Search

This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors. The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Convolutional Long Short Term Memory Neural Network (ConvLSTM) to predict short-term taxi travel demand. The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components, capturing sequence characteristics at different time scales and frequencies. Based on the sample entropy value of components, secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency. On this basis, considering the correlation between the spatiotemporal trends of short-term taxi traffic, a ConvLSTM neural network model with Long Short Term Memory (LSTM) time series processing ability and Convolutional Neural Networks (CNN) spatial feature processing ability is constructed to predict the travel demand for urban taxis. The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing. The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM, Autoregressive Integrated Moving Average model (ARIMA), CNN, and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error (SMAPE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R2 metrics. Notably, the SMAPE metric exhibits a remarkable decline of 21.03% with the utilization of our proposed model. These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting. [ABSTRACT FROM AUTHOR]

Tourism demand forecasting is proven essential to optimize management, increase revenues, and control risks. Spatial effects have been widely considered in forecasting models and achieved good results. However, existing studies paid little attention to the dynamicity and hierarchy of spatial correlations among tourist attractions within tourism destination complex networks. This study addresses this paucity by proposing a novel deep learning model, namely, multi-hierarchy dynamic spatiotemporal network (MHDSTN). Innovatively, dynamic and hierarchical spatiotemporal features are extracted for forecasting improvement by integrating transformer, gated graph convolution, and long short-term memory. The effectiveness, robustness, and interpretability of the model are demonstrated through an empirical case in Beijing, China. Results indicate that incorporating dynamic and hierarchical spatial effects remarkably improves forecasting accuracy. [ABSTRACT FROM AUTHOR]

Summary: State of charge and state of energy are essential performance indicators of the battery management system and the key to reflecting the remaining capacity of batteries. Aiming at the problems of low precision, long time, and strongly nonlinear system estimation of state of charge and state of energy of lithium‐ion batteries based on traditional algorithm under complex working conditions, this paper proposes a hybrid method consisting of the long short‐term memory neural network and square root extended Kalman smoothing. The long short‐term memory neural network can enhance the memory ability of the previous time data. The sliding window technology is introduced into the network to improve the correlation between the last time and the subsequent time estimation. Based on the traditional Kalman filtering algorithm, the square root and reverse smoothing algorithms are introduced to solve the risk of the negative covariance matrix and the problems of slow convergence and significant estimation deviation caused by a strongly nonlinear system. According to experiments, under the hybrid pulse power characterization working condition at 25°C, the maximum absolute errors of state of charge and state of energy are 1.779% and 1.487%, and the mean absolute errors are 0.352% and 0.894%, respectively. Under the Beijing bus dynamic stress test working condition at 25°C, the maximum absolute errors of state of charge and state of energy are 2.703% and 2.369%, and the mean absolute errors are 0.462% and 0.621%, respectively. The experimental results show that this algorithm can obtain reliable state of charge and state of energy under different complex working conditions with high accuracy, convergence, and robustness. [ABSTRACT FROM AUTHOR]

Air pollution is a major global problem, closely related to economic and social development and ecological environment construction. Air pollution data for most regions of China have a close correlation with time and seasons and are affected by multidimensional factors such as meteorology and air quality. In contrast with classical peaks-over-threshold modeling approaches, we use a deep learning technique and three new dynamic conditional generalized Pareto distribution (DCP) models with weather and air quality factors for fitting the time-dependence of the air pollutant concentration and make statistical inferences about their application in air quality analysis. Specifically, in the proposed three DCP models, a dynamic autoregressive exponential function mechanism is applied for the time-varying scale parameter and tail index of the conditional generalized Pareto distribution, and a sufficiently high threshold is chosen using two threshold selection procedures. The probabilistic properties of the DCP model and the statistical properties of the maximum likelihood estimation (MLE) are investigated, simulating and showing the stability and sensitivity of the MLE estimations. The three proposed models are applied to fit the PM 2.5 time series in Beijing from 2015 to 2021. Real data are used to illustrate the advantages of the DCP, especially compared to the estimation volatility of GARCH and AIC or BIC criteria. The DCP model involving both the mixed weather and air quality factors performs better than the other two models with weather factors or air quality factors alone. Finally, a prediction model based on long short-term memory (LSTM) is used to predict PM 2.5 concentration, achieving ideal results. [ABSTRACT FROM AUTHOR]

