DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction
Accurate station-level numerical weather predictions are critical for disaster prevention and mitigation, with error correction playing an essential role. However, existing correction models struggle to effectively handle the high-dimensional features and complex dependencies inherent in meteorologi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/206 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587597576142848 |
|---|---|
| author | Kaixin Chen Jiaxin Chen Mengqiu Xu Ming Wu Chuang Zhang |
| author_facet | Kaixin Chen Jiaxin Chen Mengqiu Xu Ming Wu Chuang Zhang |
| author_sort | Kaixin Chen |
| collection | DOAJ |
| description | Accurate station-level numerical weather predictions are critical for disaster prevention and mitigation, with error correction playing an essential role. However, existing correction models struggle to effectively handle the high-dimensional features and complex dependencies inherent in meteorological data. To address these challenges, this paper proposes the dual-branch residual-guided multi-view attention fusion network (DRAF-Net), a novel deep learning-based correction model. DRAF-Net introduces two key innovations: (1) a dual-branch residual structure that enhances the spatial sensitivity of deep high-dimensional features and improves output stability by connecting raw data and shallow features to deep features, respectively; and (2) a multi-view attention fusion mechanism that models spatiotemporal influences, temporal dynamics, and spatial associations, significantly improving the representation of complex dependencies. The effectiveness of DRAF-Net was validated on two real-world datasets comprising observations and predictions from Chinese meteorological stations. It achieved an average RMSE reduction of 83.44% and an average MAE reduction of 84.21% across all eight variables, significantly outperforming other methods. Moreover, extensive studies confirmed the critical contributions of each key component, while visualization results highlighted the model’s ability to eliminate anomalous values and improve prediction consistency. The code will be made publicly available to support future research and development. |
| format | Article |
| id | doaj-art-c90c59ff91964cd6a435945f9b2b8f5b |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-c90c59ff91964cd6a435945f9b2b8f5b2025-01-24T13:47:43ZengMDPI AGRemote Sensing2072-42922025-01-0117220610.3390/rs17020206DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction CorrectionKaixin Chen0Jiaxin Chen1Mengqiu Xu2Ming Wu3Chuang Zhang4Artificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaArtificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaArtificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaArtificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaArtificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaAccurate station-level numerical weather predictions are critical for disaster prevention and mitigation, with error correction playing an essential role. However, existing correction models struggle to effectively handle the high-dimensional features and complex dependencies inherent in meteorological data. To address these challenges, this paper proposes the dual-branch residual-guided multi-view attention fusion network (DRAF-Net), a novel deep learning-based correction model. DRAF-Net introduces two key innovations: (1) a dual-branch residual structure that enhances the spatial sensitivity of deep high-dimensional features and improves output stability by connecting raw data and shallow features to deep features, respectively; and (2) a multi-view attention fusion mechanism that models spatiotemporal influences, temporal dynamics, and spatial associations, significantly improving the representation of complex dependencies. The effectiveness of DRAF-Net was validated on two real-world datasets comprising observations and predictions from Chinese meteorological stations. It achieved an average RMSE reduction of 83.44% and an average MAE reduction of 84.21% across all eight variables, significantly outperforming other methods. Moreover, extensive studies confirmed the critical contributions of each key component, while visualization results highlighted the model’s ability to eliminate anomalous values and improve prediction consistency. The code will be made publicly available to support future research and development.https://www.mdpi.com/2072-4292/17/2/206numerical weather prediction correctiondeep learningresidual connectionbias adjustmentspatiotemporal modelingattention fusion |
| spellingShingle | Kaixin Chen Jiaxin Chen Mengqiu Xu Ming Wu Chuang Zhang DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction Remote Sensing numerical weather prediction correction deep learning residual connection bias adjustment spatiotemporal modeling attention fusion |
| title | DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction |
| title_full | DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction |
| title_fullStr | DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction |
| title_full_unstemmed | DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction |
| title_short | DRAF-Net: Dual-Branch Residual-Guided Multi-View Attention Fusion Network for Station-Level Numerical Weather Prediction Correction |
| title_sort | draf net dual branch residual guided multi view attention fusion network for station level numerical weather prediction correction |
| topic | numerical weather prediction correction deep learning residual connection bias adjustment spatiotemporal modeling attention fusion |
| url | https://www.mdpi.com/2072-4292/17/2/206 |
| work_keys_str_mv | AT kaixinchen drafnetdualbranchresidualguidedmultiviewattentionfusionnetworkforstationlevelnumericalweatherpredictioncorrection AT jiaxinchen drafnetdualbranchresidualguidedmultiviewattentionfusionnetworkforstationlevelnumericalweatherpredictioncorrection AT mengqiuxu drafnetdualbranchresidualguidedmultiviewattentionfusionnetworkforstationlevelnumericalweatherpredictioncorrection AT mingwu drafnetdualbranchresidualguidedmultiviewattentionfusionnetworkforstationlevelnumericalweatherpredictioncorrection AT chuangzhang drafnetdualbranchresidualguidedmultiviewattentionfusionnetworkforstationlevelnumericalweatherpredictioncorrection |