SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory

Cloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spati...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanzhao Ren, Jinyuan Ye, Xiaochuan Wang, Fengjin Xiao, Ruijun Liu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4213
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850147191330439168
author Yanzhao Ren
Jinyuan Ye
Xiaochuan Wang
Fengjin Xiao
Ruijun Liu
author_facet Yanzhao Ren
Jinyuan Ye
Xiaochuan Wang
Fengjin Xiao
Ruijun Liu
author_sort Yanzhao Ren
collection DOAJ
description Cloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spatio-temporal sequence prediction models. However, most models now rely on stacking convolutional layers to obtain local spatial features. In response to the complex changes in cloud position and shape in cloud images, the prediction module of the model needs to be able to extract both global and local spatial features from the cloud images. In addition, for irregular cloud motion, more attention should be paid to the spatio-temporal sequence features between input cloud image frames in the temporal sequence prediction module, considering the extraction of temporal features with long temporal dependencies, so that the spatio-temporal sequence prediction network can learn cloud motion trends more accurately. To address these issues, we have introduced an innovative model called SAM-Net. The self-attention module of this model aims to extract an inner image frame’s spatial features of global and local dependencies. In addition, a memory mechanism has been added to the self-attention module to extract interframe features with long temporal and spatial dependencies. Our method shows better performance than the PredRNN-v2 model on publicly available datasets such as MovingMNIST and KTH. We achieved the best performance in both the 4-time-step and 10-time-step typhoon cloud image predictions. On a cloud dataset consisting of 10 time steps, we observed a decrease in MSE of 180.58, a decrease in LPIPS of 0.064, an increase in SSIM of 0.351, and a significant improvement in PSNR of 5.56 compared to PredRNN-v2.
format Article
id doaj-art-ae4e12f8ba104f08a892fae6504e6f57
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-ae4e12f8ba104f08a892fae6504e6f572025-08-20T02:27:38ZengMDPI AGRemote Sensing2072-42922024-11-011622421310.3390/rs16224213SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention MemoryYanzhao Ren0Jinyuan Ye1Xiaochuan Wang2Fengjin Xiao3Ruijun Liu4School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 100048, ChinaChina Meteorological Administration, National Climate Center, Beijing 100081, ChinaSchool of Software, Beihang University, Beijing 100191, ChinaCloud image prediction is a spatio-temporal sequence prediction task, similar to video prediction. Spatio-temporal sequence prediction involves learning from historical data and using the learned features to generate future images. In this process, the changes in time and space are crucial for spatio-temporal sequence prediction models. However, most models now rely on stacking convolutional layers to obtain local spatial features. In response to the complex changes in cloud position and shape in cloud images, the prediction module of the model needs to be able to extract both global and local spatial features from the cloud images. In addition, for irregular cloud motion, more attention should be paid to the spatio-temporal sequence features between input cloud image frames in the temporal sequence prediction module, considering the extraction of temporal features with long temporal dependencies, so that the spatio-temporal sequence prediction network can learn cloud motion trends more accurately. To address these issues, we have introduced an innovative model called SAM-Net. The self-attention module of this model aims to extract an inner image frame’s spatial features of global and local dependencies. In addition, a memory mechanism has been added to the self-attention module to extract interframe features with long temporal and spatial dependencies. Our method shows better performance than the PredRNN-v2 model on publicly available datasets such as MovingMNIST and KTH. We achieved the best performance in both the 4-time-step and 10-time-step typhoon cloud image predictions. On a cloud dataset consisting of 10 time steps, we observed a decrease in MSE of 180.58, a decrease in LPIPS of 0.064, an increase in SSIM of 0.351, and a significant improvement in PSNR of 5.56 compared to PredRNN-v2.https://www.mdpi.com/2072-4292/16/22/4213spatio-temporal sequence predictive learningremote sensingrecurrent neural networksself-attention memory
spellingShingle Yanzhao Ren
Jinyuan Ye
Xiaochuan Wang
Fengjin Xiao
Ruijun Liu
SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
Remote Sensing
spatio-temporal sequence predictive learning
remote sensing
recurrent neural networks
self-attention memory
title SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
title_full SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
title_fullStr SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
title_full_unstemmed SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
title_short SAM-Net: Spatio-Temporal Sequence Typhoon Cloud Image Prediction Net with Self-Attention Memory
title_sort sam net spatio temporal sequence typhoon cloud image prediction net with self attention memory
topic spatio-temporal sequence predictive learning
remote sensing
recurrent neural networks
self-attention memory
url https://www.mdpi.com/2072-4292/16/22/4213
work_keys_str_mv AT yanzhaoren samnetspatiotemporalsequencetyphooncloudimagepredictionnetwithselfattentionmemory
AT jinyuanye samnetspatiotemporalsequencetyphooncloudimagepredictionnetwithselfattentionmemory
AT xiaochuanwang samnetspatiotemporalsequencetyphooncloudimagepredictionnetwithselfattentionmemory
AT fengjinxiao samnetspatiotemporalsequencetyphooncloudimagepredictionnetwithselfattentionmemory
AT ruijunliu samnetspatiotemporalsequencetyphooncloudimagepredictionnetwithselfattentionmemory