Search

Short-term origin–destination (termed as OD) prediction is crucial to improve the operation of urban rail transit (termed as URT). The latest research results show that deep learning can effectively improve the performance of short-term OD prediction and meet the real-time requirements. However, many advanced neural network design ideas have not been fully applied in the field of short-term OD prediction in URT. In this paper, a novel parallel interactive attention network (termed as PIANet) for short-term OD prediction in URT is proposed to further improve the short-term OD prediction accuracy. In the proposed PIANet, a novel omnidirectional attention module (termed as OAM) is proposed to improve the representational power of the network by calculating the feature weights in the channel–spatial dimension. Moreover, a simple yet effective feature interaction is proposed to improve the feature utilization. Based on the two real-world datasets from the Beijing subway, the comparative experiments demonstrate that the proposed PIANet outperforms the state-of-the-art deep learning methods for short-term OD prediction in URT, and the ablation studies demonstrate that the proposed OAMs and feature interaction play an important role in improving the short-term OD prediction accuracy. [ABSTRACT FROM AUTHOR]

The air quality index (AQI), as an indicator to describe the degree of air pollution and its impact on health, plays an important role in improving the quality of the atmospheric environment. Accurate prediction of the AQI can effectively serve people's lives, reduce pollution control costs and improve the quality of the environment. In this paper, we constructed a combined prediction model based on real hourly AQI data in Beijing. First, we used singular spectrum analysis (SSA) to decompose the AQI data into different sequences, such as trend, oscillation component and noise. Then, bidirectional long short-term memory (BiLSTM) was introduced to predict the decomposed AQI data, and a light gradient boosting machine (LightGBM) was used to integrate the predicted results. The experimental results show that the prediction effect of SSA-BiLSTM-LightGBM for the AQI data set is good on the test set. The root mean squared error (RMSE) reaches 0.6897, the mean absolute error (MAE) reaches 0.4718, the symmetric mean absolute percentage error (SMAPE) reaches 1.2712%, and the adjusted R2 reaches 0.9995. [ABSTRACT FROM AUTHOR]

Time series forecasting and analysis are widely used in many fields and application scenarios. Time series historical data reflects the change pattern and trend, which can serve the application and decision in each application scenario to a certain extent. In this paper, we select the time series prediction problem in the atmospheric environment scenario to start the application research. In terms of data support, we obtain the data of nearly 3500 vehicles in some cities in China fromRunwoda Research Institute, focusing on the major pollutant emission data of non-road mobile machinery and high emission vehicles in Beijing and Bozhou, Anhui Province to build the dataset and conduct the time series prediction analysis experiments on them. This paper proposes a P-gLSTNet model, and uses Autoregressive Integrated Moving Average model (ARIMA), long and short-term memory (LSTM), and Prophet to predict and compare the emissions in the future period. The experiments are validated on four public data sets and one self-collected data set, and the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) are selected as the evaluationmetrics. The experimental results show that the proposed P-gLSTNet fusion model predicts less error, outperforms the backbone method, and is more suitable for the prediction of time-series data in this scenario. [ABSTRACT FROM AUTHOR]

To predict and explore the return period wind speed distribution in Beijing urban area, based on the short-term measured wind speed record, the measured independent storm peak samples are extracted and the Monte–Carlo numerical simulation method is used to randomly generate pseudo-independent storm peak samples with the same distribution as the independent storm peak samples. In addition, the appropriate threshold is used to select and extract the over-threshold independent storm peak samples from the measured samples. And, then, the return period wind speed of the whole wind direction is predicted. Further, the traditional Cook method is used to predict and analyze the return period wind speed of each wind direction according to the measured wind speed data. The results show that the return period wind speed prediction results of the whole wind direction corresponding to the simulated pseudo samples and the measured over-threshold samples are basically close to each other, and the maximum relative deviation is less than 7%. The mean relative deviation of the return period wind speed prediction results is about 10.6% between each wind direction and the whole wind direction, and the mean relative deviation is about 9.4% between the RPWS prediction result of each wind direction and the design value of the code. In addition, the return period wind speed prediction values of the west by southwest, northwest and north by northeast wind directions exceed the design value of the code, while the predicted values of the other wind directions are within the envelope range of the design value of the code. Finally, the research content of this paper can provide some reference for the wind resistance design analysis of building structures in Beijing area. [ABSTRACT FROM AUTHOR]

To deal with the issues of high computational cost and prediction uncertainty of numerical models in train-induced ground-borne vibration prediction, a prediction method based on transfer learning is proposed in this study. In this method, the vehicle–track-coupled analytical model and three-dimensional finite element model are first used to calculate the train-induced ground vibration under various condition variables, and these data were used as training samples to pre-train the deep neural network models. Numerous train-induced ground vibration experiments were then conducted along the metro lines in Beijing, and those measured vibration data were used to fine-tune the pre-trained deep neural network model with the transfer learning strategy. A random variable obeying a Gaussian distribution is assumed over the predicted vibration acceleration levels to model the randomness of train-induced vibration, and the parameters of this distribution were determined by the statistical results of vibration monitoring data in the metro tunnels. The fully trained model could complete the prediction of train-induced ground vibration in seconds. Finally, a case study was carried out, by comparing the probabilistic prediction results with the statistical results of the field measurements, and the feasibility and the improvement of the proposed method were demonstrated. [ABSTRACT FROM AUTHOR]

Long-term exposure to air environments full of suspended particles, especially PM2.5, would damage people's health and life seriously. Nowadays, plenty of air quality monitoring networks have been established in several countries. Timely and accurate prediction of PM2.5 concentration is of great significance. However, current studies on PM2.5 concentration assume that the training set and testing set have the same data distribution, which leads to low accuracy and weak robustness of the model. In this paper, in order to predict accurately and solve the problem that the probability distribution of PM2.5 data may change over time, a feature transfer learning for time series model called adaptive GRU (ADGRU) is proposed. First, the training set data of Beijing PM2.5 concentration is divided into source domain data and target domain data. Then an adaptive bandwidth method is applied in ADGRU to improve its accuracy. Finally, extensive experimental simulations show that ADGRU can learn the time distribution changes of data efficiently, and predict the trend of PM2.5 concentration accurately, which may provide effective reference for people's travel and health. [ABSTRACT FROM AUTHOR]

