Search

Data driven deep learning methods have become the mainstream method of building extraction from remote sensing images. In this paper, deep learning algorithm is used to classify and extract buildings from remote sensing images of rural areas around the Great Wall in the suburbs of Beijing captured by unmanned aerial vehicles. Aiming at the shortcomings of the current mainstream instance segmentation algorithm Mask R-CNN in feature fusion and poor prediction of instance mask boundaries, this paper proposes a boundary optimization algorithm for building instance segmentation based on discrete wavelet transform. Firstly, the discrete wavelet transform is introduced into the segmentation task branch of Mask R-CNN algorithm to extract the low-frequency and high-frequency information of the real mask, in which the high-frequency information includes the boundary information. Secondly, the pixel by pixel prediction of the mask turns into the learning of the low-frequency and high-frequency information of the real mask. The learning of the high-frequency information helps the segmentation network to learn the boundary features better. Finally, using the reversibility of discrete wavelet transform, the low-frequency and high-frequency information of the learned mask is inversely transformed to reconstruct the final mask. The improved algorithm is evaluated on the dataset COCO, and applied to the automatic extraction of buildings. The DWT Mask R-CNN algorithm model achieved 70.2% segmentation accuracy and 71.4% detection accuracy, which were improved by 1% and 0.7% respectively compared with the Mask R-CNN and Cascade Mask R-CNN models. The experimental results show that the instance segmentation edge optimization algorithm combined with wavelet transform has achieved better results on the segmentation boundary, improved the poor effect of mask edge detection and achieved higher detection accuracy, and can accurately extract village buildings. [ABSTRACT FROM AUTHOR]

Indoor environmental parameters are closely related to the energy consumption and indoor thermal comfort of office buildings. Predicting these parameters, especially indoor temperature, can contribute to the management of energy consumption and thermal comfort levels in office buildings. An accurate indoor temperature prediction model is the basis for implementing this process. To this end, this paper first discusses the input and output parameters of the model, and then it compares the prediction effects of mainstream prediction model algorithms based on data mining under the same data conditions. The superiority of the XGBoost integrated learning algorithm is verified, and a further XGBoost-based indoor temperature online prediction method is designed. The effectiveness of the method is validated using actual data from a commercial office building in Haidian District, Beijing. Finally, optimization methods for the prediction method are discussed with regard to the scheduler mechanism proposed in this paper. Overall, this work can assist building operators in optimizing HVAC equipment running strategies, thus improving the indoor thermal comfort and energy efficiency of the building. [ABSTRACT FROM AUTHOR]

Rapid simulation of land subsidence can provide an effective means of facilitating its management and control. This paper innovatively introduced a back-propagation (BP) neural network subsidence simulation model which was optimized by the sparrow search algorithm (SSA), hereinafter referred to as the SSA-BP model, to simulate land subsidence in Tongzhou District, Beijing. First, based on the time series interferometric synthetic aperture radar (InSAR) monitoring, different technologies such as spatial analysis, Google Earth Engine (GEE), and machine learning were utilized together with a variety of multi-source spatial data, including groundwater level, compressible layer thickness, Visible Infrared Imager Radiometer Suite (VIIRS) nighttime light images, and the OpenStreetMap (OSM) road distribution. Furthermore, we determined the optimal grid scale for land subsidence research and worked out a multifactor-driven SSA-BP land subsidence simulation model for which sensitivity analysis was performed with great care. Main conclusions: (1) From November 2010 to January 2020, the average annual surface displacement rate in Beijing's subcentre, Tongzhou, ranged from −133.9 to +3.9 mm/year. (2) Our SSA-BP land subsidence simulation model allows for a relatively high overall accuracy. The average root mean square error (RMSE) is 5.00 mm/year, the average mean absolute error (MAE) is 3.80 mm/year, and the average coefficient of determination (R2) is 0.83. (3) Sensitivity analysis shows that the SSA-BP model driven by multiple factors has a far better simulation performance than the model driven by any single weighting factor, and displays the highest sensitivity to the groundwater level factor among all the weighting factors. In terms of subdividing the study area, our SSA-BP land subsidence model runs with multifunctional zones displayed a higher accuracy than that without. This paper made use of a machine learning model to simulate land subsidence in Beijing's Tongzhou District and explored the sensitivity of different factors to land subsidence, which is helpful for its scientific prevention. [ABSTRACT FROM AUTHOR]

