This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Spatiotemporal Feature Fusion Transformer for Precipitation Nowcasting via Feature Crossing
by
Taisong Xiong
Taisong Xiong 1,2,
Weiping Wang
Weiping Wang 3,*,
Jianxin He
Jianxin He 1,2,
Rui Su
Rui Su 3,
Hao Wang
Hao Wang 1,4,5
and
Jinrong Hu
Jinrong Hu 6
1
College of Meteorological Observation, Chengdu University of Information Technology, Chengdu 610225, China
2
The Key Laboratory of Atmospheric Sounding, CMA, Chengdu 610225, China
3
Jiangxi Atmospheric Observation Technology Center, Nanchang 330000, China
4
China Meteorological Administration Radar Meteorology Key Laboratory, Nanjing 210000, China
5
Wenjiang National Climatology Observatory, Sichuan Provincial Meteorological Service, Chengdu 611130, China
6
School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2024, 16(14), 2685; https://doi.org/10.3390/rs16142685 (registering DOI)
Submission received: 5 June 2024
/
Revised: 14 July 2024
/
Accepted: 19 July 2024
/
Published: 22 July 2024
Abstract
Precipitation nowcasting plays an important role in mitigating the damage caused by severe weather. The objective of precipitation nowcasting is to forecast the weather conditions 0–2 h ahead. Traditional models based on numerical weather prediction and radar echo extrapolation obtain relatively better results. In recent years, models based on deep learning have also been applied to precipitation nowcasting and have shown improvement. However, the forecast accuracy is decreased with longer forecast times and higher intensities. To mitigate the shortcomings of existing models for precipitation nowcasting, we propose a novel model that fuses spatiotemporal features for precipitation nowcasting. The proposed model uses an encoder–forecaster framework that is similar to U-Net. First, in the encoder, we propose a spatial and temporal multi-head squared attention module based on MaxPool and AveragePool to capture every independent sequence feature, as well as a global spatial and temporal feedforward network, to learn the global and long-distance relationships between whole spatiotemporal sequences. Second, we propose a cross-feature fusion strategy to enhance the interactions between features. This strategy is applied to the components of the forecaster. Based on the cross-feature fusion strategy, we constructed a novel multi-head squared cross-feature fusion attention module and cross-feature fusion feedforward network in the forecaster. Comprehensive experimental results demonstrated that the proposed model more effectively forecasted high-intensity levels than other models. These results prove the effectiveness of the proposed model in terms of predicting convective weather. This indicates that our proposed model provides a feasible solution for precipitation nowcasting. Extensive experiments also proved the effectiveness of the components of the proposed model.
Share and Cite
MDPI and ACS Style
Xiong, T.; Wang, W.; He, J.; Su, R.; Wang, H.; Hu, J.
Spatiotemporal Feature Fusion Transformer for Precipitation Nowcasting via Feature Crossing. Remote Sens. 2024, 16, 2685.
https://doi.org/10.3390/rs16142685
AMA Style
Xiong T, Wang W, He J, Su R, Wang H, Hu J.
Spatiotemporal Feature Fusion Transformer for Precipitation Nowcasting via Feature Crossing. Remote Sensing. 2024; 16(14):2685.
https://doi.org/10.3390/rs16142685
Chicago/Turabian Style
Xiong, Taisong, Weiping Wang, Jianxin He, Rui Su, Hao Wang, and Jinrong Hu.
2024. "Spatiotemporal Feature Fusion Transformer for Precipitation Nowcasting via Feature Crossing" Remote Sensing 16, no. 14: 2685.
https://doi.org/10.3390/rs16142685
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.