Making accurate predictions of subway passenger flow is conducive to optimizing operation plans. This study aims to analyze the regularity of subway passenger flow and combine the modeling skills of deep learning with transportation knowledge to predict the short-term subway passenger flow in the scenarios of workdays and holidays. The processed data were collected from two months of Automated Fare Collection (AFC) data from Xizhimen station of Beijing metro. The data were first cleaned by the established cleansing rules to delete malformed and abnormal logic data. The cleaned data were used to analyze the spatial characteristics in passenger flow. Second, a short-term subway passenger flow prediction model was built on the basis of long short-term memory (LSTM). Determining that the error will be relatively high in peak hours, we proposed gradual optimizations from data input by dividing one whole day into different time periods, and then used particle swarm optimization (PSO) to search for the optimal hyperparameters setting. Finally, inbound passenger flow of Beijing Xizhimen subway station in 2018 was selected for numerical experiments. Predictions of the LSTM-based model had higher accuracy than the traditional machine learning support vector regression (SVR) model, with mean absolute percentage error (MAPE) of 21.97% and 4.80% in the scenarios of workdays and holidays, respectively, which are both lower than those of the SVR model. The optimized PSO-LSTM model has been verified for its effectiveness and accurateness by the AFC data. [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]

[Display omitted] • Propose variational mode decomposition optimized by capuchin search algorithm. • Propose a prediction model of optimized LSTM by pelican optimization algorithm. • Consider error sequence, and propose the error correction module CVMD-POA-LSTM. • Propose a new hybrid prediction model for PM2.5 concentration, named CEEMDAN-ApEn-CVMD-POA-LSTM-EC. • In this paper, all data and code links are shared on GitHub. With the acceleration of urbanization leading to a general decrease in air quality, accurate PM2.5 concentration prediction is of the utmost practical meaning for the control and prevention of air pollution in the region. Therefore, a new hybrid prediction model for PM2.5 concentration based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), approximate entropy (ApEn), variational mode decomposition optimized by capuchin search algorithm (CVMD), long short-term memory optimized by pelican optimization algorithm (POA-LSTM) and error correction (EC), named CEEMDAN-ApEn-CVMD-POA-LSTM-EC, is proposed. First, CEEMDAN is used to acquire a limited amount of intrinsic mode functions (IMFs). Second, calculate ApEn value for each IMF component, and divide each IMF component into high-complexity and low-complexity components by the size of ApEn values. Third, variational mode decomposition optimized by capuchin search algorithm (CVMD), named CVMD, is proposed. CVMD is used as a secondary decomposition method to further decompose high-complexity components adaptively into a finite number of IMFs. Fourth, long short-term memory optimized by pelican optimization algorithm, named POA-LSTM, is proposed. POA-LSTM predicts all IMF components, and the results of their predictions are combined to generate the original prediction results. Final, error sequence is decomposed and predicted again by the EC module CVMD-POA-LSTM to obtain prediction results of error sequence, and final prediction results are acquired by combining original prediction results and prediction results of error sequence. The datasets in Beijing, Shanghai, and Xi'an were selected for simulation experiments to demonstrate the superiority of the proposed model. Taking Beijing as an example, RMSE, MAE, MAPE and R2 values are 1.9947, 1.5577, 0.1157 and 0.9947, which are superior to other comparison models and have the best performance. [ABSTRACT FROM AUTHOR]

The increasing free access of the Internet provides us with favorable circumstances to investigate search engine index reflecting more and more personal behavior information. Part of valuable travel search information can assist us to achieve more robust and reliable prediction of metro passenger flow. Inspired by this, the paper develops a new multi-source time series fusion and direct interval prediction approach to grasp the dynamic law of metro passenger flow effectively. Multi-source index regarding metro travel from three major search engines (Baidu, Sogou and 360) in China are screened out and fused into the powerful predictors. By integrating an optimized multivariate mode decomposition strategy and long short-term memory model, lower and upper bounds of prediction interval are estimated directly by a multi-objective framework that combines the advantages of both the deep learning models long short-term memory and the ensemble learning approach. Especially, two sets of real experiment data of Beijing and Shanghai metro systems are employed to test our approach. Findings show that fusion of multi-source index information promotes the predictability of metro passenger flow, contributing to improving operation management and service quality. [Display omitted] • Fusing multi-source search data from three search engines based on query popularity. • Developing a new multivariate preprocessing technique MOHHOMVMD. • Proposing a direct multi-objective interval prediction approach LSTM-based LUBE. • Verifying the superiority of our approach over six benchmark models in two cases. [ABSTRACT FROM AUTHOR]