Geological hazards often occur in mountainous areas and are sudden and hidden, so it is important to identify and assess geological hazards. In this paper, the western mountainous area of Beijing was selected as the study area. We conducted research on landslides, collapses, and unstable slopes in the study area. The surface deformation of the study area was monitored by multi-temporal interferometric synthetic aperture radar (MT-InSAR), using a combination of multi-looking point selection and permanent scatterer (PS) point selection methods. Random forest (RF), support vector machine (SVM), convolutional neural network (CNN), and recurrent neural network (RNN) models were selected for the assessment of geological hazard susceptibility. Sixteen geological hazard-influencing factors were collected, and their information values were calculated using their features. Multicollinearity analysis with the relief-F method was used to calculate the correlation and importance of the factors for factor selection. The results show that the deformation rate along the line-of-sight (LOS) direction is between −44 mm/year and 28 mm/year. A total of 60 geological hazards were identified by combining surface deformation with optical imagery and other data, including 7 collapses, 25 unstable slopes, and 28 landslides. Forty-eight of the identified geological hazards are not recorded in the Beijing geological hazards list. The most effective model in the study area was RF. The percentage of geological hazard susceptibility zoning in the study area is as follows: very low susceptibility 27.40%, low susceptibility 28.06%, moderate susceptibility 21.19%, high susceptibility 13.80%, very high susceptibility 9.57%. [ABSTRACT FROM AUTHOR]

BACKGROUND: The emergency rescue ability of firefighters is particularly important in the event of major disasters or accidents. Therefore, an assessment of the firefighter-training effectiveness is necessary. OBJECTIVE: This paper aims to achieve a scientific and effective assessment of the firefighter-training effectiveness in China. An assessment method based on human factor parameters and machine learning was proposed. METHOD: The model is constructed by collecting the corresponding human factor parameters such as electrocardiographic signals, electroencephalographic signals, surface electromyographic signals, and photoplethysmographic signals through wireless sensors and using them as constraint indicators. For the problems of weak human factor parameters and high noise proportion, an improved flexible analytic wavelet transform algorithm is used to denoise and extract the corresponding feature values. To overcome the limitations of traditional assessment methods, improved machine learning algorithms are used to comprehensively assess the training effectiveness of firefighters and provide targeted training suggestions. RESULTS: The effectiveness of this study's evaluation method is verified by comparing it with the expert scoring method and considering firefighters from a special fire station in Xhongmen, Daxing District, Beijing, as an example. CONCLUSION: This study can effectively guide the scientific training of firefighters and the method is more objective and accurate than the traditional method. [ABSTRACT FROM AUTHOR]

Land surface temperature (LST) is one of the most important parameters of the interface between the earth surface and the atmosphere, and it plays a significant role in many research fields, such as agriculture, climate, hydrology, and the environment. However, the thermal infrared band of remote sensors is easily affected by clouds and aerosols, leading to many data gaps in LST products, which restricts the subsequent application of these products. In this paper, Beijing, China, is selected as the study area, and the LST data retrieved from Fengyun 4A (FY-4A) Advanced Geosynchronous Radiation Imager (AGRI) are reconstructed based on the two-point machine learning method. Firstly, the two-point machine learning model is built to reconstruct the theoretical clear-sky LST from simulated and actual images, and the accuracy of the reconstruction results is evaluated compared with the random forest algorithm and the inverse distance weighted method. Secondly, the actual LST under the influence of clouds is reconstructed by using the ERA5 reanalysis LST data as the auxiliary data, and the reconstruction accuracy is then evaluated by the field measurement LST data. The experimental results show that (1) the prediction accuracy of the two-point machine learning method is higher than that of the random forest method in both simulated data and actual data experiments; (2) the R2 of reconstructed LST under theoretical clear-sky conditions is 0.6860 and the root mean square error (RMSE) is 2.9 K, while the R2 of the reconstructed accuracy of actual LST under clouds is 0.7275 and the RMSE is 2.6 K, i.e., the RMSE decreases by 10.34%; (3) the two-point machine method combined with the auxiliary ERA5 LST data can well reconstruct LST under cloudy conditions and present a reasonable LST distribution. [ABSTRACT FROM AUTHOR]

Geospatial artificial intelligence (GeoAI) has emerged as a subfield of GIScience that uses artificial intelligence approaches and machine learning techniques for geographic knowledge discovery. The non-regularity of data structures has recently led to different variants of graph neural networks in the field of computer science, with graph convolutional neural networks being one of the most prominent that operate on non-euclidean structured data where the numbers of nodes connections vary and the nodes are unordered. These networks use graph convolution – commonly known as filters or kernels – in place of general matrix multiplication in at least one of their layers. This paper suggests spatial regression graph convolutional neural networks (SRGCNNs) as a deep learning paradigm that is capable of handling a wide range of geographical tasks where multivariate spatial data needs modeling and prediction. The feasibility of SRGCNNs lies in the feature propagation mechanisms, the spatial locality nature, and a semi-supervised training strategy. In the experiments, this paper demonstrates the operation of SRGCNNs with social media check-in data in Beijing and house price data in San Diego. The results indicate that a well-trained SRGCNN model is capable of learning from samples and performing reasonable predictions for unobserved locations. The paper also presents the effectiveness of incorporating the idea of geographically weighted regression for handling heterogeneity between locations in the model approach. Compared to conventional spatial regression approaches, SRGCNN-based models tend to generate much more accurate and stable results, especially when the sampling ratio is low. This study offers to bridge the methodological gap between graph deep learning and spatial regression analytics. The proposed idea serves as an example to illustrate how spatial analytics can be combined with state-of-the-art deep learning models, and to enlighten future research at the front of GeoAI. [ABSTRACT FROM AUTHOR]

