SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction

Spatial-temporal prediction, to predict future spatial data for a period with past data, is widely used in precipitation prediction, target motion prediction, and traffic flow forecasting. The data for these tasks typically exhibits multi-scale variability which imposes a great deal of difficulty fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Ge Peng, Yujing Zhong
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10938129/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704446310744064
author Ge Peng
Yujing Zhong
author_facet Ge Peng
Yujing Zhong
author_sort Ge Peng
collection DOAJ
description Spatial-temporal prediction, to predict future spatial data for a period with past data, is widely used in precipitation prediction, target motion prediction, and traffic flow forecasting. The data for these tasks typically exhibits multi-scale variability which imposes a great deal of difficulty for long-term prediction. A deep learning model, named sliding window recurrent vision mamba (SWRVM), is proposed for exploiting spatial and long-term temporal information accurately and dexterously to perform effective long-term spatial-temporal prediction in this paper. The proposed SWRVM model combines improved embedding module and sliding window recurrent mechanisms into vision mamba, while the improved embedding module is to retain more spatial and temporal feature, the sliding window recurrent mechanism is the key structure for long-term prediction, and the vision mamba model gives effective results by global receptive field and computational efficiency. We perform extensive experiments on four public datasets and one private dataset in three situations of 10 in 10 out, 20 out, and 40 out. The quantitative and qualitative visualization results demonstrate the SWRVM model outperforms the state-of-the-arts (SOTA) models in multi-scale variations long-term spatial-temporal prediction tasks.
format Article
id doaj-art-833a43f18abb4fa78c984cc0b4c1932f
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-833a43f18abb4fa78c984cc0b4c1932f2025-08-20T03:16:46ZengIEEEIEEE Access2169-35362025-01-0113552315524310.1109/ACCESS.2025.355425410938129SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal PredictionGe Peng0https://orcid.org/0000-0002-3437-7936Yujing Zhong1https://orcid.org/0009-0001-2431-3736School of Big Data, Baoshan University, Baoshan, Yunnan, ChinaSchool of Big Data, Baoshan University, Baoshan, Yunnan, ChinaSpatial-temporal prediction, to predict future spatial data for a period with past data, is widely used in precipitation prediction, target motion prediction, and traffic flow forecasting. The data for these tasks typically exhibits multi-scale variability which imposes a great deal of difficulty for long-term prediction. A deep learning model, named sliding window recurrent vision mamba (SWRVM), is proposed for exploiting spatial and long-term temporal information accurately and dexterously to perform effective long-term spatial-temporal prediction in this paper. The proposed SWRVM model combines improved embedding module and sliding window recurrent mechanisms into vision mamba, while the improved embedding module is to retain more spatial and temporal feature, the sliding window recurrent mechanism is the key structure for long-term prediction, and the vision mamba model gives effective results by global receptive field and computational efficiency. We perform extensive experiments on four public datasets and one private dataset in three situations of 10 in 10 out, 20 out, and 40 out. The quantitative and qualitative visualization results demonstrate the SWRVM model outperforms the state-of-the-arts (SOTA) models in multi-scale variations long-term spatial-temporal prediction tasks.https://ieeexplore.ieee.org/document/10938129/Long-term spatial-temporal predictionvideo predictionlong-term memoryprecipitation radar map predictiondeep learning
spellingShingle Ge Peng
Yujing Zhong
SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
IEEE Access
Long-term spatial-temporal prediction
video prediction
long-term memory
precipitation radar map prediction
deep learning
title SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
title_full SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
title_fullStr SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
title_full_unstemmed SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
title_short SWRVM: Sliding Window Recurrent Vision Mamba Model for Long-Term Spatial-Temporal Prediction
title_sort swrvm sliding window recurrent vision mamba model for long term spatial temporal prediction
topic Long-term spatial-temporal prediction
video prediction
long-term memory
precipitation radar map prediction
deep learning
url https://ieeexplore.ieee.org/document/10938129/
work_keys_str_mv AT gepeng swrvmslidingwindowrecurrentvisionmambamodelforlongtermspatialtemporalprediction
AT yujingzhong swrvmslidingwindowrecurrentvisionmambamodelforlongtermspatialtemporalprediction