Emergencies have a significant impact on the passenger flow of urban rail transit. It is of great practical significance to accurately predict the urban rail transit passenger flow and carry out research on its temporal and spatial distributions under emergency conditions. Urban rail transit operating units currently use video surveillance information mainly to process emergencies and rarely use computer vision technology to analyze passenger flow information collected. Accordingly, this paper proposes a passenger flow-based temporal and spatial distribution model for urban rail transit emergencies based on the CPT. First, this paper clarifies the categories and classification of urban rail transit emergencies, analyzes the factors affecting passenger route selection, and establishes a generalized travel cost model for passengers under emergencies. Second, this paper establishes a passenger route choice behavior model for urban rail transit based on the cumulative prospect theory. Finally, taking Beijing as an example, this paper analyzes passenger travel behavior under emergencies based on multiple logistic regression models and analyzes the impact of emergencies on rail transit travel behavior. The research results show that the cumulative prospect theory can better describe the route choice behavior of rail transit passengers under emergencies than the existing models, and this model is of great significance for handling urban rail transit emergencies. The model proposed in this paper can provide a theoretical basis for the government and relevant departments to formulate traffic management measures. [ABSTRACT FROM AUTHOR]

Intelligent connected vehicles (ICVs) have played an important role in improving the intelligence degree of transportation systems, and improving the trajectory prediction capability of ICVs is beneficial for traffic efficiency and safety. In this paper, a real-time trajectory prediction method based on vehicle-to-everything (V2X) communication is proposed for ICVs to improve the accuracy of their trajectory prediction. Firstly, this paper applies a Gaussian mixture probability hypothesis density (GM-PHD) model to construct the multidimension dataset of ICV states. Secondly, this paper adopts vehicular microscopic data with more dimensions, which is output by GM-PHD as the input of LSTM to ensure the consistency of the prediction results. Then, the signal light factor and Q-Learning algorithm were applied to improve the LSTM model, adding features in the spatial dimension to complement the temporal features used in the LSTM. When compared with the previous models, more consideration was given to the dynamic spatial environment. Finally, an intersection at Fushi Road in Shijingshan District, Beijing, was selected as the field test scenario. The final experimental results show that the GM-PHD model achieved an average error of 0.1181 m, which is a 44.05% reduction compared to the LiDAR-based model. Meanwhile, the error of the proposed model can reach 0.501 m. When compared to the social LSTM model, the prediction error was reduced by 29.43% under the average displacement error (ADE) metric. The proposed method can provide data support and an effective theoretical basis for decision systems to improve traffic safety. [ABSTRACT FROM AUTHOR]

Air quality plays a vital role in people's health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal and spatial dimensions. Deep models, with their ability to model strong nonlinearities, have become the primary methods for air quality forecasting. However, because of the lack of mechanism-based analysis, uninterpretability forecasting makes decisions risky, especially when the government makes decisions. This paper proposes an interpretable variational Bayesian deep learning model with information self-screening for PM2.5 forecasting. Firstly, based on factors related to PM2.5 concentration, e.g., temperature, humidity, wind speed, spatial distribution, etc., an interpretable multivariate data screening structure for PM2.5 forecasting was established to catch as much helpful information as possible. Secondly, the self-screening layer was implanted in the deep learning network to optimize the selection of input variables. Further, following implantation of the screening layer, a variational Bayesian gated recurrent unit (GRU) network was constructed to overcome the complex distribution of PM2.5 and achieve accurate multi-step forecasting. The high accuracy of the proposed method is verified by PM2.5 data in Beijing, China, which provides an effective way, with multiple factors for PM2.5 forecasting determined using deep learning technology. [ABSTRACT FROM AUTHOR]

Day by day pollution in cities is increasing due to urbanization. One of the biggest challenges posed by the rapid migration of inhabitants into cities is increased air pollution. Sustainable Development Goal 11 indicates that 99 percent of the world's urban population breathes polluted air. In such a trend of urbanization, predicting the concentrations of pollutants in advance is very important. Predictions of pollutants would help city administrations to take timely measures for ensuring Sustainable Development Goal 11. In data engineering, imputation and the removal of outliers are very important steps prior to forecasting the concentration of air pollutants. For pollution and meteorological data, missing values and outliers are critical problems that need to be addressed. This paper proposes a novel method called multiple iterative imputation using autoencoder-based long short-term memory (MIA-LSTM) which uses iterative imputation using an extra tree regressor as an estimator for the missing values in multivariate data followed by an LSTM autoencoder for the detection and removal of outliers present in the dataset. The preprocessed data were given to a multivariate LSTM for forecasting PM2.5 concentration. This paper also presents the effect of removing outliers and missing values from the dataset as well as the effect of imputing missing values in the process of forecasting the concentrations of air pollutants. The proposed method provides better results for forecasting with a root mean square error (RMSE) value of 9.8883. The obtained results were compared with the traditional gated recurrent unit (GRU), 1D convolutional neural network (CNN), and long short-term memory (LSTM) approaches for a dataset of the Aotizhonhxin area of Beijing in China. Similar results were observed for another two locations in China and one location in India. The results obtained show that imputation and outlier/anomaly removal improve the accuracy of air pollution forecasting. [ABSTRACT FROM AUTHOR]

This paper proposes a feedback, rolling and adaptive operation decision-making mechanism for coupling and nesting of time scales. It is aimed at the change of time scale and the dynamics in the operation process, considering the relationship between operation period and multi-time scales. The key point is to integrate forecasting and operation in order to adapt to the multi-time scales dynamic change in the operation process. The operation process is divided into different time scales; forecasting and operation model method libraries are constructed, and the progressive updating and nesting mechanism are used to realize the process dynamic operation, according to the regulation period or operation period of the reservoir. Taking the Miyun Reservoir in Beijing, China as the research object, the operation mechanism is integrated into the operation process, and the complex forecasting operation and control mechanism are integrated, based on the integrated platform and using modern information technology. The forecasting and operation method uses classic different models, which can be selected based on different goals. The forecasting inflow is used as input, and the output is the water distribution plan, more importantly, the mechanism in the operation process is the key point. This is a rolling modification of the inflow process in the next stage, and the operation plan also changes accordingly. The feasibility, effectiveness, rationality and flexibility of the reservoir dynamic and adaptive operation are verified, so that the reservoir operation is dynamically changing and adapting to the changing demand. The proposed operation mechanism has scientific value and guiding significance to improve the reservoir operation theory, and it provides decision support for the actual reservoir operation and operation business. [ABSTRACT FROM AUTHOR]