A good risk warning model is an effective way to guarantee the stable operation of the carbon market and exert its emission reduction function. This paper takes the China's pilot carbon market as the research object and measures the carbon market risk by ARMA-GARCH-VaR. Then, influential factors are selected as non-market characteristics from the perspective of causality and incorporated into the risk warning model, and SMOTE and SMOTEENN are introduced to deal with the unbalanced samples. Results show that (1) The risk fluctuations of Beijing and Shenzhen carbon market are large, and the risk fluctuations of Guangdong carbon market are relatively smooth in the early period and larger in the recent period. (2) Air quality, average daily temperature, CSI 300, power coal, natural gas, European carbon market, exchange rate, and Baidu index are all important factors in the risk volatility of carbon market. (3) The Classification Decision Tree (CDT) has the best performance. CDT has the best performance in Guangdong carbon market, SMOTE-CDT has the best performance in Hubei carbon market, and SMOTEENN-CDT has the best performance in Shanghai carbon market, in which SMOTEENN-CDT has a 76% Recall. The non-equilibrium treatment improves the overall Recall, and the risk warning model after non-equilibrium treatment can avoid missing important risk points. This paper can provide a certain degree of reference for the improvement of carbon trading market and risk management. [Display omitted] • A carbon market warning model is constructed. • The average VaR of the carbon trading markets in Shenzhen and Beijing is larger. • CDT performs better in market risk warning. • The model improves 34.8% in the avoidance of risk compared with other models. [ABSTRACT FROM AUTHOR]

• We investigate driving forces of different land-use types to BSD. • Diversified machine learnings are proposed for spatial interpolation fusion. • Hotspot detection establishes sampling points for reducing the MAUP effect. • Fusion models improve the interpolation performance: accuracy and stability. • Word clouds identifies predominant facility names in each land-use type. Land use plays a crucial role in promoting the bike-sharing demand. Traditionally, studies on bike-sharing demand (BSD) are mainly focused on its prediction through regression methods, but the influence of MAUP (modifiable areal unit problem) in modeling is ignored. This paper aims to model spatial BSD distribution and prove the driving forces of different land use types to BSD through a machine-learning-based multiple interpolation fusion method. The hotspot detection model is employed to establish sample points covering different land use types in urban areas. In order to capture the differences in adaptations among different urban regions and for different data sizes, six machine learning methods are applied and evaluated to improve BSD estimation by fusing five spatial interpolation algorithms, including Inverse Distance Weight, Spline, Kriging, Natural Neighborhood and Trend. The methodological verification of Beijing City shows that the fusion models improve the estimation performance compared with individual interpolation algorithms, and that GRNN (generalized regression neural network) method is superior to all the others. According to fitting results of all POIs based on the GRNN fusion model, we identify which types of facilities correspond to customers that will have a stronger preference for bike-sharing and demonstrate which facility names are more prominent in each land use type. The conclusions presented here enrich our understanding relationships between land-use and BSD, which provide a valuable foundation for the bike-sharing development. Compared with implementing regression in an analysis zone or a square grid, troubles caused by the MAUP are effectively solved through this method. [ABSTRACT FROM AUTHOR]

Surface settlement is one of the key engineering issues during shield construction process. In order to accurately predict surface settlement, this paper proposes a new machine learning method based on relevance vector machine (RVM), principal component analysis (PCA), and particle swarm optimization (PSO). Taking Beijing Metro Line 6 as a case study, the PCA-PSO-RVM model is used to make the prediction and compared with the prediction results of the RVM model using the same samples. In order to evaluate the reliability of the model, three evaluation indexes including mean relative error (MRE), root mean square error (RMSE), and Theil inequality coefficient (TIC) were calculated, and sensitivity analysis was carried out on them. The results show that the minimum relative error between PCA-PSO-RVM and the actual value is only 0.06%. The calculated MRE, RMSE, and TIC are 0.17%, 0.0714 mm, and 0.027%, respectively, which shows that PCA-PSO-RVM model has higher prediction accuracy, smaller deviations, and higher reliability compared with the three other models. Through sensitivity analysis, it is found that the weighted average internal friction angle (φ) has the most significant impact on the surface settlement, which should be focused on in relevant research. [ABSTRACT FROM AUTHOR]