• A long-term trajectory prediction method using generative adversarial networks. • A useful imaged 4D trajectory method for converting 4D trajectory series data to RGB images. • 4D trajectory prediction based on machine learning model. Four-dimensional trajectory prediction is one of the key technologies of air traffic management (ATM) and plays a considerably significant role in enhancing air traffic safety, accelerating air traffic flow and improving ATM efficiency. In this work, we propose a novel long-term 4D trajectory prediction model based on generative adversarial network (GAN). First, trajectory data is preprocessed. Then, three deep generation models for trajectory prediction are designed based on one-dimensional convolution neural network (Conv1D-GAN), two-dimensional convolution neural network (Conv2D-GAN), and long short-term memory neural network (LSTM-GAN). Finally, the models are trained and tested using historical 4D trajectory data from Beijing to Chengdu, China. The results demonstrate that the Conv1D-GAN is the most suitable generative adversarial network for long-term aircraft trajectory prediction. [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]

• Synchronous multi-parameter prediction for battery systems is investigated. • All-climate and all-state application in electric vehicles can be obtained. • A developed pre-dropout technique is introduced to prevent LSTM from overfitting. • Different models can be intelligently applied in driving/charging states. • The predicted horizons are adjustable to provide adequate emergency time. Voltage, temperature, and state of charge (SOC) are the main characterizing parameters for various battery faults that can cause these parameters' abnormal fluctuations. Accurate prediction for these parameters is critical for the safe, durable, and reliable operation of battery systems in electric vehicles. This paper investigates a new deep-learning-enabled method to perform accurate synchronous multi-parameter prediction for battery systems using a long short-term memory (LSTM) recurrent neural network. A year-long dataset of an electric taxi was retrieved at the Service and Management Center for electric vehicles (SMC-EV) in Beijing to train the LSTM model and verify the model's validity and stability. By taking into account the impacts of weather and driver's behaviors on a battery system's performance to improve the prediction accuracy, a Weather-Vehicle-Driver analysis method is proposed, and a developed pre-dropout technique is introduced to prevent LSTM from overfitting. Besides, the many-to-many(m-n) model structure using a developed dual-model-cooperation prediction strategy is applied for offline training the LSTM model after all hyperparameters pre-optimized. Additionally, the stability and robustness of this method have been verified through 10-fold cross-validation and comparative analysis of multiple sets of hyperparameters. The results show that the proposed model has powerful and precise online prediction ability for the three target parameters. This paper also provides feasibility for synchronous multiple fault prognosis based on accurate parameter prediction of the battery system. This is the first of its kind to apply LSTM to the synchronous multi-parameter prediction of the battery system. [ABSTRACT FROM AUTHOR]

• Accurate real-time multi-forward-step battery voltage prediction is investigated. • Impacts of weather and driver's behaviors are both taken into account. • Trained cell-voltage model can be shared by all cells without mutual interference. • Prediction accuracy can be ensured neglecting vehicular driving/charging status. • Ample time is available to safeguard drivers with adjustable predicted horizons. State prediction and fault prognosis are generating considerable interest regarding battery system due to the healthy development momentum of electric vehicles. Voltage is one of the main characterisation parameters for various battery faults, so accurate voltage abnormity prognosis is critical to the safe and durable operation of the battery system. A novel deep-learning-enabled method to perform accurate multi-forward-step voltage prediction for battery systems is investigated using long short-term memory(LSTM) recurrent neural network. A high volume of real-world operational data of an electric taxi is acquired from the Service and Management Center for electric vehicles(SMC-EV) in Beijing. To improve the prediction accuracy, a Weather-Vehicle-Driver analysis is implemented to consider the impacts of weather and driver's behaviour on a battery system's performance, and the many-to-one(4-1) model structure using an improved pre-dropout technology and a developed dual-model-cooperation prediction strategy is applied for offline training the LSTM models after all hyperparameters pre-optimized. The results showcase that the proposed method has a powerful prediction ability for battery voltage, and the accuracy and robustness of this method are verified through the comparisons among different hyperparameters and seasons using 10-fold cross-validation. Furthermore, combined with alarm or warning thresholds, the prognosis feasibility, stability, and reliability of the proposed models for various voltage abnormities are also verified through actual operational data, thereby this method can assess the battery safety via predicting voltage to determine the advent of battery faults and mitigate runaway risk. This is the first of its kind to apply the LSTM to voltage prediction and fault prognosis of the battery system. [ABSTRACT FROM AUTHOR]