MAFNet: Multimodal Asymmetric Fusion Network for Radar Echo Extrapolation
Remote Sensing · 26.09.2024 · 16 (19) · 3597
DOI: 10.3390/rs16193597 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 26.09.2024. Verfasst von Yanle Pei und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Hunan Province Natural Science Foundation.
Abstract (Originalsprache)
Radar echo extrapolation (REE) is a crucial method for convective nowcasting, and current deep learning (DL)-based methods for REE have shown significant potential in severe weather forecasting tasks. Existing DL-based REE methods use extensive historical radar data to learn the evolution patterns of echoes, they tend to suffer from low accuracy. This is because data of radar modality face difficulty adequately representing the state of weather systems. Inspired by multimodal learning and traditional numerical weather prediction (NWP) methods, we propose a Multimodal Asymmetric Fusion Network (MAFNet) for REE, which uses data from radar modality to model echo evolution, and data from satellite and ground observation modalities to model the background field of weather systems, collectively guiding echo extrapolation. In the MAFNet, we first extract overall convective features through a global shared encoder (GSE), followed by two branches of local modality encoder (LME) and local correlation encoders (LCEs) that extract convective features from radar, satellite, and ground observation modalities. We employ an multimodal asymmetric fusion module (MAFM) to fuse multimodal features at different scales and feature levels, enhancing radar echo extrapolation performance. Additionally, to address the temporal resolution differences in multimodal data, we design a time alignment module based on dynamic time warping (DTW), which aligns multimodal feature sequences temporally. Experimental results demonstrate that compared to state-of-the-art (SOTA) models, the MAFNet achieves average improvements of 1.86% in CSI and 3.18% in HSS on the MeteoNet dataset, and average improvements of 4.84% in CSI and 2.38% in HSS on the RAIN-F dataset.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Hunan Province Natural Science Foundation
Zitieren
APA
Pei, Y., Li, Q., Wu, Y., Peng, X., Guo, S., Ye, C., & Wang, T. (2024). MAFNet: Multimodal Asymmetric Fusion Network for Radar Echo Extrapolation. Remote Sensing, 16(19), 3597. https://doi.org/10.3390/rs16193597
Vancouver
Pei Y, Li Q, Wu Y, Peng X, Guo S, Ye C, et al. MAFNet: Multimodal Asymmetric Fusion Network for Radar Echo Extrapolation. Remote Sensing. 2024;16(19):3597. doi:10.3390/rs16193597
BibTeX
@article{Pei2024,
author = {Pei, Yanle and Li, Qian and Wu, Yayi and Peng, Xuan and Guo, Shiqing and Ye, Chengzhi and Wang, Tianying},
title = {MAFNet: Multimodal Asymmetric Fusion Network for Radar Echo Extrapolation},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {19},
pages = {3597},
doi = {10.3390/rs16193597}
}
EUVIMED