Search

The continuous development of Educational Data Mining (EDM) and Learning Analytics (LA) technologies has provided more effective technical support for accurate early warning and interventions for student academic performance. However, the existing body of research on EDM and LA needs more empirical studies that provide feedback interventions, and more attention should be paid to primary and secondary school students. This study proposed a data-driven precision teaching intervention mechanism combining EDM and LA technologies. The proposed mechanism aims to assist teachers in predicting students' academic performance and implementing corresponding interventions. This approach enables early warnings and reminders for students in crisis, and offers teaching assistance and support tailored to students at different levels. A quasi-experimental design was employed to examine the impact of the data-driven precision teaching intervention mechanism on secondary school students' learning outcomes. A total of 142 seventh-grade students participated in the intervention experiment, with an experimental group (50) receiving the data-driven precision teaching intervention, control group2 (48) receiving a group intervention stratified by teacher experience, and control group1 (44) receiving a traditional group intervention. Posttest data were collected after three rounds of intervention. Compared to the two control groups, students in the experimental group demonstrated superior academic achievement, intrinsic motivation, self-efficacy, and meta-cognitive awareness. These findings indicate that the data-driven precision teaching intervention approach positively impacted students' academic development, and effectively promoted their personalized learning. The findings provide pedagogical insights into the application of EDM in conjunction with LA prediction and actionable interventions. [ABSTRACT FROM AUTHOR]

Sustainable manufacturing is crucial to achieving carbon neutrality targets. However, research on the sustainability of manufacturing systems is limited, and high consumption, low efficiency, and high emissions have resulted in high resource consumption and rapid environmental degradation. Therefore, it is of great importance to establish an evaluation and improvement indicator system conducive to sustainable development. To this end, this study developed a data-driven methodology for evaluating and enhancing the sustainability of manufacturing systems. Manufacturing system production process data, with data dimensions unified via the emergy method, were used to construct a sustainable development evaluation model that includes four perspectives: economy, environment, society, and sustainability. The model was applied to a flange production workshop in China to analyze the interrelation mechanisms among energy consumption, resource consumption, and environmental pollution, and identify optimization schemes to improve sustainability. After implementing these optimization schemes, the emergy yield rate (EYR) of the flange increased by 23.40%, the environmental load rate (ELR) decreased by 19.03%, the per capita emergy (EPP) increased by 6.88%, and the emergy-based sustainability index (ESI) increased by 52.76%. The method presented herein offers a novel and effective tool to analyze and visualize sustainable development in manufacturing systems and identify the relationship between technology and management in the manufacturing industry; however, this method is based on historical data and rules, and lacks of flexible response to unknown situations. The results provide a reference for enterprises to achieve sustainable and lean manufacturing. [ABSTRACT FROM AUTHOR]

Current irrigation water use (IWU) estimation methods confront uncertainties warranting further attention, primarily stemming from constraints within model structure and data quality. This study proposes a hybrid framework that integrates multiple machine learning (ML) methods with theory‐guided strategies to calculate IWU for three principal cereal crops within the Chinese agricultural landscape. We generated high resolution time series data sets of evapotranspiration and surface soil moisture (SM) using remote sensing resources. ML techniques, along with the Bayesian three‐cornered hat ensemble, were employed to drive multiple remote sensing‐derived data sets in IWU calculation. We applied two theory‐guided mechanisms to quantify irrigation signals: first, converting original SM values into logarithmic terms, and second, extracting process‐based SM residuals. Proposed framework has been validated at 12 field stations across China, yielding coefficient of determination (R2) ranging from 0.54 to 0.70, and root mean square error (RMSE) spanning 278–335 mm/yr. Our framework demonstrates considerable strength in IWU estimation when compared to reported IWU values form 341 cities across China. Specifically, for rice, wheat, and maize, the R2 values range from 0.78 to 0.83, 0.68 to 0.76, and 0.53 to 0.64, respectively, with corresponding RMSE measuring 0.22–0.25, 0.10–0.12, and 0.11–0.13 km3/yr, respectively. These findings highlight the effectiveness of theory‐guided strategies in discerning irrigation‐related information, thereby improving overall model performance. Attention should be directed toward the uncertainties in evapotranspiration and precipitation products on model performance, which remained modest, with a relative change of less than 5%. Key Points: Hybrid framework is developed to estimate irrigation water use (IWU) for three staple cereal crops in ChinaMachine learning is employed to drive multiple remote sensing‐derived products for precise IWU estimationProposed framework accurately estimates IWU and incorporates theory‐guided module to reveal implicit irrigation signal [ABSTRACT FROM AUTHOR]

Problem definition: We consider intertemporal pricing in the presence of reference effects and consumer heterogeneity. Our research question encompasses how to estimate heterogeneous consumer reference effects from data and how to efficiently compute the optimal pricing policy. Academic/practical relevance: Understanding reference effects is essential for designing pricing policies in modern retailing. Our work contributes to this area by incorporating consumer heterogeneity under arbitrary distributions. Methodology: We propose a mixed logit demand model that allows arbitrary joint distributions of valuations, responsiveness to prices, and responsiveness to reference prices among consumers. We use a nonparametric estimation method to learn consumer heterogeneity from transaction data. Further, we formulate the pricing optimization as an infinite horizon dynamic programming problem and solve it by applying a modified policy iteration algorithm. Results: Moreover, we investigate the structure of optimal pricing policies and prove the suboptimality of constant pricing policies even when all consumers are loss-averse according to the classical definition. Our numerical studies show that our estimation and optimization framework improves the expected revenue of retailers via accounting for heterogeneity. We validate our model using real data from JD.com, a large E-commerce retailer, and find empirical evidence of consumer heterogeneity. Managerial implications: In practice, ignoring consumer heterogeneity may lead to a significant loss of revenue. Furthermore, heterogeneous reference effect offers a strong motive for promotions and price fluctuations. History: This paper has been accepted as part of the 2020 MSOM Data Driven Research Challenge. Funding: This work was partially supported by the National Natural Science Foundation of China [Grant 71991462]. Supplemental Material: The e-companion is available at https://doi.org/10.1287/msom.2022.1134. [ABSTRACT FROM AUTHOR]

In power systems with high penetration of renewable energy, traditional physical model-based optimal dispatch methods suffer from modeling difficulties and poor adaptability, while data-driven dispatch methods, represented by reinforcement learning, have the advantage of fast decision making and reflecting long-term benefits. However, the performances of data-driven methods are much limited by the problem of distribution shift under insufficient power system scenario samples in the training. To address this issue, this paper proposes an improved scenario division method by integrating the power system's key physical features and the data-driven variational autoencoder (VAE)-generated features. Next, based on the scenario division results, a multi-scenario data-driven dispatch model is established. The effectiveness of the proposed method is verified by a simulation conducted on a real power system model in a province of China. [ABSTRACT FROM AUTHOR]

Although research has made progress in searching for an integrative factor structure of career indecision in Western cultural contexts, such an integrative structure of career indecision remains understudied in East Asia. To search for a culturally appropriate integrative factor model of career indecision in China and South Korea, the current study used a data-driven approach to summarize correlational data of indecision-related constructs in China and South Korea. Based on 16 and 21 correlational matrices in China and South Korea, respectively, results suggested that a five-factor structure (i.e., neuroticism/negative affectivity, need for information, choice/commitment anxiety, lack of readiness, and interpersonal conflicts) can adequately and parsimoniously capture major indecision factors in these two countries. By offering a universal framework of career indecision in China and South Korea, the integrative model shows potential to accelerate knowledge accumulation regarding career indecision in this cultural context. Notably, this study suggests that need for information and choice/commitment function as separate factors in China and South Korea, while neuroticism/negative affectivity, lack of readiness, and interpersonal conflicts are culturally universal across Eastern and Western cultural contexts. Thus, this study has potential to enable cross-cultural comparison and accumulation of indecision research in these two cultural contexts. [ABSTRACT FROM AUTHOR]