The outbreak of COVID-19 in Beijing has been sporadic since the beginning of 2022 and has become increasingly severe since October. In China's policy of insisting on dynamic clearance, fine-grained management has become the focus of current epidemic prevention and control. In this paper, we conduct a refined COVID-19 risk prediction and identification of its influencing factors in Beijing based on neighborhood-scale spatial statistical units. We obtained geographic coordinate data of COVID-19 cases in Beijing and quantified them into risk indices of each statistical unit. Additionally, spatial autocorrelation was used to analyze the epidemic risk clustering characteristics. With the multi-source data, 20 influencing elements were constructed, and their spatial heterogeneity was explored by screening 8 for Multiscale Geographically weighted regression (MGWR) model analysis. Finally, a neural network classification model was used to predict the risk of COVID-19 within the sixth ring of Beijing. The MGWR model and the neural network classification model showed good performance: the R2 of the MGWR model was 0.770, and the accuracy of the neural network classification model was 0.852. The results of this study show that: (1) COVID-19 risk is uneven, with the highest clustering within the Fifth Ring Road of Beijing; (2) The results of the MGWR model show that population structure, population density, road density, residential area density, and living service facility density have significant spatial heterogeneity on COVID-19 risk; and (3) The prediction results show a high COVID-19 risk, with the most severe risk being in the eastern, southeastern and southern regions. It should be noted that the prediction results are highly consistent with the current epidemic situation in Shijingshan District, Beijing, and can provide a strong reference for fine-grained epidemic prevention and control in Beijing. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to provide new ideas and methods for the sustainable use of groundwater in areas with serious groundwater overexploitation and serious groundwater pollution. Geographic information systems (GIS) were combined with machine learning algorithms, water resources optimization technology, and groundwater numerical simulation to optimize the regulation of the groundwater table and quality beneath the Daxing District in the southern plain of Beijing. By collecting local consumption and supply data and observations of the groundwater table and quality in the connected aquifer beneath Daxing for the years 2006–2020, the corresponding water demands and groundwater impact were extrapolated for the years 2021–2025 based on the basis of the existing development model. Through the combination of GIS and machine learning algorithms, the NO3-N concentration of local groundwater monitoring points in wet years, normal years, and dry years were predicted. With respect to NO3-N pollution, three new groundwater exploitation regimes were devised, which we numbered 1 to 3. The optimal allocation of water resources was then calculated for wet year, typical year, and dry year scenarios for the year 2025. By comparing the water shortage, groundwater utilization rate, and NO3-N pollution under the new groundwater exploitation regimes, the optimal groundwater exploitation mode for the three different types of hydrological year was determined. The results indicate that NO3-N pollution was greatly reduced after the adoption of the optimal regimes and that the groundwater table demonstrated rapid recovery. These results can be of great help in realizing the management, supervision, and regulation of groundwater by combining GIS with machine learning algorithms. [ABSTRACT FROM AUTHOR]

Since the limitation of carbon emissions, China's photovoltaic (PV) industry has developed vigorously, while some traditional heavy industries have been violently hit. Therefore, the industrial production data exhibits significant nonlinear and complexity characteristics, which may affect prediction accuracy, thus hindering the corresponding department's decision-making. Consequently, a novel structure-adaptive fractional Bernoulli grey model is presented in this paper to surmount this toughie, and the core innovations can be summarized as follows. Initially, a novel time function term is utilized to depict the accumulative time effect, which can smoothly represent the dynamic variations and significantly strengthen the robustness of the new model. Besides, the fractional-order accumulation technique, which could effectively improve the predicting accuracy, is employed in the proposed model. Furthermore, the adaptability and generalizability of the proposed model can be enhanced by the self-adaptive parameters optimized by the Particle Swarm Optimization. For illustration and verification purposes, experiments on forecasting the annual output of Photovoltaic modules in China and the annual output of steel in Beijing are compared with a range of benchmarks, including the classic GM (1, 1), conventional econometric technology, and machine learning methods. And the results confirmed that the proposed model is superior to all benchmark models, which indicates that the novel model is indeed suitable for industrial production forecasting. [ABSTRACT FROM AUTHOR]

