Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting
Rapidly accumulating, large-scale and long-term meteorological data provide unprecedented opportunities for data-driven meteorological models and fine-grained numerical weather prediction. Many existing approaches based on deep learning models, e.g., recurrent neutral networks and graph neural netwo...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10848064/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583265685340160 |
|---|---|
| author | Ang Guo Yanghe Liu Shiyu Shao Xiaowei Shi Zhenni Feng |
| author_facet | Ang Guo Yanghe Liu Shiyu Shao Xiaowei Shi Zhenni Feng |
| author_sort | Ang Guo |
| collection | DOAJ |
| description | Rapidly accumulating, large-scale and long-term meteorological data provide unprecedented opportunities for data-driven meteorological models and fine-grained numerical weather prediction. Many existing approaches based on deep learning models, e.g., recurrent neutral networks and graph neural networks, have been proposed for weather forecasting. However, the subtle spatial correlations hidden in the vast amount of historical meteorological data have not been fully explored, such as dynamic spatial correlation. In this paper, we propose STGAMAM, which integrates Spatial-Temporal fusion Graph neural networks with a novel Adjacency Matrix and self-Attention Mechanisms to capture both long-term temporal periodicity and short-term spatial-temporal dependencies based on mixed adjacency via graph attention networks and then makes fine-grained prediction on concatenated features which combines diverse correlations. Our approach is validated by extensive experiment on two real-world datasets, which demonstrates the superiority of the proposed method over existing methods. |
| format | Article |
| id | doaj-art-ea94a2a4c8a14ef1a9872383bda5cb91 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ea94a2a4c8a14ef1a9872383bda5cb912025-01-29T00:01:01ZengIEEEIEEE Access2169-35362025-01-0113158121582410.1109/ACCESS.2025.353247310848064Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather ForecastingAng Guo0https://orcid.org/0009-0002-2228-5425Yanghe Liu1Shiyu Shao2Xiaowei Shi3Zhenni Feng4https://orcid.org/0000-0002-8163-347XSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaHubei Key Laboratory of Intelligent Yangtze and Hydroelectric Science, China, Yangtze Power Company Ltd., Yichang, Hubei, ChinaSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaHubei Key Laboratory of Intelligent Yangtze and Hydroelectric Science, China, Yangtze Power Company Ltd., Yichang, Hubei, ChinaSchool of Computer Science and Technology, Donghua University, Shanghai, ChinaRapidly accumulating, large-scale and long-term meteorological data provide unprecedented opportunities for data-driven meteorological models and fine-grained numerical weather prediction. Many existing approaches based on deep learning models, e.g., recurrent neutral networks and graph neural networks, have been proposed for weather forecasting. However, the subtle spatial correlations hidden in the vast amount of historical meteorological data have not been fully explored, such as dynamic spatial correlation. In this paper, we propose STGAMAM, which integrates Spatial-Temporal fusion Graph neural networks with a novel Adjacency Matrix and self-Attention Mechanisms to capture both long-term temporal periodicity and short-term spatial-temporal dependencies based on mixed adjacency via graph attention networks and then makes fine-grained prediction on concatenated features which combines diverse correlations. Our approach is validated by extensive experiment on two real-world datasets, which demonstrates the superiority of the proposed method over existing methods.https://ieeexplore.ieee.org/document/10848064/Spatial-temporal time series predictionspatial-temporal fusion graphweather forecasting |
| spellingShingle | Ang Guo Yanghe Liu Shiyu Shao Xiaowei Shi Zhenni Feng Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting IEEE Access Spatial-temporal time series prediction spatial-temporal fusion graph weather forecasting |
| title | Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting |
| title_full | Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting |
| title_fullStr | Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting |
| title_full_unstemmed | Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting |
| title_short | Spatial-Temporal Fusion Graph Neural Networks With Mixed Adjacency for Weather Forecasting |
| title_sort | spatial temporal fusion graph neural networks with mixed adjacency for weather forecasting |
| topic | Spatial-temporal time series prediction spatial-temporal fusion graph weather forecasting |
| url | https://ieeexplore.ieee.org/document/10848064/ |
| work_keys_str_mv | AT angguo spatialtemporalfusiongraphneuralnetworkswithmixedadjacencyforweatherforecasting AT yangheliu spatialtemporalfusiongraphneuralnetworkswithmixedadjacencyforweatherforecasting AT shiyushao spatialtemporalfusiongraphneuralnetworkswithmixedadjacencyforweatherforecasting AT xiaoweishi spatialtemporalfusiongraphneuralnetworkswithmixedadjacencyforweatherforecasting AT zhennifeng spatialtemporalfusiongraphneuralnetworkswithmixedadjacencyforweatherforecasting |