We study a multi-objective optimization model of a stochastic multimodal transportation network considering key impact factors such as transit cost, time, and transport mode schedule while minimizing total transportation cost and transportation time. In this study, we apply the Monte Carlo simulation to deal with the stochastic transportation time in the network and propose a data-driven approach that combines historical data and the dataset generated by the data mining algorithm to accelerate the search for the nondominated solution in the simulation. To validate the effectiveness of the proposed Data-Driven Multi-Objective Simulation Ant Colony (DD-MSAC) algorithm, we compare the optimum-seeking performance and the running time consumption of the Nondominated Sorting Genetic Algorithm-II (NSGA-II) and the Multi-Objective Simulation Ant Colony (MSAC) algorithm. Then, the MSAC algorithm is adopted as the benchmark for the comparison study on the solving performance of the proposed DD-MSAC algorithm. We conducted 30 times simulation run under different network scales in our numerical examples to show that the DD-MSAC algorithm can be equally effective as the non-data-driven MSAC algorithm in finding a nondominated solution as the average error does not exceed 5%. Meanwhile, we analyze the impact of different data-driven approaches, including data pool and support vector machine, on the solution quality and the running time. Finally, we use an example of China's Belt Road Initiative to verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Electricity is an essential resource that plays a vital role in modern society, and its demand has increased rapidly alongside industrialization. The accurate forecasting of a country's electricity demand is crucial for economic development. A high-precision electricity forecasting framework can assist electricity system managers in predicting future demand and production more accurately, thereby effectively planning and scheduling electricity resources and improving the operational efficiency and reliability of the electricity system. To address this issue, this study proposed a hybrid forecasting framework called T-LGBKS, which incorporates TPE-LightGBM, k-nearest neighbor (KNN), and the Shapley additive explanation (SHAP) methods. The T-LGBKS framework was tested using Chinese provincial panel data from 2005 to 2021 and compared with seven other mainstream machine learning models. Our testing demonstrated that the proposed framework outperforms other models, with the highest accuracy ( R 2 = 0.9732 ). This study also analyzed the interpretability of this framework by introducing the SHAP method to reveal the relationship between municipal electricity consumption and socioeconomic characteristics (such as how changes in economic strength, traffic levels, and energy structure affect urban electricity demand). The findings of this study provide guidance for policymakers and assist decision makers in designing and implementing electricity management systems in China. [ABSTRACT FROM AUTHOR]

To improve the economy and meet the demand for transporting different oil products, multi-product pipelines are utilized to transport multi-products in sequence in the same pipelines. It is fundamentally important for operators in stations to know the accurate location of the head of each batch interface, to swing the valve at a station, and deliver oil products with minimal contamination. However, it is difficult to determine the location of the batch interface accurately, due to the complex hydrothermal conditions and mixed oil segment. In this paper, a hybrid intelligent framework is proposed to track the real-time batch interface of multi-product pipelines. The batch injection judgment module is applied to determine whether there is a new product batch injected in the pipeline. Applying the upstream and downstream flowrate, the volume calculation model is proposed to track the real-time location of each batch interface. Considering the deviation between the estimated location and the actual location of the batch interface, a self-learning modified model is proposed to compensate for the tracking errors. Taking a real-world multi-product pipeline network in China as an example, the accuracy and efficiency of the proposed model are verified. The results suggested that the hybrid intelligent framework outperforms other comparative methods, with minimal tracking errors being 3.79 min ● A hybrid framework is proposed for batch tracking of multi-product pipelines. ● The volume calculation model is the basic to track the location of each batch head. ● A self-learning modified model is proposed to compensate for the tracking errors. ● A real pipeline network is used to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

• A new data-driven model (SeismNet) for simultaneous prediction of magnitude and instrumental intensity in the north–south seismic belt of China is proposed. • SeismNet fulfills the requirement of rapid and accurate prediction of magnitude and instrumental intensity in earthquake early warning. • The performance of SeismNet is better than that of the baseline model and allows for more desirable threshold alarms. • SeismNet consistently predicts better than the traditional method Pd and single-task model with the increase of input data. The seismic activity in the north–south seismic belt of China is among the highest in the world. Predicting instrumental intensity and magnitude after an earthquake mitigates regional seismic disasters. The standard workflow for prediction involves building empirical formulas using characteristic parameters of the initial arrival seismic wave, but this method has limitations in accuracy. Recent data-driven models have shown promise in predicting instrument intensity and magnitude. Still, this is currently done mainly on a single-task basis and does not consider whether a multi-task model can utilize complementary information from different tasks to improve overall performance. This study proposes a data-driven multi-task model called SeismNet, which can simultaneously predict instrument intensity and magnitude. We tested the effectiveness of SeismNet using ground motion records of the north–south seismic belt of China. The model can predict instrument intensity and magnitude more rapidly and accurately than the baseline and single-task models, with increasing accuracy as the input seismic wave duration increases. We also tested the method on three destructive earthquake events (Ms > 6.5) that occurred in China and found that at 3 s after the P-wave arrival, the prediction is almost consistent with the observation. Overall, this study offers a new method for improving earthquake prediction accuracy in the North-South seismic belt of China. [ABSTRACT FROM AUTHOR]

In this study, a data-driven way is proposed to evaluate and optimize the sustainable development of the logistics industry (LI). Based on a comprehensive consideration of economic, societal, and environmental factors, an evaluation index system was established for the sustainable development of the logistics industry (LISD). Logistics industry-related data were collected from the Yangtze River Delta (YRD) from 2011 to 2020. The anti-entropy method was used to determine the index weight and process the data. Furthermore, the coupling harmonization degree and barrier degree models were used to analyze the coordinated development of each subsystem and identify key obstacles. Our results indicate that there are significant temporal and spatial differences in the level of LISD in YRD, with Shanghai (score 0.4834) being the best and Anhui (score 0.4553) the worst, showing a wave-like evolution in time. The coupling and coordination states among the subsystems are significantly different, with that of environmental benefits and other subsystems being poor. Moreover, innovation ability and environmental benefits are the main obstacle factors of this system. Based on the results of this study, targeted optimization countermeasures are put forward and evaluation indicators and research methods are suggested, which will provide the government and practitioners decision support, as well as provide theoretical and methodological support for LISD. [ABSTRACT FROM AUTHOR]

• A novel hybrid model and data-driven voltage stability online assessment approach is proposed. • The parameters in the model-driven method are modified based on the response data. • To improve accuracy, impedance difference is included in the data-driven input data. • The proposed method combines the clear mechanism of the model-driven and high accuracy of the data-driven. With the continuously increasing integration of renewable energy sources into power grids, the dynamic response of a power system is becoming more complex. For example, the interaction between the dynamic loads and low-voltage ride-through of renewable energy generators makes the voltage response more rapid and unpredictable. Ensuring the accuracy and speed of traditional voltage stability assessment methods is difficult. This study developed a novel hybrid model and data-driven voltage stability assessment approach. First, the equivalent parameters of a power system were calculated based on the measured data, and the parameters were constantly modified based on the response data. To further improve the accuracy of the approach, a data-driven method was introduced to correct the assessment results using a Thevenin equivalent-based assessment. The difference between the Thevenin and system impedances, which better reflects the system stability, was included in the data-driven input data. Finally, by combining the clear physical mechanism of the model-driven method and high accuracy of the data-driven method, the final the assessment process was a serial combination of the model- and data-driven methods. The effectiveness of the method was verified using an IEEE New England 10-generator 39-bus test system and a 100-bus actual system in China. The results showed that the method developed was more accurate and had higher robustness under data loss and noise conditions than other methods. [ABSTRACT FROM AUTHOR]