Timely and accurate survey of construction and demolition waste (C&DW) distribution is of significance for managing C&DW and enhancing the quality of the urban environment, especially in rapidly urbanizing country of China. Automatic C&DW recognition using high-resolution remote sensing images is an extremely important surveying method. Existing C&DW recognition methods can only obtain a rough spatial distribution of C&DW. Mapping precise C&DW distribution on large-scale remote sensing images is still challenging. In this paper, to solve the problem of precise C&DW recognition, a novel deep learning algorithm based on high-resolution remote sensing images is proposed, which we refer to as the cross-channel multi-scale gated fusion network (CCMGNet). CCMGNet extracts depth features of C&DW from RGB and NIR bands by using two independent encoding streams. A gated fusion layer and a multi-scale attention module are designed to effectively fuse the features from two encoding streams. We manually labelled the sample set used for training and testing on 26 remote sensing images captured by the Gaofen-2 (GF-2) satellite. These images were taken in nine typical cities in China over the time period from 2019 to 2021. The results showed that the proposed method is effective in recognizing C&DW, realizing 89.42% and 84.52% in precision and IoU, and is superior to other state-of-the-art deep learning algorithms and existing C&DW recognition methods. The effectiveness of all significant components in CCMGNet was confirmed by ablation experiments. The proposed method was applied to extract C&DW regions in large-scale remote sensing images, with an example of a GF-2 image of Beijing. The high extraction efficiency and satisfactory visual effect demonstrate the potential of the proposed method for surveying the spatial distribution of C&DW. The novel method will play a crucial role in automatically surveying the spatial distribution and size of C&DW across the country. [ABSTRACT FROM AUTHOR]

Accurate traffic congestion estimation and prediction are critical building blocks for smart trip planning and rerouting decisions in transportation systems. Over the decades, there have been many studies focusing on traffic congestion estimation and prediction with different statistical approaches (e.g., Markov chain) and machine learning models (e.g., clustering, Bayesian networks, and artificial neural networks). However, there is a lack of a unified framework to address the mechanisms of different models and integrate the advantages of different methods through combinations. This paper introduces the FD-Markov-LSTM model, a hybrid interpretable approach that combines the fundamental diagram (FD), Markov chain, and long short-term memory (LSTM). The aim is to estimate and predict traffic states by integrating statistical data in both congested and uncongested scenarios. The FD-Markov-LSTM model leverages the FD to identify hierarchical traffic states and utilizes the Markov process to capture the probabilistic transitions between these states. We employ the LSTM model to further capture the residual time series produced by the Markov chain model (assuming a memoryless property) to enhance the estimation and prediction performance. The proposed model's accuracy in estimating and predicting traffic flow is evaluated using empirical data from three case studies conducted in Beijing and Los Angeles. The results highlight a significant improvement in accuracy compared to classical benchmark models such as the Markov model, ARIMA model, k-Nearest Neighbor model, Random Forest model, and LSTM. Specifically, the FD-Markov-LSTM model achieves reductions of over 39% in mean absolute error, 35% in root mean squared error, and 7.4% in mean absolute percentage error. These results clearly demonstrate that the FD-Markov-LSTM model outperforms the benchmark models, enabling more precise predictions of traffic flow. [ABSTRACT FROM AUTHOR]

• Experiments contrasted ten machine learning models in susceptibility prediction. • Hybrid ensemble models significantly outperformed widely-used individual models. • Study profiled the first urban waterlogging susceptibility map in Beijing, China. • Urban road network and densely populated areas face severer waterlogging risk. Urban waterlogging has emerged as a significant problem worldwide, particularly in densely populated cities. Accurate assessment of waterlogging susceptibility at the city scale is crucial for mitigating the risks associated with waterlogging and optimizing municipal design accordingly. However, existing studies on urban waterlogging susceptibility assessment have primarily relied on individual machine learning models. It is worthwhile to explore whether hybrid ensemble models have the potential to enhance the predictive performance. This research presents two hybrid ensemble machine learning models, namely Stacking and Blending, for assessing urban waterlogging susceptibility in the metropolitan area of Beijing, China. The performances of these models are compared with those of the widely used individual machine learning models. Evaluation of all the models is based on metrics such as Accuracy rate and Area Under Curve (AUC) score. The results demonstrate that the Stacking and Blending models consistently outperform the traditional machine learning models, such as Random Forest, Logistic Regression, etc. Through susceptibility analysis and model interpretation with SHAP method, this paper obtains several key findings that low lying areas may not necessarily be areas with severe waterlogging; urban roads and densely populated areas are highly susceptible to becoming high-risk areas for waterlogging in the study area. This study not only highlights the effectiveness of the Stacking and Blending models for urban waterlogging susceptibility assessment but also provides valuable insights for waterlogging mitigation strategies in urban planning. [ABSTRACT FROM AUTHOR]