Missing data presents a significant challenge when forecasting unknown data in lime series. To address this issue. this paper proposes an Altenuated Long and Short-Term Memory model based on a dec·aying filliction, which is abbreviated as A D-LSTM, for forecasting unknown data in time series. As strong correlations exist in adjacent data, the Grey model is level·aged to predict and impute missing values in small-sample datasets. To improve the accuracy offorecasting in time series with missing data, we introduce subspace decomposition, which can correct errors in the memory state cell caused by missing elements, and a time decay function, which utilizes the number of adjacent continuous missing data as a weight to modify the memory cell and enables the model to detect the existence of missing elements, into the LSTM unit. These enhancements reduce the impact of imptited data on model training in time series analysis. Finally, to verify the effectiveness of our proposed method, we conduct experimental validation and comparative analysis using the Beijing house price dataset. Our results indicate that the AD-LSTM model perfbrnis better in reducing the impact of missing data and achieving lower fbrecast ert·ors compared to the baseline models. [ABSTRACT FROM AUTHOR]

In recent years, with the continuous improvement of urban public transportation capacity, citizens' travel has become more and more convenient, but there are still some potential problems, such as morning and evening peak congestion, imbalance between the supply and demand of vehicles and passenger flow, emergencies, and social local passenger flow surged due to special circumstances such as activities and inclement weather. If you want to properly guide the local passenger flow and make a reasonable deployment of operating buses, it is necessary to grasp the changing law of public transportation short-term passenger flow. This paper builds a short-term passenger flow prediction model for urban public transportation based on the idea of integrated learning. The goal is to use the integrated model to accurately predict the short-term passenger flow of urban public transportation, using Multivariable Linear Regression (MLR), K-Nearest Neighbor (KNN), eXtreme Gradient Boosting (XGBoost), and Gated Recurrent Unit (GRU) as the four seed models, and then use regression algorithm to integrate the model and predict the passenger flow, station boarding and landing, and cross-sectional passenger flow data of the typical representative line 428 in the "Huitian Area" of Beijing from January 1, 2020, to May 31, 2020. Finally, the prediction results of the submodels are compared with those of the integrated model to verify the superiority of the integrated model. The research results of this paper can enrich the short-term passenger flow forecasting system of urban public transportation and provide effective data support and scientific basis for the passenger flow, vehicle management, and dispatch of urban public transportation. [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]

Copyright of Advances in Atmospheric Sciences is the property of Springer Nature 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.)

The predictions from time series data can help us sense development trends and make scientific decisions in advance. The commonly used forecasting methods with backpropagation consume a lot of computational resources. The deep echo state network (DeepESN) is an advanced prediction method with a deep neural network structure and training algorithm without backpropagation. In this paper, a Bayesian optimization algorithm (BOA) is proposed to optimize DeepESN to address the problem of increasing parameter scale. Firstly, the DeepESN was studied and constructed as the basic prediction model for the time series data. Secondly, the BOA was reconstructed, based on the DeepESN, for optimal parameter searching. The algorithm is proposed within the framework of the DeepESN. Thirdly, an experiment was conducted to verify the DeepESN with a BOA within three datasets: simulation data generated from computer programs, a real humidity dataset collected from Beijing, and a power load dataset obtained from America. Compared with the models of BP (backpropagation), LSTM (long short-term memory), GRU (gated recurrent unit), and ESN (echo state network), DeepESN obtained optimal results, which were 0.0719, 18.6707, and 764.5281 using RMSE evaluation. While getting better accuracy, the BOA optimization time was only 323.4 s, 563.2 s, and 9854 s for the three datasets. It is more efficient than grid search and grey wolf optimizer. [ABSTRACT FROM AUTHOR]

Highly accurate monthly rainfall predictions can provide early warnings for rain-related disasters, such as floods and droughts, and allow governments to make timely decisions. This paper proposes a two-phase error compensation model based on a gated recurrent unit (GRU), variational mode decomposition (VMD), and error compensation mechanism (ECM) (GRU-VMD-ECM) for accurate multi-step-ahead monthly rainfall forecasts. In the first phase, the GRU model is used to make an initial monthly rainfall prediction, and the error series is extracted. In the second phase, the error series is decomposed into eight subseries using the VMD method. Each subseries is then input into the GRU model to build different forecasting models. These predicted error sequences are added to the initial prediction results to obtain the final forecast. The model's performance is tested using six evaluation indicators based on Beijing's monthly rainfall data from 1951 to 2018. The results show that the error compensation mechanism significantly improved the prediction accuracy, particularly in the Nash–Sutcliffe efficiency (NSE) of single-step-ahead prediction which recorded a substantial increase of 281.16% from 0.259981 to 0.990944, as well as a decrease in root mean square error (RMSE) from 2.257580 to 0.249746. Furthermore, the GRU-VMD-ECM model outperforms the RF, GRU-CNN, and VMD-GRU models in terms of precision across all forecasting horizons. These findings highlight the potential of the GRU-VMD-ECM model in providing highly accurate monthly rainfall predictions for early warnings and informed decision-making by governments. [ABSTRACT FROM AUTHOR]

Air pollution has become a critical factor affecting the health of human beings. Forecasting the trend of air pollutants will be of considerable help to public health, including improving early-warning systems. The article designs a novel hybrid deep learning framework FPHFA (FPHFA is the abbreviation of the title of this paper) for PM2.5 concentration forecasting is proposed, which learns spatially correlated features and long-term dependencies of time series data related to PM2.5. Owing to the complex nonlinear dynamic and spatial features of pollutant data, the FPHFFA model combines multi-channel one-dimensional convolutional neural networks, bi-directional long short-term memory neural networks, and attention mechanisms for the first time. Multi-channel 1D CNNs are applied to capture trend features between some sites and overall spatial characteristics of PM2.5 concentration, Bi LSTMs are used to learn the temporal correlation of PM2.5 concentration, and the attention mechanism is used to focus more effective information at different moments. We carried out experimental evaluations using the Beijing dataset, and the outcomes show that our proposed model can effectively handle PM2.5 concentration prediction with satisfactory accuracy. For the prediction task from 1 to 12 h, our proposed prediction model performs well. The FPHFA also achieves satisfactory results for prediction tasks from 13 to 96 h. [ABSTRACT FROM AUTHOR]