Polarization information can greatly improve the ability of detection, parameter retrieval, and classification for entomological radar. In recent, the instantaneous fully polarimetric measurement technique is used in entomological radar, so as to relax the restriction of invariant orientation during observation compared to the typical vertical-looking radar with linear-polarized rotation configuration. However, the fully polarimetric measurement is based on a multichannels’ radar system, and the imbalance and crosstalk between channels, namely, polarimetric errors, will severely affect the measurement of the polarimetric scattering matrix (PSM). Thus, polarimetric calibration is essential to obtain the accurate polarization information of targets. In contrast to inefficient and manual calibration methods, a data-driven polarimetric calibration method is proposed based on the assumption of reciprocity and bilateral symmetry of insects in this article. The polarimetric errors are elaborately decomposed into two components, which could be estimated by reciprocity and bilateral symmetry, respectively. In addition, because the proposed method is data-driven, the calibration process could be automatically executed to compensate for the temporal-variant polarimetric errors induced by temperature change and, thus, suitable for the long-term operation of entomological radar. Simulations and experiments are carried out to evaluate the performance of the proposed calibration method. Results show that it could achieve high accuracy when the number of insects used as calibrators is large enough. The proposed method has been applied in Ku-band high-resolution fully polarimetric entomological radars for cross-border migratory insect observation in Yunnan province, China. [ABSTRACT FROM AUTHOR]

Identifying and assessing the disaster risk of landslide-prone regions is very critical for disaster prevention and mitigation. Owning to their special advantages, neural network algorithms have been widely used for landslide susceptibility mapping (LSM) in recent decades. In the present study, three advanced neural network models popularly used in relevant studies, i.e. artificial neural network (ANN), one dimensional convolutional neural network (1D CNN) and recurrent neural network (RNN), were evaluated and compared for LSM practice over the Qingchuan County, Sichuan province, China. Extensive experimental results demonstrated satisfactory performances of these three neural network models in accurately predicting susceptible regions. Specifically, ANN and 1D CNN models yielded quite consistent LSM results but slightly differed from those of RNN model spatially. Nevertheless, accuracy evaluations revealed that the RNN model outperformed the other two models both qualitatively and quantitatively but its complexity was relatively high. Experiments concerning training hyper-parameters on the performance of neural network models for LSM suggested that relatively small batch size values with Tanh activation function and SGD optimizer are essential to improve the performance of neural network models for LSM, which may provide a thread to help those who apply these advanced algorithms to improve their efficiency. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Agricultural Science & Technology (1008-0864) is the property of Journal of Agricultural Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• A novel two-stage flexibility evaluation methodology is proposed for CIES. • A data-driven scenario analysis is developed considering environmental characteristic. • Flexibility supply models of flexible resources are improved to increase accuracy. • Fine-grained flexibility adjustment domain is portrayed through envelope. • The approach manages to accurately quantify and evaluate CIES operating flexibility. Flexibility operation and evaluation have become central and critical for grid integration of high percentage of renewable energy generations (REGs). However, the interactions between multiple energy forms in community integrated energy system (CIES) and the uncertainty of REG significantly complicate the quantification of flexibility. To this end, a novel two-stage data-driven flexibility evaluation methodology is proposed for CIES. The first stage performs optimal scheduling of multiple flexible resources, where the flexible thermal comfort requirements of users in integrated response demand are considered by introducing a predicted mean vote index. The second stage refines the flexibility supply model for flexible resources, and carves out the system flexibility supply domain by enveloping the net load. To overcome the uncertainty of REG, a data-driven scenario analysis approach is developed, which fully captures the renewable output characteristics under different climate environments and avoids complicated explicit feature model construction. Furthermore, a set of evaluation metrics is proposed from the aspect of direction, amount, and frequency to quantify the flexibility. The effectiveness and accuracy of the proposed methodology are verified by applying it to a modified CIES located in North China. The sensitivity analysis of multiple time scales and flexible resources to operational flexibility and economy of CIES is presented, which provides guidelines for the efficient allocation of flexible resources and expand planning of CIES. [ABSTRACT FROM AUTHOR]

Improving passive design methods are important for achieving zero-carbon building (ZCB) targets. Data-driven design approaches are more accurate than conventional methods for multiple-objective optimization (MOO) targets such as carbon emissions (CE), economics, and thermal comfort. In this study, a comprehensive data-driven-based PSO-SVM-NSGA-III method that assists in optimizing passive design parameters are proposed. First, the simulation results for the objectives of CE, incremental cost (IC), and time not comfort (TNC) are performed for an office building in a cold region in China using EnergyPlus and jEPlus software. Then, key influencing factors are chosen via a sensitivity analysis. Second, nonlinear mapping relationships between the passive design parameters and objectives are established with the PSO-SVM model. Compared to the BPNN, SVM, and PSO-BPNN algorithms, the PSO-SVM model exhibits superior prediction performance, with R 2 values of 0.977, 0.925, and 0.903 for CE, IC, and TNC, respectively. Third, the nonlinear mapping relationships are used in the established objective functions of NSGA-II and NSGA-III. NSGA-III performed 100 iterations within 21 min and exhibited robust diversity within its population, with a hypervolume value of 0.738. Finally, the Pareto-optimal solution set is formed with the PSO-SVM-NSGA-III framework. This data-driven method offers an efficient approach for improving building performance. • Data-driven-based PSO-SVM-NSGA-III method for optimizing ZCBs is proposed. • Simulation results generated for office building in a cold region in China. • Key influencing factors are chosen via a sensitivity analysis. • PSO-SVM model exhibits superior prediction performance. • Data-driven method offers an efficient approach for improving building performance. [ABSTRACT FROM AUTHOR]

Aiming at a large number of decentralized resources such as rural biomass, rooftop photovoltaic, and decentralized wind power, a novel rural virtual power plant (VPP) has been conceptualized. The VPP is integrated by biomass waste conversion system (BWC), carbon to energy (C2P), demand response aggregator (DRA), and distributed renewable energy (DRE), namely, BDCD-VPP. Then, this paper proposes a data-driven two-stage robust optimization dispatching model for BDCD-VPP considering carbon-green certificates equivalent conversion mechanism. This model aims to address the uncertainty of wind power plants (WPP) and photovoltaic (PV) power generation. Strong duality theorem (SDT) and C&CG algorithm are applied to construct this model. Thirdly, the Aumann-Shapley method (A-S) was enhanced by incorporating risk factor, cost factor, and carbon reduction factor. This refinement results in the development of a synergistic scheduling revenue allocation method for electricity‑carbon-green certificates. Finally, the Lankao rural energy revolution pilot program in China is selected as the case study, the results showed: (1) The BDCD-VPP aggregates distributed energy sources such as the rural WPP and the PV to realize electricity‑carbon-electricity cycle effect. The BDCD-VPP generates a green certificate revenue of 47.17¥/MWh and exhibited carbon emissions of 0.37 t/MWh. The proposed Carbon-Green Certificates Equivalent Conversion Mechanism increases BDCD-VPP benefit ratio by 3.52%. (2) The proposed two-stage robust optimization dispatching model enhances the ability of BDCD-VPP to adapt to uncertainty. Compared to the day-ahead stage, biomass power generation (BPG) and waste power generation (WPG) increase upward peaking power by 24.05% and 9.99% in intra-day stage. Flue gas treatment system (FG-TS), gas-power plant carbon capture (GPPCC) and power to gas (P2G) increase downward peaking power by 65.15%, 70.99% and 25.94%. (3) Utilizing the proposed benefit allocation methodology, BPG and WPG need to concede 38.25¥/MWh and 65.02¥/MWh for carbon emissions associated with electricity. WPP and PV need to concede 64.25¥/MWh and 33.71¥/MWh for power generation uncertainty. GPPCC, P2G, DRA, and small hydropower station (SHS) obtain revenues of 24.48 ¥/MWh, 55.07 ¥/MWh, 70.38 ¥/MWh, and 51.30 ¥/MWh. Compared to the A-S, the proposed benefit allocation methodology exhibits 6.92% improvement in satisfaction. Overall, the proposed data-driven two-stage robust optimization dispatching model and benefit allocation strategy facilitates the optimal aggregation and utilization of rural distributed energy resources, considering the interests of various stakeholders. This is conducive to achieving a clean and low-carbon transformation of the overall energy structure. • Proposed a novel rural virtual power plant considering biomass waste conversion and carbon to power. • Designed carbon-green certificate equivalence conversion mechanism. • Proposed a data-driven scenarios generation and reduction strategy for uncertainty factors. • Construct a two-stage robust optimization dispatching model and strong duality C&CG algorithm. • Construct an improved Aumann-Shapley-based benefit allocation strategy [ABSTRACT FROM AUTHOR]