This article focuses on the study of intelligent art resulting from the fusion growth of artificial intelligence and art, and proposes the process of collision and integration between them. At the same time, this paper explores the space and possibility of the fusion development of AI and art, illustrates how technology reconstructs and further inspires art design innovation. Beijing Winter Olympics opening ceremony is selected as an example, to underline the application of AI technology in large-scale visual art design. In addition, it summarizes also the advantages and limitations of AI applications in art, analyzes the opportunities and challenges facing the integration of such technology and art, and discusses their future development and outlook. [ABSTRACT FROM AUTHOR]

• Spatiotemporal usage patterns of station-free shared bikes are explored. • A topic-based two-stage algorithm is proposed to discover city functional regions. • Region functions are labeled by static POI data and dynamic mobility patterns. Station-free shared bike (SFSB) is a new travel mode that shared bikes are allowed to park in any proper places. It implies that the users are more likely to park the SFSB as close as their destinations. This advantage makes the SFSB data to be an ideal source to understand the land-use distribution. Inspired by the idea in text mining, this paper proposes a topic-based two-stage SFSB data mining algorithm to understand the SFSB user's travel behavior and to discover city functional regions. A region, a function and human mobility patterns are treated as a document, a topic and words, respectively. Then, a region is represented by a distribution of functions, and a function is featured by a distribution of mobility patterns. The point-of-interest data is combined to annotate the clustered regions to discover the real functions. At last, the proposed method is tested using 14-day SFSB data in Beijing and the results are estimated by the Satellite Map data. The proposed methods and the results can be applied to infer the individual's travel purpose through functional regions and to improve land-use planning, etc. [ABSTRACT FROM AUTHOR]

In this paper, the model output machine learning (MOML) method is proposed for simulating weather consultation, which can improve the forecast results of numerical weather prediction (NWP). During weather consultation, the forecasters obtain the final results by combining the observations with the NWP results and giving opinions based on their experience. It is obvious that using a suitable post-processing algorithm for simulating weather consultation is an interesting and important topic. MOML is a post-processing method based on machine learning, which matches NWP forecasts against observations through a regression function. By adopting different feature engineering of datasets and training periods, the observational and model data can be processed into the corresponding training set and test set. The MOML regression function uses an existing machine learning algorithm with the processed dataset to revise the output of NWP models combined with the observations, so as to improve the results of weather forecasts. To test the new approach for grid temperature forecasts, the 2-m surface air temperature in the Beijing area from the ECMWF model is used. MOML with different feature engineering is compared against the ECMWF model and modified model output statistics (MOS) method. MOML shows a better numerical performance than the ECMWF model and MOS, especially for winter. The results of MOML with a linear algorithm, running training period, and dataset using spatial interpolation ideas, are better than others when the forecast time is within a few days. The results of MOML with the Random Forest algorithm, year-round training period, and dataset containing surrounding gridpoint information, are better when the forecast time is longer. [ABSTRACT FROM AUTHOR]

Identifying the structures of buildings in urban areas is a prerequisite for robust urban planning and regeneration. Owing to the diverse structural designs of urban buildings, automated approaches are required to classify building structures. Supervised machine learning is usually employed to classify various building characteristics. However, this approach requires significant labeling effort. Therefore, this paper proposes a new pre-clustering active learning method for building structure classification. The proposed method captures the statistical characteristics of samples and enhances the recognition of the most valuable training samples, thereby substantially reducing the labeling workload and improving the efficiency and effectiveness of classification. This method was tested via the classification of 3718 buildings in Beijing, China, into five common structures. The results showed that the proposed method could reduce labeling effort by 60% while achieving a promising 90% F1 score for overall classification performance, thus indicating its effectiveness. [ABSTRACT FROM AUTHOR]

Battery swap stations have become an important alternative to general charging posts. Predicting battery swapping demand at the station level would be helpful for real-time operation of stations. This paper first provided insights into battery swapping demand patterns by analyzing a real-world dataset which contained 2,529 battery swapping events collected from 36 battery swap stations in Beijing from 31st July to 20th August 2019. Further, we developed a series of deep learning methods to predict the EV battery swapping demand, particularly considering temporal demand patterns obtained from the dataset. The deep learning models were Long Short-Term Memory, Bidirectional Long Short-Term Memory, Gated Recurrent Units, and Bidirectional Gated Recurrent Units. The results showed that the four deep learning models outperformed typical machine learning methods (e.g., support vector regression). An ablation study indicated that incorporating temporal battery swapping demand patterns into the deep learning methods could greatly improve model performance. [ABSTRACT FROM AUTHOR]

