EnPredRNN: An Enhanced PredRNN Network for Extending Spatio-Temporal Prediction Period
Open Access
- 5 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 107631-107644
Abstract
We propose the Enhanced Predictive Recurrent Neural Network (EnPredRNN) based on PredRNN to extend the period of spatio-temporal prediction. To better capture global spatial dependencies, we integrate the Self-Attention (SA) module into PredRNN’s basic unit, forming the Enhanced Long Short-Term Memory (EnLSTM). Aiming at the problem that the standard temporal memory state in PredRNN contains insufficient information about inter-frame motion, we propose the Enhanced Temporal Memory (ETM) by aggregating past multi-step temporal memory states. Aiming at the gradient vanishing problem in Recurrent Neural Networks (RNN), the Alleviating Gradient Vanishing (AGV) structure is used to construct the high-speed path that facilitates gradient propagation. Experimental results show that EnPredRNN effectively extends spatio-temporal prediction from ten to thirty time-steps.Keywords
Funding Information
- Natural Science Foundation of Qinghai Province (2023-QLGKLYCZX-017, 2023-ZJ-906M, 2023-QLGKLYCZX-026, 2023-QLGKLYCZX-027)
- Qinghai University 2023 Young Researchers’ Fund (2023-QGY-7)
This publication has 30 references indexed in Scilit:
- Pedestrian detection using RetinaNet with multi-branch structure and double pooling attention mechanismMultimedia Tools and Applications, 2023
- Analysis of the future trends of typical mountain glacier movements along the Sichuan-Tibet Railway based on ConvGRU networkInternational Journal of Digital Earth, 2023
- Video Extrapolation in Space and Time2022
- STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction2022
- Smartphone power management based on ConvLSTM modelNeural Computing and Applications, 2021
- HPRNN: A Hierarchical Sequence Prediction Model for Long-Term Weather Radar Echo Extrapolation2020
- Predicting air quality with deep learning LSTM: Towards comprehensive modelsEcological Informatics, 2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Machine translation using deep learning: An overview2017