As the main contributor of cadmium (Cd) pollution in China, industrial aqueous Cd emissions are influenced by both industrial and socioeconomic characteristics owing to their "environmental service" nature. It is essential to understand the relationship between these characteristics and industrial aqueous Cd emissions during industrialization. In this study, a data-driven framework was proposed to reveal these relationships. The framework comprises two key steps. i) Three state-of-the-art tree-based machine learning models, including LightGBM, Gradient Boosting Decision Tree and Random Forest, were trained to capture the relationships among variables. ii) Shapley additive explanation was utilized to decompose the contribution of the characteristics to the prediction for each sample. The trained LightGBM model demonstrated the most superior performance in predicting industrial aqueous Cd emissions in test datasets (R 2 = 0.881 ± 0.0431 ， R M S E = 58.260 ± 11.839 ， M A E = 27.743 ± 3.274), significantly overperforming traditional linear regression model. Our analysis revealed that during our sample period, the influence of industrial characteristics on regional industrial aqueous Cd emissions was approximately 1.796 times greater than that of socioeconomic characteristics. Shifts in the characteristics of the non-ferrous metal industry contributed to approximately 74% of the average increase in industrial aqueous Cd emissions in China approximately. Regional emissions were found to be positively affected by average size and density but negatively affected by the operation duration of local non-ferrous metal industrial firms. Further driver analysis showed that the growth trajectory of emissions in China can be split into three stages based on the main drivers and growth rate: 2000–2002, 2003–2004, and 2005–2007. The proposed framework overcomes the limitations of the previous methods in terms of application scope, potential factor considerations, and regression structure predefinition. Our analysis implies that policymakers should proactively adjust industrial policies and emissions regulations in response to market shocks and industrial shifts, to a better management of industrial aqueous Cd emissions. [Display omitted] [ABSTRACT FROM AUTHOR]

The construction of electronic government (e-government) systems is a process of continuous improvement. It is necessary to evaluate the performance of e-government systems regularly to improve the services provided by government agencies and enhance the exchange of information between governments and citizens. Evaluating e-government performance based on citizens' experience is a multiple criterion decision making (MCDM) problem under uncertainty, where assessments are qualitative, and many e-government system users are involved. Deriving criterion weights from a large amount of evaluation data is rarely discussed in previous MCDM studies. This paper proposes a data-driven evidential reasoning (DDER) method for evaluating e-government performance. A criteria framework from the citizens' experience perspective, including service guide clarity, site usability, information sharing, documentation, and the availability of e-services, is proposed. Belief structures are used to portray uncertain assessments from e-government system users. The criterion weights are learned from the data by minimizing the dissimilarity between the aggregation assessments of the alternatives on each criterion and citizens' historical observations on a whole. A case study is conducted in 16 cities of Anhui province in China to evaluate the performance of e-government systems. The ranking results verified the applicability and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The high penetration of renewable energy will substantially change the power system operation. Traditionally, the annual operation of a power system can be represented by some typical operation modes and acts as the basis for the power-system-related analysis. The introduction of highly penetrated renewable energy will make the power system operation mode highly diversified and variable. These modes may not follow traditional empirical patterns. In this paper, we propose a data-driven method based on high-dimensional power system operation data (including power flow, unit generation, and load demand) to identify the pattern of the operation modes and analyze the impact of high renewable penetration. Specifically, the proposed data-driven method is composed of simulation, preprocessing, clustering, dimension reduction, and visualization with the aim to provide an intuitive understanding of the operation mode variety under high renewable penetration. In addition, several indices are introduced to quantify the space dispersion, time variation, and seasonal consistency of operation modes. A case study on actual Qinghai provincial power system in China validates the effectiveness of the proposed data-driven method and indicates that the dispersion and time variation of operation mode will significantly increase in the beginning and then saturate with the increase in renewable penetration level. The operation mode is also less correlated with seasons in renewable energy dominated power system. [ABSTRACT FROM AUTHOR]

It is a significant trend that the Internet Content Providers (ICPs) improve the quality of service and reduce the cost of content distribution by the Content Delivery Networks (CDNs). In order to spend the less money to get better services, ICPs need to find a lot of information about CDNs, such as server deployment, performance, price and so on, to determine whether CDN services satisfy their requirements. Unfortunately, these information can't be obtained by third party due to business secret. ICPs still choose CDNs on the basis of one-sided viewpoint. For this reason, we have proposed a data-driven and the deep learning based CDN recommendation framework for ICPs. The contributions lie in: 1) A three-tier CDN recommendation framework is presented to achieve data-driven and the deep learning based recommendation service. 2) A CDN recommendation model is built based on the deep neural network, which improves the efficiency of the recommendation service and satisfies the personalized demand. 3) A prototype system is developed and deployed on the real-world large-scale Internet in China. Experimental results demonstrate that the correctness of the recommendation results is up to 91%, and degree of satisfaction reached 80%. [ABSTRACT FROM AUTHOR]

Consumers’ transformers play an important role in power systems, and they are essential for operation reliability and commercial benefits. In the past, maintenance personnel had to spend plenty of time on examining consumers’ transformers one by one. Nowadays, with the wide deployment of power user electric energy data acquire system (PUEEDAS), informative metering data are becoming available, which can be utilized for further condition monitoring. Thus, this paper proposes a data-driven abnormal condition monitoring algorithm of data acquisition for consumers’ transformers, which could timely send abnormal condition alerts to operators and maintenance personnel. In the proposed algorithm, Spearman's rank correlation coefficient is utilized to show the degree of correlation among phase currents, and its t-Statistics is used to determine whether abnormal condition of data acquisition exists based on the hypothesis testing. Finally, actual acquisition data from Zhejiang power system in China are employed to validate the effectiveness of the proposed algorithm, and to analyze the characteristics of normal and abnormal conditions, respectively. Sensitive analyses on different significant levels and sampling rates are performed for considering its impact on monitoring results; the application in real power systems is also given to demonstrate the practicality of the proposed algorithm. [ABSTRACT FROM AUTHOR]

• A novel vector field-based SVR for building energy consumption prediction (ECP) is proposed. • Nonlinearity of the ECP models is transformed into linearity via vector field-based SVR. • Two high precision, generalization capability, and robustness energy consumption prediction models are established. • A real case study demonstrates the superiority of this study compared with previous studies. Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Data-driven approaches, such as artificial neural networks, support vector regression, gradient boosting regression and extreme learning machine are the most advanced methods for building energy prediction. However, owing to the high nonlinearity between inputs and outputs of building energy consumption prediction models, the aforementioned approaches require improvement with regard to the prediction accuracy, robustness, and generalization ability. To counter these shortcomings, a novel vector field-based support vector regression method is proposed in this paper. Through multi-distortions in the sample data space or high-dimensional feature space mapped by a vector field, the optimal feature space is found, in which the high nonlinearity between inputs and outputs is approximated by linearity. Hence, the proposed method ensures a high accuracy, a generalization ability, and robustness for building energy consumption prediction. A large office building in a coastal town of China is used for a case study, and its summer hourly cooling load data are used as energy consumption data. The results indicate that the proposed method achieves better performance than commonly used methods with regard to the accuracy, robustness, and generalization ability. [ABSTRACT FROM AUTHOR]

• An adaptive soft sensor is developed by integrating NNG with an ARIMA model. • The soft sensor is utilized to predict the economic efficiency of the CDQ process. • An economic efficiency index is adopted to access the CDQ process. • A model-based optimization strategy is implemented. • The feasibility of the proposed method is illustrated with experiments. Energy conservation and emission reduction in steelmaking have received significant attention owing to the high amount of fossil energy consumption and emissions. Many methods have been adopted for saving energy, among which coke dry quenching (CDQ) is a cost-effective option. In this work, a CDQ process in a steel plant in China is studied. Here, an economic efficiency index is adopted to handle the trade-off between the steam productivity and the coke burning loss. The operation data analysis indicates that the supplementary air flow rate in the CDQ operation does not follow the variation in the discharge rate of incandescent coke adequately, and this results in an increase in the concentration of combustible gas in the exhaust gas and a decrease in economic efficiency. The correlation analysis results show that it is necessary to introduce several derived variables into the data-driven model of this process because these derived variables are more useful than a few original variables for the prediction purposes. Based on these analyses, a soft sensor is proposed by integrating a nonnegative garrote variable selection algorithm with an autoregressive integrated moving average model, which provides a good solution for the real-time prediction of the economic efficiency of the CDQ process. Using this soft sensor, model-based optimization can be conducted, the performance of which is verified with a virtual implementation on the historical operation data and experiments performed in a real CDQ system. The results indicate that there is considerable room for improving the economic efficiency of this process. [ABSTRACT FROM AUTHOR]