Complete and high-quality deformation monitoring data are critical for shield tunnel construction safety and quality. In engineering practices, data missing frequently occurs during instrumentation, adversely impacting further analysis and decision making. Existing imputation methods either ignore the crucial interactions between different parameters during shield tunneling or focus on the global characteristics of deformation data while neglect their local difference. This paper proposes a novel hybrid model, MCCB, combining multi-view matrix completion algorithms, convolutional neural network (CNN), and bidirectional long short-term memory (BiLSTM) algorithms to impute missing deformation values in shield tunnel monitoring data. The performance of the proposed method is verified using bridge deformation data from a practical project in Beijing. Different missing patterns of the bridge deformation data are filled. The experiment results show that the proposed model can effectively learn the various characteristics of the deformation data and outperforms the four selected models and its two sub-models, and can be used to improve the accuracy of the deformation prediction through data imputation. The novelty of this study includes two aspects. First is that the complicated interaction between different parameters and local difference of the data are considered simultaneously. They have not been addressed before by existing studies. Second is that the innovative combination of matrix completion and deep learning algorithm for application in missing deformation values imputation. To our best knowledge, no research on engineering construction has implemented this technique before. [ABSTRACT FROM AUTHOR]

• An imputation model imputes specific missing values in multivariate time series. • Our method outperforms the comparison method when specific values are missing. • Our experiments provide selection principles of hyperparameters. • Our experiment determines the best training method with introduction of noise. Data missing is a ubiquitous phenomenon in multivariate time series analysis because of failure measurements, improper installation or other unfavorable factors. Most imputation methods, such as statistical methods and machine learning methods, are mainly for dealing with random or continuous missing, but do not take into consideration the non-random specific missing situation. This paper proposes an imputation model based on the variational auto-encoders (VAE) and shift correction for specific missing values, which is also extended to the β -VAE model. The shift correction is used to correct the original probability distribution deviation caused by specific values concentrated missing. Then taking the meteorological and air quality data sets in Beijing as the example, this paper mainly explores two common specific missing situations, including large values missing and small values missing. The experimental results show that the proposed model can effectively impute specific missing values, which has high imputation accuracy and robustness. [ABSTRACT FROM AUTHOR]

• Propose a physics-informed transfer learning method for network-scale traffic prediction. • Integrate transfer learning algorithms with network MFD properties and physical invariants. • Develop novel domain adaptation mechanism to transfer domain-invariant traffic flow features. • Alleviate existing data insufficiency, dataset shift, and heavy computational cost problems. • Explore network traffic flow pattern transferability and its relation to network traffic properties. Network traffic flow prediction on a fine-grained spatio-temporal scale is essential for intelligent transportation systems, and extensive studies have been carried out in this area. However, existing methods are mostly data-driven, with stringent requirements on the amount and quality of data. The collected network-scale traffic data are expected to be complete, sufficient, and representative, containing most traffic flow patterns in the road network. Unfortunately, it is very rare that sufficient and representative traffic data across the whole road network in several consecutive weeks are available for model calibration. In real-world applications, data insufficiency and dataset shift problems are prevalent, resulting in the 'cold start' issue in traffic prediction. To deal with the challenges above, this paper develops a two-stage physics-informed transfer learning method for network-scale link-wise traffic flow knowledge transfer under MFD-based physical constraints. In the first stage, the road network is partitioned and similar traffic regions are identified according to the physical invariants and MFD characteristics. In this way, the network-scale link-wise traffic flow pattern transfer between similar regions can be initiated under the assumption that regions with similar aggregated traffic flow patterns are more likely to share comparable link-wise traffic flow features. In the second stage, we propose our knowledge transfer architecture Deep Tensor Adaptation Network (DTAN) to bridge traffic flow knowledge in source and target regions via the parallel Siamese network structure, and further reduce domain discrepancy by imposing two distribution adaptation regularizations. A real-world traffic dataset on the urban expressway network of Beijing is used for numerical tests. The experiment results show that the proposed framework can leverage the trade-off between specific regression task performance in a single region and generalized domain adaptation capacity across multiple regions. The data insufficiency, dataset shift, and heavy computational cost problems are alleviated by improving model transferability. Finally, extensive empirical analysis is carried out to explore traffic flow pattern transferability and its relation to network traffic properties. [ABSTRACT FROM AUTHOR]

This paper introduces a new algorithm (BUNTUS—Built-up, Nighttime Light, and Travel time for Urban Size) using remote sensing techniques to delineate urban boundaries. The paper is part of a larger study of the role of urbanisation in changing fossil fuel emissions. The method combines estimates of land cover, nighttime lights, and travel times to classify contiguous urban areas. The method is automatic, global and uses data sets with enough duration to establish trends. Validation using ground truth from Landsat-8 OLI images revealed an overall accuracy ranging from 60% to 95%. Thus, this approach is capable of describing spatial distributions and giving detailed information of urban extents. We demonstrate the method with examples from Brisbane, Australia, Melbourne, Australia, and Beijing, China. The new method meets the criteria for studying overall trends in urban emissions. [ABSTRACT FROM AUTHOR]