For prediction of urban remote sensing surface temperature, cloud, cloud shadow and snow contamination lead to the failure of surface temperature inversion and vegetation‐related index calculation. A time series prediction framework of urban surface temperature under cloud interference is proposed in this paper. This is helpful to solve the problem of the impact of data loss on surface temperature prediction. Spatial and temporal variation trends of surface temperature and vegetation index are analyzed using Landsat 7/8 remote sensing data of 2010 to 2019 from Beijing. The geographically weighed regression (GWR) method is used to realize the simulation of surface temperature based on the current date. The deep learning prediction network based on convolution and long short‐term memory (LSTM) networks was constructed to predict the spatial distribution of surface temperature on the next observation date. The time series analysis shows that the NDBI is less than −0.2, which indicates that there may be cloud contamination. The land surface temperature (LST) modeling results show that the precision of estimation using GWR method on impervious surface and water bodies is superior compared to the vegetation area. For LST prediction using deep learning methods, the result of the prediction on surface temperature space distribution was relatively good. The purpose of this study is to make up for the missing data affected by cloud, snow, and other interference factors, and to be applied to the prediction of the spatial and temporal distributions of LST. This article is categorized under:Technologies > Machine Learning [ABSTRACT FROM AUTHOR]

The rapid growth of passenger flows has brought a series of challenges to the environment and safety management of tourist attractions. It is vital to establish an accurate passenger flow prediction model to reduce the risks associated with human flows. Owing to the limitation of a single data source, the existing research on the prediction of tourist flows in scenic spots ignores the impact of public transport passengers on the internal tourist flow in scenic areas. The prediction model lacks the learning process of data samples, and the ability of generalization and self-study is weak. In this paper, we propose a new method of predicting passenger flow in scenic areas based on a convolutional neural network and long short-term memory (CNN-LSTM) hybrid neural network (HNN) model, which considers the multisource traffic flow around a scenic area. It uses a series of HNNs to mine the temporal and spatial correlation between the passenger flows from multiple sources and solves the problem of data stability dependence. The time series of the passenger flow in the study area was designed and extracted on the basis of the spatial analysis of South Luogu Lane in Beijing, and the input structure was constructed by combining the multisource traffic passenger flow dimension. This model for predicting passenger flow in scenic areas based on CNN-LSTM provides a reference for the comprehensive application of multisource data in scenic areas and has high accuracy and robustness. [ABSTRACT FROM AUTHOR]

In rainy weather, the accurate prediction of traffic status not only helps road traffic managers to formulate traffic management methods but also helps travelers design travel routes and even adjust travel time. In this paper, based on six-dimensional data (e.g., past and present spatiotemporal traffic status, road network structure, pavement type, water accumulation, and rainfall level), a fuzzy neural network (FNN) prediction system is proposed to predict traffic status. The traffic status evolution trend is related not only to the existing traffic but also to the new traffic demand. Therefore, the FNN prediction system designed includes offline and online parts using the data of the past and the day separately and avoids the forecast of new traffic demand. The fuzzy C-means clustering algorithm is applied to cluster traffic status data under similar rainy weather in the past to form an offline initial dataset, which is used to train FNN weight parameters. The online part uses real-time detection data and the parameters trained by the offline part to further predict the traffic status and returns the prediction errors to the offline part to correct the weight parameters to further improve prediction accuracy. Finally, the FNN prediction system is verified using real Beijing expressway network data. The verification results show that the prediction system can guarantee prediction accuracy and can be used to effectively identify traffic status. [ABSTRACT FROM AUTHOR]

In a multimodal public transport network, transfers are inevitable. Planning and managing an efficient transfer connection is thus important and requires an understanding of the factors that influence those transfers. Existing studies on predicting passenger transfer flows have mainly used transit assignment models based on route choice, which need extensive computation and underlying behavioral assumptions. Inspired by studies that use network properties to estimate public transport (PT) demand, this paper proposes to use the network properties of a multimodal PT system to explain transfer flows. A statistical model is estimated to identify the relationship between transfer flow and the network properties in a joint bus and metro network. Apart from transfer time, the number of stops, and bus lines, the most important network property we propose in this study is transfer accessibility. Transfer accessibility is a newly defined indicator for the geographic factors contributing to the possibility of transferring at a station, given its position in a multimodal PT network, based on an adapted gravity-based measure. It assumes that transfer accessibility at each station is proportional to the number of reachable points of interest within the network and dependent on a cost function describing the effect of distance. The R-squared of the regression model we propose is 0.69, based on the smart card data, PT network data, and Points of Interest (POIs) data from the city of Beijing, China. This suggests that the model could offer some decision support for PT planners especially when complex network assignment models are too computationally intensive to calibrate and use. [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]

Traffic prediction is the cornerstone of intelligent transportation system. In recent years, graph neural network has become the mainstream traffic prediction method due to its excellent processing ability of unstructured data. However, the network relationship in the real world is more complex. Multiple nodes and various associations such as different types of stations and lines in rail transit always exist at the same time. In an end-to-end model, the training accuracy will suffer if the same weights are assigned to multiple views. Thus, this paper proposes a framework with multi-view and multi-layer attention, which aims to solve the problem of node prediction involving multiple relationships. Specifically, the proposed model maps multiple relationships into multiple views. A graph convolutional neural network of multiple views with multi-layer attention learns the optimal regression of nodes. Furthermore, the model uses an autoencoder module to alleviate the over-smoothing problem during the training phase. With the historical dataset of Beijing rail transit, the experiment proves that the prediction accuracy of the model is generally better than the baseline traffic prediction algorithms. [ABSTRACT FROM AUTHOR]

With the rapid growth of car ownership, traffic congestion has become one of the most serious social problems. For us, accurate real-time travel time predictions are especially important for easing traffic congestion, enabling traffic control and management, and traffic guidance. In this paper, we propose a method to predict urban road travel time by combining XGBoost and LightGBM machine learning models. In order to obtain a relatively complete data set, we mine the GPS data of Beijing and combine them with the weather feature to consider the obtained 14 features as candidate features. By processing and analyzing the data set, we discussed in detail the correlation between each feature and the travel time and the importance of each feature in the model prediction results. Finally, the 10 important features screened by the LightGBM and XGBoost models were used as key features. We use the full feature set and the key feature set as input to the model to explore the effect of different feature combinations on the prediction accuracy of the model and then compare the prediction results of the proposed fusion model with a single model. The results show that the proposed fusion model has great advantages to urban travel time prediction. [ABSTRACT FROM AUTHOR]