Highlights • A novel two-stage modeling framework based on event sequence is developed. • A SIASA algorithm is presented to re-optimize the solution of first-stage model. • A data-driven method is proposed to accomplish the fast optimization of pipeline scheduling. • The experimental results of 50 cases are given to illustrate the superiority of the proposed method. Abstract The detailed scheduling of distributing products through pipelines is one of the most essential tasks in the management of multiproduct pipelines. The current methods of scheduling optimization are still limited by the dilemma between optimality and efficiency, especially when dealing with real-world scheduling issues. This paper introduces a two-stage mathematical model based on the event sequence, whose model scale greatly decreases after stripping the terms of event sequence. Then, a data-driven method is presented to learn a large number of existing scheduling data and accelerate the calculation of first-stage model. The method is decomposed into three parts: (1) take cold start to generate a good deal of basic training data; (2) train the neural network for the fast solution of first-stage model; (3) take real-world cases to improve the self-learning of neural network. A multiproduct pipeline in China is taken as the example to prove the practicability and superiority of the proposed method. The experimental results show that the proposed method could decrease the computation time from about several hours to several minutes. [ABSTRACT FROM AUTHOR]

Many indoor temperature sensors have been installed in building rooms with district heating systems (DHSs) in China. To apply the collected indoor temperature data to district heating substation regulation, the indoor characteristic temperature of the heat substation (ICTS) should be calculated. However, previous calculation methods for ICTS cannot accurately evaluate their comprehensive characteristics. This study proposed a novel method to calculate the ICTS based on the entropy value and applied it to three actual DHSs in northern China. First, the variation trend and influencing factors of indoor temperature data were analyzed. Second, the ICTS was calculated and compared using various methods. Third, a correlation analysis of the ICTS and input features was performed. Finally, five typical machine learning models were used to predict the ICTS. The results demonstrated that the proposed method can better reflect the characteristics of the data and eliminate the impact of subjective preferences. The average mean absolute percentage errors of five models were less than 1%; the linear regression model performed best when denoising the original data, with a value of 0.12%. This study is helpful for better understanding the influencing factors on the ICTS and the strategies for adjusting feature values. • ICTS can evaluate heating quality and provide feedback control in DHS. • A novel calculation method of ICTS based on entropy value is proposed. • The proposed method can better reflect the characteristics of the data. • SVR, LR, XGBoost, RF, and GBM are used to predict ICTS. • The LR model using denoising original data performs best with MAPE of 0.12%. [ABSTRACT FROM AUTHOR]

With the coming of intelligent manufacturing, multi-variety and small-batch production mode has gradually become popular. Aiming at the characteristics of high dimensional information and limited samples in this mode, a novel data-driven grey Weibull model is established for product quality prediction. Firstly, a high-dimensional information from the production process is integrated as the process variation using a data-driven method. Then, the quality prediction function is deducted by considering that process variation follows Weibull distribution-based mechanism, the Hausdorff difference scheme is adopted to weaken the error from the difference to the differential, heuristic algorithm is selected to optimize the distribution parameters of the model. Finally, an experimental analysis is designed using the dataset from some personalized customization manufacturer in China. Results show that the proposed model is not only superior to the other eight models in terms of stability and prediction accuracy, but also boasts the features of amalgamation of data-driven and mechanism-driven methods, which can simultaneously process high-dimensional information and limited samples in multi-variety and small-batch production system. [ABSTRACT FROM AUTHOR]

Enjoying widespread government support and encouragement for the digital projects of publishers and media industry. The Chinese publishing business continues to show steady development in the past year. At the same time, significant changes are taking place in the structure of the publishing industry. The content production, marketing, operating, and consumption are not linear upstream-downstream related any more. Instead, they have fused together, and thus formed a new industrial ecosphere. In this paper, we investigate the new technology research and practice in the digital publishing industry. There is obvious indication that new technology plays an important role in the structural change of the publishing industry. [ABSTRACT FROM AUTHOR]

Nowadays, we can obtain a huge amount of information and data of railway dangerous goods transportation system through various technical documents, accident reports, monitoring technologies etc. For the space composed of massive historical information and data, a data-driven fault predication approach that can better grasp some important local information while ignoring the negative impact of other data in the global might be practical. However, we have the following challenges: (i) How to reduce the impact of unimportant information on prediction results in advance? (ii) What kind of local approximation data-driven approach should be applied, and (iii) How to correct the results and improve the reliability and accuracy after fault predication based on the local approximation data-driven approach? In this paper, two data-driven approaches including Back Propagation with Markov Correction and Radial Basis Function with Markov Correction are proposed to predicate the fault in a railway dangerous goods transportation system. In order to solve challenge (i), we decompose the whole transportation process into multiple sub-processes based on Work Breakdown Structure with clear duration boundary on the time axis, and use Risk Breakdown Structure to detect the possible faults in each sub-process. In order to solve challenge (ii), we use and compare Back Propagation/Radial Basis Function with global approximation/local approximation and nonlinear prediction ability to learn and predicate the fault based on the collected historical data. In order to solve challenge (iii), we correct the prediction results with fluctuating deviation by using Markov Correction due to its non-aftereffect. Finally, a case study is conducted based on the collected historical fault data of railway dangerous goods transportation system in China. The results show that, for the prediction results based on Back Propagation, the average error increases from 1.43 to 1.88 and the Mean Square Error increases from 3.27 to 5.60 after Markov Correction. For the prediction results based on Radial Basis Function, the average error decreases from 1.13 to 1.11 and the Mean Square Error decreases from 1.81 to 1.76 after Markov Correction. The non-aftereffect of Markov chain well corresponds to the local approximation of Radial Basis Function. When the prediction value is determined by some data of the series, Radial Basis Function with Markov Correction can be applied. When the prediction value is determined by all the data (small-scale) of the series, Back Propagation with Markov Correction is better. • BP-MC and RBF-MC are proposed to predicate the fault in a RDGT system. • WBS-RBS is used to detect possible faults in the whole transportation process. • BP/RBF is applied to learn and predicate the fault based on the historical data. • MC is used to correct the predication results due to its non-aftereffect. • RBF-MC has better fault predication performance than BP-MC. [ABSTRACT FROM AUTHOR]

With the explosive growth of electric vehicles (EVs), it is an urgent task to incorporate low-carbon EVs with advanced optimization strategies to achieve orderly charging–discharging and economical operations for EVs. Nevertheless, current charging–discharging optimization strategies for EVs may be impractical since their energy consumption uncertainty and the driving trip cost are generally not considered. Therefore, a collaborative optimization model for large-scale EV charging–discharging with energy consumption uncertainty in this paper is proposed to simultaneously maximize passenger revenue and reduce the costs of the driving, charging–discharging, and battery depletion. Subsequently, a data-driven approach is developed to tackle the model. In this approach, an uncertainty predictor based on wavelet transform, deep deterministic policy gradient, and quantile regression is first applied to estimate the energy consumption uncertainty. Then, an adaptive learning rate firefly algorithm is presented to identify the most satisfactory solution for the optimization model. Finally, taking the actual data of 300 EVs in a city in China as case studies, the simulation results reveal that the proposed method is effective and has high application significance. • A new collaborative optimization model for EV charging–discharging is formulated. • A deep reinforcement learning method for energy consumption prediction is proposed. • The impact of driving behavior on energy consumption prediction is studied. • A new adaptive learning rate Firefly algorithm is presented and applied. • The effectiveness of the proposed methodology is verified by simulations of 300 EVs. [ABSTRACT FROM AUTHOR]

