment and socio-economic factors play a negligible role in determining the optimal siting of solar power farms. Simulated solar photovoltaics installations probability maps illustrated that the most suitable regions account for 4.6 % of China's total land area. The evidence-based method proposed in this research can not only help identify suitable solar photovoltaics farm locations in terms of various decision-making criterion, but also provide a robust planning tool for sustainable development of solar energy sources. [ABSTRACT FROM AUTHOR]