Accurate forecasting of future meteorological elements is critical and has profoundly affected human life in many aspects from rainstorm warning to flight safety. The conventional numerical weather prediction (NWP) sometimes leads to unsatisfactory performance due to inappropriate initial state settings. In this paper, a short-term weather forecasting model based on wavelet packet denoising and Catboost is proposed, which takes advantage of the fusion information combining the historical observation data with the prior knowledge from NWP. The feature selection and spatiotemporal feather addition are also explored to further improve performance. The proposed method is evaluated on the datasets provided by Beijing weather stations. Experimental results demonstrate that compared with many deep-learning or machine-learning methods such as LSTM, Seq2Seq, and random forest, the proposed Catboost model incorporated with wavelet packet denoising can achieve shorter convergence time and higher prediction accuracy. [ABSTRACT FROM AUTHOR]

The notion of path dependence provides a useful perspective to understand the dynamics of industrial space. However, it is much developed on institutional and technological aspects. This paper proposes the idea of spatial path dependence, arguing that previous spatial distribution of economic activities and associated factors in a given industrial space shall affect current and future ones. Availing of big data technology, the spatial distribution is quantified, and spatial path dependence is examined by means of standard deviation ellipse and machine learning method for information service and its sub-sectors in Beijing during the periods of 2008 and 2013. The analysis shows an existence of spatial path dependence for those industries in the two periods. The dominant factors are screened out, which are differ in different sub-sectors and in different periods, but contribute to the same or similar spatial path. The findings call for the attention of the existing situation for industrial spatial planning, and new emerging "people-oriented" factors in influencing the spatial layout of information services industries. • Spatial path dependence is suggested. • Big data technology (BDT) offers new opportunities for industrial space analysis. • Uses case study of Beijing's information services industry development, 2008–2013. • Shows spatial path dependence in industry as whole, and among individual industry types. • Demonstrates value of BDT in identifying and examining spatial path dependence. [ABSTRACT FROM AUTHOR]

• Traffic accident and flow data obtained simultaneously from crowdsourcing approach. • Entire traffic accidents post-impact from occurrence to recovery can be predicted. • Machine learning models were applied and good performance was achieved. • Results improved when updated information added into the model sequentially. Traffic accident management is a critical issue for advanced intelligent traffic management. The increasingly abundant crowdsourcing data and floating car data provide new support for improving traffic accident management. This paper investigates the methods to predict the complicated behavior of traffic flow evolution after traffic accidents using crowdsourcing data. Based on the available data source, the traffic condition is divided into four levels by congestion delay index: severely congested, congested, slow moving and uncongested. Four types of accidents are consequently defined based on the occurrence of each level. A hierarchical scheme is designed for identifying the most congested level and sequentially predicting duration of each level. The proposed model is validated using traffic accident data in 2017 from an anonymous source in Beijing, China by embedding three machine learning algorithms, random forest (RF), support vector machine (SVM) and neural network (NN), in the scheme. The results show NN outperforms the other two models when the assessment is conducted in absolute differences. Meanwhile, RF has a slightly better performance than SVM, especially when predicting the short-period congestion of severely congested level at the first time. By continuously updating the traffic condition information, significant improvement in accuracy can be acquired regardless of the exact model used. This study shows that emerging crowdsourcing data can be used in a real-time analysis of traffic accidents and the proposed model is effective to analyze such data. [ABSTRACT FROM AUTHOR]

Remote sensing data have been widely used in research on population spatialization. Previous studies have generally divided study areas into several sub-areas with similar features by artificial or clustering algorithms and then developed models for these sub-areas separately using statistical methods. These approaches have drawbacks due to their subjectivity and uncertainty. In this paper, we present a study of population spatialization in Beijing City, China based on multisource remote sensing data and town-level population census data. Six predictive algorithms were compared for estimating population using the spatial variables derived from The National Polar-Orbiting Partnership/ Visible Infrared Imaging Radiometer Suite (NPP/VIIRS) night-time light and other remote sensing data. Random forest achieved the highest accuracy and therefore was employed for population spatialization. Feature selection was performed to determine the optimal variable combinations for population modeling by random forest. Cross-validation results indicated that the developed model achieved a mean absolute error (MAE) of 2129.52 people/km2 and a R2 of 0.63. The gridded population density in Beijing at a spatial resolution of 500 m produced by the random forest model was also adjusted to be consistent with the census population at the town scale. By comparison with Google Earth high-resolution images, the remotely-sensed population was qualitatively validated at the intra-town scale. Validation results indicated that remotely sensed results can effectively depict the spatial distribution of population within town-level districts. This study provides a valuable reference for urban planning, public health and disaster prevention in Beijing, and a reference for population mapping in other cities. [ABSTRACT FROM AUTHOR]