The accurate prediction of short-term passenger flow is of high importance to efficiently manage the passenger flow of metro systems and adjust timetable accordingly. However, the existing methods of passenger flow prediction cannot achieve adequate accurate results due to its complex nonlinear spatiotemporal characteristics. To improve the accuracy of short-term passenger flow prediction, this paper proposes a deep learning model based on a spatiotemporal framework. Firstly, the graph convolutional network, which incorporates prior domain knowledge (such as travel time and origin–destination demand), is used to extract spatial features of passenger flow. Secondly, the attention mechanism is integrated into the gated recurrent unit to extract the time correlation of passenger flow. Finally, external factors are introduced to capture their impact on passenger flow as well. A case study of the Beijing Subway system is illustrated to verify the performance of the proposed model. The results show that compared with the existing models, the proposed model achieves the highest prediction accuracy and strong robustness. Furthermore, we demonstrate that the adjacency matrix based on travel time outperforms the one based on OD demand, especially during evening peak hours. In addition, it is also verified that the attention mechanism and external factors can improve the prediction performance of the proposed model. [ABSTRACT FROM AUTHOR]

Compared with mechanism-based modeling methods, data-driven modeling based on big data has become a popular research field in recent years because of its applicability. However, it is not always better to have more data when building a forecasting model in practical areas. Due to the noise and conflict, redundancy, and inconsistency of big time-series data, the forecasting accuracy may reduce on the contrary. This paper proposes a deep network by selecting and understanding data to improve performance. Firstly, a data self-screening layer (DSSL) with a maximal information distance coefficient (MIDC) is designed to filter input data with high correlation and low redundancy; then, a variational Bayesian gated recurrent unit (VBGRU) is used to improve the anti-noise ability and robustness of the model. Beijing's air quality and meteorological data are conducted in a verification experiment of 24 h PM2.5 concentration forecasting, proving that the proposed model is superior to other models in accuracy. [ABSTRACT FROM AUTHOR]

Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around the world. Among air pollutants, Particulate Matter with a diameter of less than 2.5 μ m ( P M 2.5 ) is a serious health problem. It causes various illnesses such as respiratory tract and cardiovascular diseases. Hence, it is necessary to accurately predict the P M 2.5 concentrations in order to prevent the citizens from the dangerous impact of air pollution beforehand. The variation of P M 2.5 depends on a variety of factors, such as meteorology and the concentration of other pollutants in urban areas. In this paper, we implemented a deep learning solution to predict the hourly forecast of P M 2.5 concentration in Beijing, China, based on CNN-LSTM, with a spatial-temporal feature by combining historical data of pollutants, meteorological data, and P M 2.5 concentration in the adjacent stations. We examined the difference in performances among Deep learning algorithms such as LSTM, Bi-LSTM, GRU, Bi-GRU, CNN, and a hybrid CNN-LSTM model. Experimental results indicate that our method "hybrid CNN-LSTM multivariate" enables more accurate predictions than all the listed traditional models and performs better in predictive performance. [ABSTRACT FROM AUTHOR]

It is of great importance to predict or assess the water shortage risk to take some effective measures to reduce risk and losses. A new method of selecting water shortage risk factors is proposed according to the definition of a matrix-based Renyi's α -order entropy in this paper. Important factors were detected in terms of the values of mutual information between water shortage risk and risk factors. Furthermore, a logistic regression model is built to predict water shortage risk. Risks in Beijing during the period of 1979–2017 are evaluated to verify the performance of the model. Water consumption per GDP, water resources per capita and precipitation are the sensitive factors for water shortage risk. Water shortage risks in 2020 under different situations of precipitation are calculated by using the model. The result shows that the water shortage risk is greater than 0.9 with a possibility of 0.56 and greater than 0.5 with a possibility of 0.56 without consideration of the transferred and reclaimed water use. The average water shortage risk declines considerably by using the transferred and reclaimed water. However, the water shortage risk still exceeds 0.9 with a possibility of 0.32. The predicted risks are consistent with the observed risks in 2020 under different conditions of precipitation. [ABSTRACT FROM AUTHOR]

The generalized regression neural network (GRNN) is one of the most effective neural models in the field of information prediction. In this paper, we take advantage of the hesitant fuzzy set (HFS) and develop the GRNN under the hesitant fuzzy environment. However, the performance of the GRNN only depends on the smooth factor after determining the input and output variables. To determine the most appropriate smooth factor of network, we propose an improved fruit fly optimization algorithm with fast decreasing step (FDS-FOA) based on a dynamic step size function. A specific implementation process of the optimized GRNN based on FDS-FOA is also presented. Moreover, we apply the proposed model to the prediction of air quality index (AQI) in Beijing. Comparative analysis and sensitivity analysis are further conducted to illustrate the advantages of the optimized GRNN based on FDS-FOA. [ABSTRACT FROM AUTHOR]

Accurate monitoring of air quality can no longer meet people's needs. People hope to predict air quality in advance and make timely warnings and defenses to minimize the threat to life. This paper proposed a new air quality spatiotemporal prediction model to predict future air quality and is based on a large number of environmental data and a long short-term memory (LSTM) neural network. In order to capture the spatial and temporal characteristics of the pollutant concentration data, the data of the five sites with the highest correlation of time-series concentration of PM2.5 (particles with aerodynamic diameter ≤2.5 mm) at the experimental site were first extracted, and the weather data and other pollutant data at the same time were merged in the next step, extracting advanced spatiotemporal features through long- and short-term memory neural networks. The model presented in this paper was compared with other baseline models on the hourly PM2.5 concentration data set collected at 35 air quality monitoring sites in Beijing from January 1, 2016, to December 31, 2017. The experimental results show that the performance of the proposed model is better than other baseline models. [ABSTRACT FROM AUTHOR]

