Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks

Wind speed forecasting is significant in practical applications such as energy dispatch and meteorological early warning systems. However, spatiotemporal correlations of wind speed are dynamically influenced by weather conditions, seasonal variations, and diurnal fluctuations, resulting in constantl...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianhong Gan, Runqing Kang, Xun Deng, Chentao Mao, Zhibin Li, Peiyang Wei, Chunjiang Wu, Tongli He
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11078154/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850034612264239104
author Jianhong Gan
Runqing Kang
Xun Deng
Chentao Mao
Zhibin Li
Peiyang Wei
Chunjiang Wu
Tongli He
author_facet Jianhong Gan
Runqing Kang
Xun Deng
Chentao Mao
Zhibin Li
Peiyang Wei
Chunjiang Wu
Tongli He
author_sort Jianhong Gan
collection DOAJ
description Wind speed forecasting is significant in practical applications such as energy dispatch and meteorological early warning systems. However, spatiotemporal correlations of wind speed are dynamically influenced by weather conditions, seasonal variations, and diurnal fluctuations, resulting in constantly changing spatiotemporal patterns. Meanwhile, wind speed data inherently include short-term high-frequency fluctuations and long-term low-frequency trends, which traditional methods struggle to adapt to and accurately capture multiscale features. This article proposes a dynamic spatiotemporal graph convolutional network (DSTGFP) model for multistation wind speed prediction to address this challenge. First, the model constructs an adaptive dynamic adjacency matrix by integrating geographical locations among stations, dynamic time warping, and mutual information, facilitating dynamic graph modeling. Next, we introduce a novel spatiotemporal feature extraction framework, which employs residual graph convolutional networks combined with a multihead attention mechanism to extract spatial features. We simultaneously integrate temporal- and frequency-domain convolutions to capture multiscale temporal-frequency features. Finally, the particle swarm optimization algorithm is used for hyperparameter optimization to improve the prediction accuracy. Experimental results demonstrate that the DSTGFP model achieves reductions of 24.66% in the mean absolute error and 25.47% in the root-mean-square error compared to existing deep learning methods, highlighting its superior predictive performance.
format Article
id doaj-art-428bcfa41b5a41eabff140fd60b573e5
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-428bcfa41b5a41eabff140fd60b573e52025-08-20T02:57:45ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118187891880510.1109/JSTARS.2025.358826011078154Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional NetworksJianhong Gan0Runqing Kang1https://orcid.org/0009-0001-0075-801XXun Deng2https://orcid.org/0009-0005-8173-4157Chentao Mao3https://orcid.org/0000-0002-9648-1835Zhibin Li4https://orcid.org/0000-0002-0501-2305Peiyang Wei5https://orcid.org/0009-0008-9632-8006Chunjiang Wu6Tongli He7College of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaCollege of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaCollege of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaHangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, ChinaCollege of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaCollege of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaCollege of Software Engineering, Chengdu University of Information Technology, Chengdu, ChinaCollege of Applied Mathematics, Chengdu University of Information Technology, Chengdu, ChinaWind speed forecasting is significant in practical applications such as energy dispatch and meteorological early warning systems. However, spatiotemporal correlations of wind speed are dynamically influenced by weather conditions, seasonal variations, and diurnal fluctuations, resulting in constantly changing spatiotemporal patterns. Meanwhile, wind speed data inherently include short-term high-frequency fluctuations and long-term low-frequency trends, which traditional methods struggle to adapt to and accurately capture multiscale features. This article proposes a dynamic spatiotemporal graph convolutional network (DSTGFP) model for multistation wind speed prediction to address this challenge. First, the model constructs an adaptive dynamic adjacency matrix by integrating geographical locations among stations, dynamic time warping, and mutual information, facilitating dynamic graph modeling. Next, we introduce a novel spatiotemporal feature extraction framework, which employs residual graph convolutional networks combined with a multihead attention mechanism to extract spatial features. We simultaneously integrate temporal- and frequency-domain convolutions to capture multiscale temporal-frequency features. Finally, the particle swarm optimization algorithm is used for hyperparameter optimization to improve the prediction accuracy. Experimental results demonstrate that the DSTGFP model achieves reductions of 24.66% in the mean absolute error and 25.47% in the root-mean-square error compared to existing deep learning methods, highlighting its superior predictive performance.https://ieeexplore.ieee.org/document/11078154/Adjacency matrixdynamic time warping (DTW)graph convolutionparticle swarm optimization (PSO)wind speed forecasting
spellingShingle Jianhong Gan
Runqing Kang
Xun Deng
Chentao Mao
Zhibin Li
Peiyang Wei
Chunjiang Wu
Tongli He
Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Adjacency matrix
dynamic time warping (DTW)
graph convolution
particle swarm optimization (PSO)
wind speed forecasting
title Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
title_full Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
title_fullStr Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
title_full_unstemmed Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
title_short Multistation Wind Speed Forecasting Based on Dynamic Spatiotemporal Graph Convolutional Networks
title_sort multistation wind speed forecasting based on dynamic spatiotemporal graph convolutional networks
topic Adjacency matrix
dynamic time warping (DTW)
graph convolution
particle swarm optimization (PSO)
wind speed forecasting
url https://ieeexplore.ieee.org/document/11078154/
work_keys_str_mv AT jianhonggan multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT runqingkang multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT xundeng multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT chentaomao multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT zhibinli multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT peiyangwei multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT chunjiangwu multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks
AT tonglihe multistationwindspeedforecastingbasedondynamicspatiotemporalgraphconvolutionalnetworks