Despite the increasing volume of oceanographic data, the available ocean salinity data remains patently insufficient which limits studying ocean dynamics, climate change and the calculation of salinity-related ocean elements. Considering that traditional salinity reconstruction methods often suffer from various factors such as additional constraints, priori physical assumptions and large of specific regression coefficients, a generative adversarial networks (GANs) based deep learning (DL) framework is proposed to directly construct a near real-time, high-resolution daily three-dimensional ocean subsurface salinity (3D OSS) dataset from a data-driven perspective in this study. Four models with different structural combinations are designed in the China's marginal seas. Experimental results demonstrate that the models can successfully reconstruct the high-precision and high-resolution 3D OSS on a daily scale in 12 depth levels (from 2 m to 200 m). The asymmetric inception-3DGAN model with all enhanced structures has the highest accuracy, the average root-mean-squared error (RMSE) is 0.135psu, the average coefficient of determination (R2) is 0.5641 and the percent bias is 0.436%. Comparing with model without enhanced structures, the average RMSE is decreased by 22.41% when adding all the enhancement structures. Besides, temporal and spatial error analysis are also conducted to evaluate the models' performance from different aspects. Finally, the model results are used to analyze common ocean elements, such as water mass properties, dynamic fields and geostrophic velocity fields, demonstrating that the 3D OSS dataset construction approach proposed in this study not only provides some new insights into ocean observations, but also has high application values. • High precision daily 3D OSS is reconstructed via T–S mapping from a data-driven view. • Four 3D GAN based models are progressively built by powerful enhancement techniques. • Results are analyzed with in situ observations and reanalysis data. • Best reconstruction performance is found for the asymmetric inception-3DGAN case. • Reliable near real-time data can be provided for operational oceanography research. [ABSTRACT FROM AUTHOR]

[Display omitted] • The Metallogenic prediction by fusion geological model-driven and data-driven improve the model-driven precision and increase data-driven model interpretability. • The data-driven applied the XGBoost and LightGBM algorithm with better prediction ability and stability in the Xiong'ershan area. • The SHAP value was used to evaluate the importance of evidence layers. It increases the interpretability of ensemble learning, and has provided a basis for further exploration. The traditional metallogenic prediction based on the geological model has been extensively used in prospecting, and the emerging machine learning method has also been successfully applied to mineral prospectivity prediction. In this study, we proposed a method based on the combination of model-driven and data-driven approaches, which was applied to the prospective area of the gold deposits in Xiong'ershan area. In this method, the geological prospecting model was taken as the prior knowledge of the data-driven model, and the metallogenic prediction elements of the prospecting model were constructed as the characteristic variables of the data-driven model, which improved the prediction accuracy of prospecting based on the geological model and reduced the uncertainty of outcome prediction based on data-driven. The XGBoost and LightGBM decision tree algorithms were selected for the data-driven method to create MPM. Then the SHAP framework was used to analyze the characteristic variables of the model, thus showing that geochemical prospecting could be carried out at the intersection of faults in the study area. Finally, the performance indicators based on machine learning and the legacy geological data were used to verify the robustness of the model. The AUC values of the final model were >0.95, and the new exploration targets were delineated in the high anomaly area, indicating the direction for subsequent exploration work. [ABSTRACT FROM AUTHOR]

• XGBoost and ANN based reservoir operation schemes are developed to predict the reservoir release and storage in hydrologic models. • A hybrid hydrologic modelling framework is developed by coupling data-driven and conceptual reservoir operation schemes. • The prospects, possible limitations and future directions of data-driven reservoir operation schemes are discussed. Reservoirs have been built worldwide to address the water-related issues. To fully understand their potential impacts on the hydrologic regime, explicitly parameterizing reservoir operation in hydrologic models is often required. In this study, two data-driven reservoir operation schemes based on extreme gradient boosting (XGBoost) and artificial neural network (ANN) are respectively developed to predict the reservoir release and storage in hydrologic models for reservoirs with historic in-situ inflow, storage, release data. Then, a hybrid modelling framework is proposed by coupling a high-resolution (3 km) hydrologic model with (1) the developed data-driven reservoir operation schemes and (2) a calibration-free conceptual reservoir operation scheme designed for data-scarce reservoirs. This allows quantitative assessment of the cumulative impacts of dam operation on the hydrologic regime under different reservoir data availability. The framework is applied to the Upper Yangtze River Basin (UYRB) in China that is one of the most regulated river basins across the country due to extensive reservoir construction. Results indicate that both data-driven reservoir operation schemes can well reconstruct the reservoir releases and storage in the UYRB (daily NSE of ∼ 0.9), and the XGBoost performs slightly better than ANN. By coupling reservoir operation, the model shows a remarkably improved performance in reconstructing the daily streamflow of the basin. The major reservoirs in the UYRB can redistribute excessive water in the wet season to the dry season and attenuate the high and low flows, leading to enhanced water security along the river. Our approach provides a practical framework for reservoir impact assessment and predictions. [ABSTRACT FROM AUTHOR]

At present, the remote sensing (RS) thermal infrared (TIR) images that are commonly used to obtain land surface temperature (LST) are contaminated by clouds and thus cannot obtain spatiotemporal integrity of LST. To solve this problem, this study combined a physical model with strong interpretability with a data-driven model with high data adaptability. First, the physical model (Weather Research and Forecast (WRF) model) was used to generate LST source data. Then, combined with multisource RS data, a data-driven method (random forest (RF)) was used to improve the accuracy of the LST, and a model framework for a data-driven auxiliary physical model was formed. Finally, all-weather MODIS-like data with a spatial resolution of 1 km were generated. Beijing, China, was used as the study area. The results showed that in cases of more clouds and fewer clouds, the reconstructed all-weather LST had a high spatial continuity and could restore the spatial distribution details of the LST well. The mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (ρ) in the case of more (fewer) clouds were ranked as follows: MAE < 1 K (< 2 K), RMSE < 2 K (< 2 K), and ρ > 0.9. The errors obeyed an approximately normal distribution. The total MAE, RMSE, and ρ were 0.80 K, 1.09 K, and 0.94 K, respectively. Generally, the LST reconstructed in this paper had a high accuracy, and the model could provide all-weather MODIS-like LST to compensate for the disadvantages of satellite TIR images (i.e., contamination by clouds and inability to obtain complete LST values)., (© 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

[Display omitted] • The contribution of influential factors on the change of indoor PM 2.5 is evaluated. • A method for quantifying the monthly variation pattern of PM 2.5 concentrations. • The ambient PM 2.5 contributions are varied in each month. • N, M, and W-shaped PM 2.5 variation patterns are found from observed data. • Time-specific indoor air interventions can help seasonally target management. Indoor air quality is crucial to the physical and psychological health of students because they spend a large portion of their time in classrooms. Indoor PM 2.5 concentrations are affected by various complex factors, such as outdoor PM 2.5 , temperature, and relative humidity. However, how and to what extent these factors contribute to PM 2.5 concentrations remains unclear. Recently, black-box (e.g., neural networks) and white-box (e.g., linear regression) models have been applied to analyze their contributions. However, these models either have low interpretability or are insufficient for revealing complex nonlinear relationships. To address these issues, indoor PM 2.5 concentrations in ten classrooms were monitored for twelve months at a primary school in North China, and the contribution of various influential factors was calculated using partial derivatives based on this approach. This method can automatically identify linear and nonlinear relationship models from a large amount of data without a prior hypothesis. Experimental results showed that: (1) The contribution of each influential factor to indoor PM 2.5 varied greatly in the 12 months based on the identified relationships. In addition, no single relationship pattern was identified that could universally describe the factors influencing indoor PM 2.5. (2) The method developed in this study can automatically identify linear and nonlinear relationship models with white-box structures from a large amount of data without a prior hypothesis, which is more interpretable and applicable than other baselines. (3) Targeted solutions can be drawn by the contribution of each factor and three types of relationship curves (i.e., N -shaped, M−shaped, and W-shaped), the latter of which is the Pareto front revealed by our results. The study offers informative results regarding the temporal dynamics of indoor PM 2.5 concentrations and quantitative contributions of influential factors based on timely long-term data, which promotes the understanding of changes in indoor PM 2.5 concentrations. This also demonstrates the promising potential of using low-cost online sensors to conduct informative measurements that guide schools to more effectively improve classroom air quality. [ABSTRACT FROM AUTHOR]

