Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model

This study develops a spatio-temporal forecasting model for predicting wind speeds across the Beijing-Tianjin-Hebei region over a 4-h horizon. The model, built using advanced deep learning techniques, operates with a temporal resolution of 1 hour and a spatial resolution of 9 km. The experiments wer...

Full description

Saved in:
Bibliographic Details
Main Authors: Zixuan Chen, Jinman Zhang, Shuang Zhou, Zengbao Zhao, Yushan Liu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Earth Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/feart.2025.1580945/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736269581516800
author Zixuan Chen
Zixuan Chen
Zixuan Chen
Jinman Zhang
Jinman Zhang
Shuang Zhou
Zengbao Zhao
Zengbao Zhao
Yushan Liu
author_facet Zixuan Chen
Zixuan Chen
Zixuan Chen
Jinman Zhang
Jinman Zhang
Shuang Zhou
Zengbao Zhao
Zengbao Zhao
Yushan Liu
author_sort Zixuan Chen
collection DOAJ
description This study develops a spatio-temporal forecasting model for predicting wind speeds across the Beijing-Tianjin-Hebei region over a 4-h horizon. The model, built using advanced deep learning techniques, operates with a temporal resolution of 1 hour and a spatial resolution of 9 km. The experiments were first trained based on ConvLSTM and UNet, and improved by introducing the Self-Attention (SA) mechanism module to construct two hybrid deep learning models, Conv-SA as well as UNet-SA, respectively. The results show that the spatio-temporal predictions of the UNet model are significantly better than ConvLSTM, and the TS scores show that for the prediction of high wind, the enhancement is more than 50% for the next 4 hours. The addition of the SA module significantly improves the model prediction accuracy, and Conv-SA improves significantly, compared to ConvLSTM by more than 60%. The models were more accurate in predicting wind speeds in the region of the terrestrial than the oceanic subsurface. In addition, the model produces more accurate wind speed predictions for coastal as well as plateau regions. This study provides a new research idea for the proximity prediction of wind speed.
format Article
id doaj-art-c78beb3a88134f24af1811b5ad64b7e2
institution DOAJ
issn 2296-6463
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Earth Science
spelling doaj-art-c78beb3a88134f24af1811b5ad64b7e22025-08-20T03:07:20ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-06-011310.3389/feart.2025.15809451580945Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning modelZixuan Chen0Zixuan Chen1Zixuan Chen2Jinman Zhang3Jinman Zhang4Shuang Zhou5Zengbao Zhao6Zengbao Zhao7Yushan Liu8China Meteorological Administration Xiong’an Atmospheric Boundary Layer Key Laboratory, Xiong’an New Area, ChinaKey Laboratory of Meteorology and Ecological Environment of Hebei Province, Shijiazhuang, ChinaHebei Provincial Meteorology Service Center, Shijiazhuang, ChinaHebei Provincial Meteorology Service Center, Shijiazhuang, ChinaEnergy Meteorology Key Laboratory, China Meteorological Administration, Beijing, ChinaHebei Provincial Meteorology Service Center, Shijiazhuang, ChinaHebei Provincial Meteorology Service Center, Shijiazhuang, ChinaEnergy Meteorology Key Laboratory, China Meteorological Administration, Beijing, ChinaHebei Provincial Meteorology Service Center, Shijiazhuang, ChinaThis study develops a spatio-temporal forecasting model for predicting wind speeds across the Beijing-Tianjin-Hebei region over a 4-h horizon. The model, built using advanced deep learning techniques, operates with a temporal resolution of 1 hour and a spatial resolution of 9 km. The experiments were first trained based on ConvLSTM and UNet, and improved by introducing the Self-Attention (SA) mechanism module to construct two hybrid deep learning models, Conv-SA as well as UNet-SA, respectively. The results show that the spatio-temporal predictions of the UNet model are significantly better than ConvLSTM, and the TS scores show that for the prediction of high wind, the enhancement is more than 50% for the next 4 hours. The addition of the SA module significantly improves the model prediction accuracy, and Conv-SA improves significantly, compared to ConvLSTM by more than 60%. The models were more accurate in predicting wind speeds in the region of the terrestrial than the oceanic subsurface. In addition, the model produces more accurate wind speed predictions for coastal as well as plateau regions. This study provides a new research idea for the proximity prediction of wind speed.https://www.frontiersin.org/articles/10.3389/feart.2025.1580945/fulldeep learningwind speedpredictionultra-short-termspatio-temporal
spellingShingle Zixuan Chen
Zixuan Chen
Zixuan Chen
Jinman Zhang
Jinman Zhang
Shuang Zhou
Zengbao Zhao
Zengbao Zhao
Yushan Liu
Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
Frontiers in Earth Science
deep learning
wind speed
prediction
ultra-short-term
spatio-temporal
title Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
title_full Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
title_fullStr Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
title_full_unstemmed Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
title_short Ultra-short-term prediction of spatio-temporal wind speed based on a hybrid deep learning model
title_sort ultra short term prediction of spatio temporal wind speed based on a hybrid deep learning model
topic deep learning
wind speed
prediction
ultra-short-term
spatio-temporal
url https://www.frontiersin.org/articles/10.3389/feart.2025.1580945/full
work_keys_str_mv AT zixuanchen ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT zixuanchen ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT zixuanchen ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT jinmanzhang ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT jinmanzhang ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT shuangzhou ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT zengbaozhao ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT zengbaozhao ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel
AT yushanliu ultrashorttermpredictionofspatiotemporalwindspeedbasedonahybriddeeplearningmodel