Self-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand

Ge, Hongxia; Li, Siteng; Cheng, Rongjun; Chen, Zhenlei

doi:10.3390/su14127371

Cited by 9 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ConvLSTM is an improved model of LSTM, which overcomes the problem of LSTM not being able to represent spatial features by replacing the fully connected layer with a convolutional layer. ConvLSTM is widely used in spatiotemporal sequence prediction (Ge et al., 2022; Huang et al., 2022; Z. Lin et al., 2020). Figure 2 shows the internal structure of a ConvLSTM unit.…”

Section: Methodsmentioning

confidence: 99%

ED‐AttConvLSTM: An Ionospheric TEC Map Prediction Model Using Adaptive Weighted Spatiotemporal Features

Li,

Liu,

et al. 2024

Space Weather

View full text Add to dashboard Cite

In this paper, we propose a novel Total Electron Content (TEC) map prediction model, named ED‐AttConvLSTM, using a Convolutional Long Short‐Term Memory (ConvLSTM) network and attention mechanism based on encoder‐decoder structure. The inclusion of the attention mechanism enhances the efficient utilization of spatiotemporal features extracted by the ConvLSTM, emphasizing the significance of crucial spatiotemporal features in the prediction process and, as a result, leading to an enhancement in predictive performance. We conducted experiments in East Asia (10°N–45°N, 90°E−130°E). The ED‐AttConvLSTM was trained and evaluated using the International GNSS Service TEC maps over a period of six years from 2013 to 2015 (high solar activity years) and 2017 to 2019 (low solar activity years). We compared our ED‐AttConvLSTM with IRI‐2016, COPG, LSTM, GRU, ED‐ConvLSTM and ED‐ConvGRU. The results indicate that our model surpasses the comparison models in forecasting both high and low solar activity years, across most months and UT moments in a day. Moreover, our model exhibits notably superior prediction performance during the most severe phases of a magnetic storm when compared to the comparison models. Subsequently, we then also discuss how the prediction performance of our model is affected by latitude. Finally, we discuss the diminishing performance of our model in multi‐day predictions, demonstrating that its reliability for forecasts ranging from one to 4 days in advance. Beyond the fifth day, there is a pronounced decline in the model's performance.

show abstract

Section: Methodsmentioning

confidence: 99%

ED‐AttConvLSTM: An Ionospheric TEC Map Prediction Model Using Adaptive Weighted Spatiotemporal Features

Li,

Liu,

et al. 2024

Space Weather

View full text Add to dashboard Cite

show abstract

“…ConvLSTM is an advanced variant of the LSTM model that addresses the limitations of LSTM in extracting spatial features by replacing the fully connected layer in LSTM units with a convolutional layer. It has been proved to have excellent data modeling capability of spatiotemporal series [32][33][34]. In this paper, we combine the encoder-decoder structure with the ConvLSTM model, and propose an ED-ConvLSTM TEC prediction model.…”

Section: Methodsmentioning

confidence: 99%

Spatiotemporal Prediction of Ionospheric Total Electron Content Based on ED-ConvLSTM

Liu

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Total electron content (TEC) is a vital parameter for describing the state of the ionosphere, and precise prediction of TEC is of great significance for improving the accuracy of the Global Navigation Satellite System (GNSS). At present, most deep learning prediction models just consider TEC temporal variation, while ignoring the impact of spatial location. In this paper, we propose a TEC prediction model, ED-ConvLSTM, which combines convolutional neural networks with recurrent neural networks to simultaneously consider spatiotemporal features. Our ED-ConvLSTM model is built based on the encoder-decoder architecture, which includes two modules: encoder module and decoder module. Each module is composed of ConvLSTM cells. The encoder module is used to extract the spatiotemporal features from TEC maps, while the decoder module converts spatiotemporal features into predicted TEC maps. We compared the predictive performance of our model with two traditional time series models: LSTM, GRU, a spatiotemporal mode1 ConvGRU, and the TEC daily forecast product C1PG provided by CODE on a total of 135 grid points in East Asia (10°–45°N, 90°–130°E). The experimental results show that the prediction error indicators MAE, RMSE, MAPE, and prediction similarity index SSIM of our model are superior to those of the comparison models in high, normal, and low solar activity years. The paper also analyzed the predictive performance of each model monthly. The experimental results indicate that the predictive performance of each model is influenced by the monthly mean of TEC. The ED-ConvLSTM model proposed in this paper is the least affected and the most stable by the monthly mean of TEC. Additionally, the paper compared the predictive performance of each model during two magnetic storm periods when TEC changes sharply. The results indicate that our ED-ConvLSTM model is least affected during magnetic storms and its predictive performance is superior to those of the comparative models. This paper provides a more stable and high-performance TEC spatiotemporal prediction model.

show abstract

“…ConvLSTM is a variant of LSTM that allows data to be held in both time and space. Both E3D-LSTM and SA-ConvLSTM add attention mechanism [49], E3D-LSTM strengthens the long-distance dependence ability of LSTM, and SA-ConvLSTM solves the long-term spatial dependence problem [30,31,50]. Four networks were trained with varying parameter magnitudes to comprehensively evaluate the impact of model complexity on Chl-a prediction.…”

Section: Deep Learning Models and Implementationmentioning

confidence: 99%

Prediction of Sea Surface Chlorophyll-a Concentrations Based on Deep Learning and Time-Series Remote Sensing Data

Yao,

Wang,

Zhang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Accurate prediction of future chlorophyll-a (Chl-a) concentrations is of great importance for effective management and early warning of marine ecological systems. However, previous studies primarily focused on chlorophyll-a inversion and reconstruction, while methods for predicting Chl-a concentrations remain limited. To address this issue, we adopted four deep learning approaches, including Convolutional LSTM Network (ConvLSTM), Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), Eidetic 3D LSTM (E3D-LSTM), and Self-Attention ConvLSTM (SA-ConvLSTM) models, to predict Chl-a over the Yellow Sea and Bohai Sea (YBS) in China. Furthermore, 14 environmental variables obtained from the remote sensing data of Moderate-resolution Imaging Spectroradiometer (MODIS) and ECMWF Reanalysis v5 (ERA5) were utilized to predict the Chl-a concentrations in the study area. The results showed that all four models performed satisfactorily in predicting Chl-a concentrations in the YBS, with SA-ConvLSTM exhibiting a closer approximation to true values. Furthermore, we analyzed the impact of the Self-Attention Memory Module (SAM) on the prediction results. Compared to the ConvLSTM model, the SA-ConvLSTM model integrated with the SAM module better captured subtle large-scale variations within the study area. The SA-ConvLSTM model exhibited the highest prediction accuracy, and the one-month Pearson correlation coefficient reached 0.887. Our study provides an available approach for anticipating Chl-a concentrations over a large area of sea.

show abstract

Self-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand

Cited by 9 publications

References 35 publications

ED‐AttConvLSTM: An Ionospheric TEC Map Prediction Model Using Adaptive Weighted Spatiotemporal Features

ED‐AttConvLSTM: An Ionospheric TEC Map Prediction Model Using Adaptive Weighted Spatiotemporal Features

Spatiotemporal Prediction of Ionospheric Total Electron Content Based on ED-ConvLSTM

Prediction of Sea Surface Chlorophyll-a Concentrations Based on Deep Learning and Time-Series Remote Sensing Data

Contact Info

Product

Resources

About