Ultra-short-term load demand forecasting is significant to the rapid response and real-time dispatching of the power demand side. Considering too many random factors that affect the load, this paper combines convolution, long short-term memory (LSTM), and gated recurrent unit (GRU) algorithms to propose an ultra-short-term load forecasting model based on deep learning. Firstly, more than 100,000 pieces of historical load and meteorological data from Beijing in the three years from 2016 to 2018 were collected, and the meteorological data were divided into 18 types considering the actual meteorological characteristics of Beijing. Secondly, after the standardized processing of the time-series samples, the convolution filter was used to extract the features of the high-order samples to reduce the number of training parameters. On this basis, the LSTM layer and GRU layer were used for modeling based on time series. A dropout layer was introduced after each layer to reduce the risk of overfitting. Finally, load prediction results were output as a dense layer. In the model training process, the mean square error (MSE) was used as the objective optimization function to train the deep learning model and find the optimal super parameter. In addition, based on the average training time, training error, and prediction error, this paper verifies the effectiveness and practicability of the load prediction model proposed under the deep learning structure in this paper by comparing it with four other models including GRU, LSTM, Conv-GRU, and Conv-LSTM. [ABSTRACT FROM AUTHOR]

Short-term traffic prediction under corrupted or missing data for large-scale transportation networks has become an important and challenging topic in recent decades. Since the critical roads have predictive power on their adjacent roads, this paper proposes a novel hybrid short-term traffic state prediction method based on critical road selection optimization. First, the utility function of the quality of service (QoS) for the critical roads in a large-scale road network is proposed based on the coverage and the data score. Then, the critical road selection optimization model in the transportation networks is presented by selecting an appropriate set of critical roads with the maximum proportion of the total calculation resources to maximize the utility value of the QoS. Also, an innovative critical road selection method is introduced, which is considering the topological structure and the mobility of the urban road network. Subsequently, the traffic speed of the critical roads is regarded as the input of the convolutional long short-term memory neural network to predict the future traffic states of the entire network. Experiment results on the Beijing traffic network indicate that the proposed method outperforms prevailing DL approaches in the case of considering critical road sections. [ABSTRACT FROM AUTHOR]

Soil moisture is an important indicator for agricultural planting and agricultural water management. People have been trying to guide crop cultivation, formulate irrigation systems, and develop intelligent agriculture by knowing exactly what the soil moisture is in real time. This paper considers the impact of meteorological parameters on soil-moisture change and proposes a soil-moisture prediction method based on the Gene Expression Programming (GEP) algorithm. The prediction model is tested on datasets from Shunyi, Yanqing and Daxing agricultural farms, Beijing. The results show that the GEP model can predict soil moisture with a maximum correlation coefficient of 0.98, and the root-mean-square errors in three different farms were below 2.32. [ABSTRACT FROM AUTHOR]

Using real-time correction technology for typhoons, this paper discusses real-time correction for forecasting the track of four typhoons during 2009 and 2010 in Japan, Beijing, Guangzhou, and Shanghai. It was determined that the short-time forecast effect was better than the original objective mode. By selecting four types of integration schemes after multiple mode path integration for those four objective modes, the forecast effect of the multi-mode path integration is better, on average, than any single model. Moreover, multi-mode ensemble forecasting has obvious advantages during the initial 36h. [ABSTRACT FROM AUTHOR]

Mobile edge computing (MEC) pushes computing resources to the edge of the network and distributes them at the edge of the mobile network. Offloading computing tasks to the edge instead of the cloud can reduce computing latency and backhaul load simultaneously. However, new challenges incurred by user mobility and limited coverage of MEC server service arise. Services should be dynamically migrated between multiple MEC servers to maintain service performance due to user movement. Tackling this problem is nontrivial because it is arduous to predict user movement, and service migration will generate service interruptions and redundant network traffic. Service interruption time must be minimized, and redundant network traffic should be reduced to ensure service quality. In this paper, the container live migration technology based on prediction is studied, and an online prediction method based on map data that does not rely on prior knowledge such as user trajectories is proposed to address this challenge in terms of mobility prediction accuracy. A multitier framework and scheduling algorithm are designed to select MEC servers according to moving speeds of users and latency requirements of offloading tasks to reduce redundant network traffic. Based on the map of Beijing, extensive experiments are conducted using simulation platforms and real-world data trace. Experimental results show that our online prediction methods perform better than the common strategy. Our system reduces network traffic by 65% while meeting task delay requirements. Moreover, it can flexibly respond to changes in the user's moving speed and environment to ensure the stability of offload service. [ABSTRACT FROM AUTHOR]

With the development of modern cities, urban rail transit has become an indispensable part of residents' travelling mode, and accurate prediction of urban rail transit passenger flow is particularly important. However, due to the non-linearity and non-stability of passenger flow, the low quality of big data and the lack of data make it more and more difficult to predict the passenger flow of urban rail transit. In this paper, we propose a unique model structure that ingeniously integrates Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN) with fused residual network connections, and a self-attention mechanism. The design of this model is primarily to effectively handle complex and low-quality data, which is often prevalent in passenger flow prediction scenarios. To validate the effectiveness of the proposed model, we used data from the Beijing urban rail transit in 2016 for prediction. In the experiments, we performed comparison study and ablation study. The experimental results show that the model proposed in this paper has significantly improved prediction accuracy in both horizontal and vertical comparisons. This outcome substantiates that the proposed model can not only effectively handle complex and low-quality data but also extract short-term features and long-term dependency features of passenger flow well, thereby achieving more accurate predictions. • Integration of GRU, CNN with fused residual connections, and self-attention mechanism constitutes a novel model. • The model is capable of handling complex and lower-quality data, significantly improving the accuracy of predictions. • The model can simultaneously extract short-term features and long-term dependency features from time series. [ABSTRACT FROM AUTHOR]

Leisure time is crucial for personal development and leisure consumption. Accurate prediction of leisure time and analysis of its influencing factors creates a benefit by increasing personal leisure time. We predict leisure time and analyze its key influencing factors according to survey data of Beijing residents' time allocation in 2011, 2016, and 2021, with an effective sample size of 3356. A Light Gradient Boosting Machine (LightGBM) model is utilized to classify and predict leisure time, and the SHapley Additive exPlanation (SHAP) approach is utilized to conduct feature importance analysis and influence mechanism analysis of influencing factors from four perspectives: time allocation, demographics, occupation, and family characteristics. The results verify that LightGBM effectively predicts personal leisure time, with the test set's accuracy, recall, and F1 values being 0.85 and the AUC value reaching 0.91. The results of SHAP highlight that work/study time within the system is the main constraint on leisure time. Demographic factors, such as gender and age, are also of great significance for leisure time. Occupational and family heterogeneity exist in leisure time as well. The results contribute to the government improving the public holiday system, companies designing personalized leisure products for users with different leisure characteristics, and residents understanding and independently increasing their leisure time. [ABSTRACT FROM AUTHOR]