For multi-energy storage vehicles, the performance of online predictive energy management strategies largely relies on the length and effective utilization of predictive information. In this context, this paper proposes a novel velocity prediction method for the full driving cycle of electric vehicles based on the spatial–temporal commuting data, then the predicted velocity is applied to predictive energy management in electric vehicles with battery/supercapacitor hybrid energy storage system. Firstly, an one-year real-world commuting data set is collected on a Chinese arterial road with 10 intersections, 225 records are classified into 79 categories. Then, a real-time two-stage full driving cycle prediction method is proposed, where a medium-term prediction based on a long–short term memory (LSTM) network and a long-term prediction generated by a spatial–temporal interpolation method (STIM) are spliced for each category. The most probable category, i.e., the executed LSTM and STIM can be updated in real-time. Finally, a multi-horizon model predictive control method (MH-MPC) is established to leverage the predicted velocity for optimal power distribution. Compared with the conventional short-sighted MPC, the MH-MPC can reduce 4.2% battery degradation cost in a statistics form with real-time computation requirements satisfied. • A novel spatial–temporal data-driven velocity prediction method is proposed. • Second-level velocity prediction of the full driving cycle can be achieved. • Multi-horizon model predictive control for long-term optimal energy management. • More economy gained from leveraging the long-term prediction information. • The study is based on a one-year real-world commuting data set in China. [ABSTRACT FROM AUTHOR]

• Presents a data-driven measurement, evaluation, and identification method. • Uses a coupling coordination degree model for three regional agriculture subsystems. • Suggests ways to reduce costs, increase social support, and enhance competitiveness. This study aims to evaluate the relationship between the agriculture economy environment, and society from the perspective of system theory and then put forward targeted suggestions for sustainable development of Anhui's agriculture in China. Based on the collection of relevant data and the objective weighting of indicators, the entropy weight method is used to measure the comprehensive development level of regional agriculture. The coupling coordination degree model is employed to evaluate the coupling coordination level among the three subsystems of regional agriculture. The obstacle degree model is used to identify the key obstacle factors. The case study results show that the main obstacles of the coordination system are the use of pesticides, the number of agricultural scientific and technological achievements, the application of agricultural plastic film, the number of farmers' technical training schools, and the proportion of animal husbandry. Accordingly, the paper posits suggestions, such as reducing the input of pesticides and agricultural plastic films in agricultural production, improving the social support level of agricultural science, technology, and education, and enhancing the competitiveness of animal husbandry in the Anhui Province. This study provides theoretical and methodological support for the coupled and coordinated development of regional agricultural economy, ecology and society(EES). [ABSTRACT FROM AUTHOR]

The ecological efficiency (eco-efficiency) of a regional logistics industry (RLI) is widely regarded as a key factor affecting sustainability of economic development, environmental protection, and resources utilization. This study applied a data-driven method to evaluate and increase the eco-efficiency of an RLI. Based on RLI-related data, which were converted into proper dimensionless indices, data envelopment analysis (DEA), which assumes that the decision-making units (DMUs) are in the situation of variable returns to scale, the Banker, Charnes, and Cooper (BCC) model, and Malmquist index model were used to assess the eco-efficiency of the RLI from both static and dynamic viewpoints. Then, a Tobit regression model was built to explore the factors that influence eco-efficiency. The effectiveness of this approach was verified by its application to an example from Anhui Province. This study has theoretical and practical value for the assessment and promotion of the ecological eco-efficiency of the RLI. We believe that our approach offers a powerful tool to assist logistics enterprises and local governments in coordinating the relationship between the RLI economy and the ecological environment, facilitating the drive to carbon neutrality.

Global warming and climate change are gaining traction in recent years. As a major cause of global warming, carbon emissions were centered to China's climate change policy initiatives. Nevertheless, the existing policy discourse has yet reached a consensus on the optimal modeling method for carbon emissions prediction that is well-informed of both policy goals and the time-series pattern of carbon emissions. This paper fills the gap by promoting a novel data-driven decision model for carbon emissions prediction that is based on the extended belief rule base (EBRB) inference model. The new decision model consists of three components: 1) an indicator integration method, which aims to generate a few group indicators from a large number of statistical indicators; 2) a new EBRB construction method, which aims to consider the management policy goals for constructing EBRB; 3) a new ER-based inference method, which aims to predict carbon emissions based on time series change of relevant factors. The effectiveness of the proposed decision model has been tested against carbon emissions management data from 30 provinces in China. Experimental results demonstrate that the model will offer powerful reference value in the policy decision-making process, which will help to meet policy requirements for carbon emissions. • Proposing statistical indicators integration method for group indicator. • Considering the management policy goals in EBRB construction. • Proposing an ER-based inference model based on time series analysis. • Providing a case study for carbon dioxide emissions prediction of China. [ABSTRACT FROM AUTHOR]

• A data-driven cleaner production strategy is proposed for energy-intensive industries. • The data-driven strategy is explained by the cleaner production data lifecycle. • The implementation models are developed to illustrate the proposed strategy. • The effectiveness of the proposed strategy is discussed for companies in China. Cleaner production is an effective strategy for improving material utilization, reducing energy consumption, maximizing product output, and minimizing emissions during the entire manufacturing processes. An increasing number of enterprises promote the implementation of cleaner production. In the Industry 4.0 context, product-embedded information devices are widely used to capture product lifecycle data. Product lifecycle management provides an opportunity to achieve cleaner production strategy. This paper presents a data-driven cleaner production strategy by product lifecycle management for energy-intensive manufacturing industries. The data-driven strategy is proposed and explained by the lifecycle of cleaner production data. Implementation models are developed to illustrate the proposed data-driven cleaner production strategy. Furthermore, two case studies from Southern and Northern China are presented to demonstrate the strategy. Results show that the unit energy consumption and the energy cost of production in Company A are reduced by at least 3% after applying the proposed strategy. In addition, the "cradle-to-gate" lifecycle data analysis indicates that the costs of environmental pollution in Company B are diminished significantly. Finally, energy-intensive manufacturing companies in China are compared and evaluated, and the effectiveness of the proposed strategy is discussed. [ABSTRACT FROM AUTHOR]

Shield machine is an essential device for underground space development, and unmanned intelligent control of self-driving shields is productive research in tunnel construction technology. This paper analyzes the control functions of shield machines and proposes the definition and grading of self-driving shields. Inspired by the theory of human performance models, a Shield Automatic Intelligent Control System (SHIELD_AICS) is designed based on the combination of a data-driven and a knowledge-driven approach. A traditional shield with manual control was installed with SHIELD_AICS and transformed into an intelligent self-driving shield named Zhiyu shield. The Zhiyu shield was applied to two tunnel construction projects in China and completed the first autonomous unmanned tunneling successfully in the world. The field operation test shows that the self-driving shield is capable of automatic continuous tunneling for a long distance without manual intervention, and the shield attitude and the ground settlement level can meet the engineering requirements during tunneling. • A Shield Automatic Intelligent Control System (SHIELD_AICS) is established for the self-driving shield. • Automatic grading system of self-driving shield is defined and classified. • An approach based on knowledge and data-driven is proposed to realize control exploration, identification, tuning, and evaluation. • A traditional shield is transformed into a self-driving shield (Zhiyu) by hardware and software based on SHIELD_AICS. • Zhiyu shield completed the first unmanned tunneling, which has better decision-making and control performance than manual. [ABSTRACT FROM AUTHOR]

ABSTRACT Two distinct approaches can be employed in the classification and divisions of wet/dry climate. The first is the rule-driven strategy with predefined threshold values representing climate division boundaries, which is usually performed by Aridity Index ( AI). The second is an automated method in a data-driven fashion, avoiding the direct specification of classification rules while utilizing some forms of cluster analysis. However, various methods for climate classifications raise issues on their applicability and quality. Therefore, evaluation and comparative studies are needed to handle such issues first, in order to analyze their performance and second, to better understand climate characteristics in a region. This article makes a comprehensive analysis and comparison among five classification methods, including four rule-driven methods based on different categories [Penman-Monteith (PM), Thornthwaite, Holdridge, Sahin's method] and one data-driven method (factor-cluster analysis). With the meteorological data for long-term period (1981-2010), the wet/dry climate divisions were performed for 191 meteorological stations in Northwest China ( NW). The results indicated that the overall climate regimes were in agreement for five classifications, but boundaries of wet/dry climate divisions in a data-driven fashion showed a better consistency with topographic features. PM classifications displayed more arid climate types in NW, while the Thornthwaite approach showed an underestimate in arid environments. All wet/dry climate types corresponding to Holdridge and Sahin's classifications were represented in NW, but Holdridge classification is more easily affected by topography and elevation. Complete comparisons among rule-driven methods are difficult to conduct due to different class definitions and low coincident classes. Class definition of climate types for different rule-driven classifications thus needs further investigation. This article highlights the importance of acknowledging the limitations and advantages of different classification systems as well as the dry and wet climate conditions in NW in hope to provide a reference for a similar geographical region. [ABSTRACT FROM AUTHOR]

[Display omitted] • Only normal operating data is needed to construct the abnormal detection model. • Local behaviors of fault are easier to capture with the proposed multiblock strategy. • The uncertainty and nonlinearity of the fault data can be better processed. • Experiments on real industrial data verify the effectiveness of the proposed method. The accurate and timely detection of anomalous conditions are essential for the safe and economical operation of complex thermal power plants (TPPs). However, the development of an excellent anomaly detection model without sufficient fault data is difficult in practice. In addition, global-based detection methods can submerge local anomalous behavior, causing serious delays in providing early warning of anomalous conditions. To solve this issue, a multiblock detection method based on the framework of evidence theory is proposed in this study. Measured variables collected from different units are automatically divided into several subblocks by using mutual information (MI)-based spectral clustering. Then, an evidential k -nearest neighbors algorithm (EKNN) is developed in each block, and local detection results are calculated. To provide an intuitionistic indication, the Dempster–Shafer rule is adopted to fuse the detection results of all the subblock EKNN models. The proposed approach can be applied to linear and nonlinear processes on the basis of MI and the nonparametric k -nearest neighbors procedure. To confirm its effectiveness, the proposed method is validated on samples collected from an ultra-supercritical TPP in China. [ABSTRACT FROM AUTHOR]

Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Intense harmful algal blooms (HABs) can occur in the backwaters of tributaries supplying large-scale reservoirs. Due to the characteristics of process-based models and difficulties in modelling complex nonlinear processes, traditional models have difficulties disentangling the driving factors of HABs. In this study, we used data-driven methods (i.e., correlation analysis and machine-learning models) to identify the most important drivers of HABs in the Xiangxi River, a tributary of the Three Gorges Reservoir, China (2017–2018), for the dry season (from October to mid-April) and wet season (from April to September). We utilized the maximal information coefficient (MIC) combined with a time lag strategy and prior knowledge to quantitatively identify the driving variables of HABs. An extra trees regression (ETR) model was developed to assess the relative importance of causal variables driving algal blooms for the different periods. The results showed that water temperature was the most important driver for the duration of the study, followed by total nitrogen. Nitrogen had a stronger effect on algal blooms than phosphorus during both the wet and dry seasons. HABs were mainly affected by ammonia nitrogen in the wet season and by other forms of nitrogen in the dry season. In contrast, rather than the water temperature and nutrients, the operation of the Three Gorges Dam (difference between inflow and outflow discharge rate) was the most significant factor for algal blooms during the dry season, but its influence sharply declined during the wet season. This study showed that the key drivers of HABs can differ between seasons and suggests that HAB management should take seasonality into account. [Display omitted] • We analysed the importance of different driving factors for HABs. • Machine learning utilizing MIC combined with a time lag strategy was applied in the analysis. • The relative importance of environmental factors was analysed. • Nitrogen has a stronger effect than phosphorus on HABs. • Dam operation was an important factor for HABs, especially in the dry season. [ABSTRACT FROM AUTHOR]

Validation is a crucial technique used to strengthen the application capabilities of earthobservation satellite data and solve the quality problems of remote-sensing products. Observing land-surface parameters in the field is one of the key steps of validation. Therefore, the demand for long-term stable validation stations has gradually increased. However, the current location-selection procedure of validation stations lacks a systematic and objective evaluation system. In this research, a data-driven selection of a land product validation station (DSS-LPV) based on Machine Learning is proposed. Firstly, we construct an evaluation indicator system in which all factors affecting the location of validation stations are divided into surface characteristics, atmospheric conditions and the social environment. Then, multi-scale evaluation grids are constructed and indicators are allocated for spatial evaluation. Finally, four Machine Learning (ML) methods are used to learn the established reliable stations, and different data-driven scoring models are constructed to explore the intrinsic relationship between evaluation indicators and station locations. In this article, the reliability of DSS-LPV is effectively validated by the example of China using the national-level land product validation station that has been established. After a comparison between the four ML models, the random forest (RF) with the highest accuracy was selected as the modeling method of DSS-LPV. The correlation between the regression value of test stations and the target value is 0.9133. The average score of test stations is 0.8304. The test stations are generally located within the calculated hot-spot area of the score density map, which means that it is highly consistent with the location of the built stations. Research results indicate that DSS-LPV is an effective method that can provide a reasonable geographical distribution of the stations. The location-selection results can provide scientific decision-making support for the construction of land product validation stations. [ABSTRACT FROM AUTHOR]

We have entered the fourth research paradigm with the overwhelming availability of vast amounts of data. The processing and mining these data for a better understanding of earth systems and predicting mineral resources is challenging. This study discusses a data-driven knowledge discovery of geochemical patterns and presents a case study of geochemical data processing from a data-driven perspective. We employed local indicators of spatial association (LISA), principal component analysis (PCA), and deep autoencoder network (DAN) procedures to explore spatial association of geochemical patterns, extract elemental associations, and detect geochemical anomalies related to Au Sb mineralization in the Daqiao district, Gansu Province, China. The results indicate the following: (1) both Au and Sb, and Pb and Zn have a close spatial correlation, indicating genetic connections among them; (2) the elemental association of Au, Sb, As, Hg and Ag can be adopted as a geochemical signature for the discovery of Au Sb polymetallic mineralization in the study area; and (3) the geochemical anomalies identified by DAN exhibit a strong spatial relationship with locations of known mineral deposits and can provide a significant clue for further mineral exploration in this district. These findings indicate that data-driven procedures can help in the knowledge discovery of geochemical patterns in mineral exploration. Additional efforts are required for data-driven knowledge discovery in both geochemical prospecting and mineral exploration. • Data-driven procedures can help perform knowledge discovery of geochemical patterns. • More focus on data-driven knowledge discovery in both geochemical prospecting and mineral exploration. • Case study was conducted for geochemical patterns discovery in the Daqiao district, China. [ABSTRACT FROM AUTHOR]

This study aims to promote the high-quality development of regional agriculture. This study proposes a data-driven method for regional agricultural analysis and evaluation. Based on the data collection and processing related to regional agricultural development, the location entropy index was used to analyze the industrial agglomeration level, and the shift-share model was constructed to evaluate the industrial structure and competitiveness. Based on the above analysis and evaluation, high-quality development policy suggestions for regional agriculture were provided. Taking the agricultural development of the Yangtze River Delta from 2010 to 2019 as an example, this study shows the implementation process of the method. From the perspective of high-quality agricultural development in the Anhui Province, this paper proposes policy suggestions on industrial structure adjustment and promoting competitiveness. This study provides theoretical and methodological support for the development of high-quality regional agriculture., (© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)