PM2.5 (particulate matter with a size/diameter ≤ 2.5 μm) is an important air pollutant that affects human health, especially in urban environments. However, as time-series data of PM2.5 are non-linear and non-stationary, it is difficult to predict future PM2.5 distribution and behavior. Therefore, in this paper, we propose a hybrid short-term urban PM2.5 prediction model based on variational mode decomposition modified by the correntropy criterion, the state transition simulated annealing (STASA) algorithm, and a support vector regression model to overcome the disadvantages of traditional forecasting techniques which consider different environmental factors. Two experiments were performed with the model to assess its effectiveness and predictive ability: in experiment I, we verified the performance of STASA on benchmark functions, while in experiment II, we used PM2.5 data from different epochs and regions of Beijing to verify its forecasting performance. The experimental results showed that the proposed model is robust and can achieve satisfactory prediction results under different conditions compared with current forecasting techniques. [ABSTRACT FROM AUTHOR]

The environment and development are major issues of general concern. After much suffering from the harm of environmental pollution, human beings began to pay attention to environmental protection and started to carry out pollutant prediction research. A large number of air pollutant predictions have tried to predict pollutants by revealing their evolution patterns, emphasizing the fitting analysis of time series but ignoring the spatial transmission effect of adjacent areas, leading to low prediction accuracy. To solve this problem, we propose a time series prediction network with the self-optimization ability of a spatio-temporal graph neural network (BGGRU) to mine the changing pattern of the time series and the spatial propagation effect. The proposed network includes spatial and temporal modules. The spatial module uses a graph sampling and aggregation network (GraphSAGE) in order to extract the spatial information of the data. The temporal module uses a Bayesian graph gated recurrent unit (BGraphGRU), which applies a graph network to the gated recurrent unit (GRU) so as to fit the data's temporal information. In addition, this study used Bayesian optimization to solve the problem of the model's inaccuracy caused by inappropriate hyperparameters of the model. The high accuracy of the proposed method was verified by the actual PM2.5 data of Beijing, China, which provided an effective method for predicting the PM2.5 concentration. [ABSTRACT FROM AUTHOR]

In order to predict more accurately the structural vibration and noise of elevated tracks induced by moving trains, a new prediction method based on the scaled model test is proposed in this paper. A 32-m simply supported box girder bridge used in the Beijing–Shanghai high-speed railway is selected as the prototype for designing and constructing a scaled model test with 10:1 geometric similarity ratio. Both experimental tests and finite element analyses were carried out to verify the similarity relationship between the model and prototype. The test result shows that the scaled model can predict the structural vibration and noise of the prototype, as long as the similarity constants between the prototype and scaled model are correctively determined. Furthermore, a standard finite element analysis model for the scaled model is built. Based on the sensitivity analysis, the model parameters for finite element analysis are updated by minimizing the errors between the measured and calculated modes. The computational results show that the updated model based on the local parameters partitioning works best, and the precision of the modal frequency calculated is noticeably improved after updating, with the average relative error reduced from 5.46% to 3.09%, and the difference of the peak values reduced from 0. 3 5 8 × 1 0 3 m/s2 to 0. 1 8 9 × 1 0 3 m/s2. The calculated dynamic response of the finite element model after updating is basically in line with experimental results, indicating that the updated model can better reflect the dynamic properties of the scaled box girder model. The updated finite element model is useful both for verification with the model test result and for reliable prediction of the dynamic characteristics of the prototype. [ABSTRACT FROM AUTHOR]

Copyright of Transactions of the Chinese Society of Agricultural Engineering is the property of Chinese Society of Agricultural Engineering 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.)

Short-term traffic prediction (STTP) is one of the most critical capabilities in Intelligent Transportation Systems (ITS), which can be used to support driving decisions, alleviate traffic congestion and improve transportation efficiency. However, STTP of large-scale road networks remains challenging due to the difficulties of effectively modeling the diverse traffic patterns by high-dimensional time series. Therefore, this paper proposes a framework that involves a deep clustering method for STTP in large-scale road networks. The deep clustering method is employed to supervise the representation learning in a visualized way from the large unlabeled dataset. More specifically, to fully exploit the traffic periodicity, the raw series is first divided into a number of sub-series for triplet generation. The convolutional neural networks (CNNs) with triplet loss are utilized to extract the features of shape by transforming the series into visual images. The shape-based representations are then used to cluster road segments into groups. Thereafter, a model sharing strategy is further proposed to build recurrent NNs-based predictions through group-based models (GBMs). GBM is built for a type of traffic patterns, instead of one road segment exclusively or all road segments uniformly. Our framework can not only significantly reduce the number of prediction models, but also improve their generalization by virtue of being trained on more diverse examples. Furthermore, the proposed framework over a selected road network in Beijing is evaluated. Experiment results show that the deep clustering method can effectively cluster the road segments and GBM can achieve comparable prediction accuracy against the IBM with less number of prediction models. [ABSTRACT FROM AUTHOR]

Copyright of Advances in Atmospheric Sciences is the property of Springer Nature 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.)

More accurate multivariate load forecasting is conducive to integrated energy system planning optimization and economic operation. In this paper, based on the consideration of exogenous factors such as weather, endogenous factors are added into the prediction, and a short-term prediction model for integrated energy multivariate load based on endo-exogenous uncertainty is established using fine-tuned transfer learning. The LSTM pre-training model is first initially established using genetic algorithm and exogenous factors such as weather. Then the exogenous uncertainty of the pre-training model and the knowledge of endogenous uncertainty in the target model are combined using fine-tuned transfer learning to continuously optimize the basic parameters of the prediction model to obtain the final multivariate load prediction model. The performance of the four models is comprehensively evaluated after the historical load validation of the integrated energy system in Beijing, China. Compared with the traditional LSTM multivariate load forecasting model, the MAPE of the proposed model in this paper is reduced by 21.03 %, 13.00 %, and 24.39 % for electricity, heat, and cooling load forecasting, respectively. • The coupling mechanism between multiple energy sources of the integrated energy system is analyzed. • An endogenous-exogenous uncertainty method is proposed to extract the dynamic coupling relationship between multiple loads. • An endogenous-exogenous uncertainty-based GA-LSTM multivariate load prediction model is developed. • Optimizing model parameters using fine-tuned migration learning to deepen the impact of endo-exogenous uncertainty. [ABSTRACT FROM AUTHOR]

• Accurate risk path forecasting in rail transit systems is a significant and challenging task. • A probabilistic deep learning framework that can process multisource data for risk path forecasting. • The model can effectively handle safety issues such as cascade failures. Failure-related urban rail events can disrupt transit system operations and traffic flow and lead to serious safety problems worldwide. A domino effect can occur if potential cascading events of major failures are not effectively mitigated and controlled. Therefore, accurate risk path forecasting in rail transit systems is a significant and challenging task. Because of the limitations of traditional models in terms of computational power and feature extraction capabilities, this paper proposes a probabilistic deep learning framework that can process multisource data for risk path forecasting in urban rail transit. This paper first proposes a method for constructing a large-scale risk path ground truth dataset when fault events occur. Then, the framework uses a graph-based feature mapping method to model social media, passenger flow, and station failure information. Finally, we proposed a spatiotemporal feature extractor and a dynamic difference weighting loss function to extract features and optimize parameters. We apply real-world data from 2018 to 2019 from the Beijing urban rail transit system for experimental analysis. The analyzed results demonstrate that the proposed model exceeds the baseline models by at least 2.9% in terms of F 1 value, fusing multi-source data exceeds using single-source data by at least 14% in terms of F 1 value and the proposed attention mechanism and dynamic loss function weights can effectively improve the forecasting performance of the model. Furthermore, the results of the different steps ahead demonstrate that the above results are robust. The application of the model can effectively handle safety issues such as cascade failures. [ABSTRACT FROM AUTHOR]

The rapid adoption of electric vehicles (EVs) has led to dramatic increase in charging demands that poses great challenges for efficient charging infrastructure rollout and operation. It is crucial to accurately assess charging demand in urban areas to optimize the siting and sizing of charging infrastructure. This paper proposes a novel urban charging load forecasting model for private passenger EVs based on massive operating data of EVs in Beijing. First, the characteristics of travel patterns for private passenger EVs, urban road network, functional area distribution and charging infrastructure distribution within the entire Beijing area are identified. Then a charging load forecasting model that can simultaneously simulate trip chains for EVs is constructed by considering the occupancy states of public charging piles and the interactions among different EVs. Finally, the effectiveness of the proposed charging load forecasting model is verified based on comprehensive test data. Our findings imply that the number of EVs at recharge and the charging power can be reliably predicted with the accuracy of over 84.73 % and 81.92 %, respectively. It provides the foundation for optimal charging infrastructure planning and charging scheduling. [ABSTRACT FROM AUTHOR]

Short-term prediction of origin–destination (OD) flow is a primary but complex assignment to urban rail companies, which is the basis of intelligent and real-time urban rail transit (URT) operation and management. The short-term prediction of URT OD flow has three special characteristics: data lag, data dimensionality, and data malconformation, distinguishing it from other short-term prediction tasks. It is essential to propose a novel prediction algorithm that considers the special characteristics of the URT OD flow. For this purpose, based on deep learning methods and multi-source big data, a modified spatial–temporal long short-term memory (ST-LSTM) model is established. The proposed model comprises four components: (1) a temporal feature extraction module is devised to extract time information within network-wide historical OD data; (2) a spatial correlation learning module is introduced to address the data malconformation and data dimensionality problems, which provides an interpretable spatial correlation quantization method; (3) an input control-gated mechanism is originally proposed to solve the data lag problem, which combines the processed available OD flow and real-time inflow/outflow; (4) a fusion module combines historical spatial–temporal features with real-time information to achieve accurate OD flow prediction. We also further discuss the interpretability of the model in detail. The ST-LSTM model is evaluated by sufficient experiments on two large-scale actual subway datasets from Nanjing and Beijing, and the experimental results demonstrate that it can better learn the spatial–temporal correlations and exceed the rest benchmarking methods. [ABSTRACT FROM AUTHOR]

Due to the lack of data quality in real production environment, the traditional line loss calculation method cannot be applied, thus through the investigation of various information systems' operation in power supply enterprises, a short-term low-voltage distribution network line loss prediction algorithm based on Kmeans-LightGBM is proposed. Operating data quality evaluation system of low-voltage distribution network was set up based on Hadoop platform, the feature dimensions were expanded by feature engineering, then those with no multicollinearity and high correlation with the line loss were selected, data normalization was again performed, Kmeans clustering algorithm was used to cluster the area and then, LightGBM algorithm was used to predict the classes within the area of line loss. Finally, the line loss of the numerical inverse normalization was found and validated with Beijing Power Grid of a low-voltage distribution network. By comparison, the model's prediction accuracy is found to be higher than BPNN, FOA-SVR and traditional LightGBM. [ABSTRACT FROM AUTHOR]

Accurate PM 2.5 forecasting provides a possibility for establishing an early warning system to notify the public and take precautionary measures to prevent negative effects on ambient air quality and public health. Considering strong seasonal variation in meteorological conditions, in this paper, a seasonal stacked autoencoder model combining seasonal analysis and deep feature learning is proposed for forecasting the hourly PM 2.5 concentration, named DL-SSAE model. The original data are firstly decomposed into four seasonal subseries according to the Chinese calendar, and then the Kendall correlation coefficient method is employed to search inherent relationships between PM 2.5 concentrations and meteorological parameters within 1-h ahead for each seasonal time series. The inherent relationships of each seasonal subseries are finally extracted, learned, and modeled by different deep neural networks (stacked autoencoders for regression), and the hourly PM 2.5 forecasts are yielded. The addressed model is tested by the dataset collected from three environmental monitoring stations in Beijing, China. The results demonstrate that the proposed model outperforms all other considered models with/without seasonality consideration in this paper. [ABSTRACT FROM AUTHOR]