M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention

TL;DR

M3R is a novel deep learning architecture that combines radar imagery and weather station data using multimodal attention to improve rainfall nowcasting accuracy.

Contribution

It introduces a meteorology-informed multimodal attention mechanism that effectively leverages heterogeneous weather data sources for precipitation prediction.

Findings

M3R outperforms existing methods in accuracy and efficiency.

The model demonstrates improved precipitation detection capabilities.

Experimental results across multiple regions validate the approach.

Abstract

Accurate and timely rainfall nowcasting is crucial for disaster mitigation and water resource management. Despite recent advances in deep learning, precipitation prediction remains challenging due to limitations in effectively leveraging diverse multimedia data sources. We introduce M3R, a Meteorology-informed MultiModal attention-based architecture for direct Rainfall prediction that synergistically combines visual NEXRAD radar imagery with numerical Personal Weather Station (PWS) measurements, using a comprehensive pipeline for temporal alignment of heterogeneous meteorological data. With specialized multimodal attention mechanisms, M3R novelly leverages weather station time series as queries to selectively attend to spatial radar features, enabling focused extraction of precipitation signatures. Experimental results for three spatial areas of 100 km * 100 km centered at NEXRAD radar stations demonstrate that M3R outperforms existing approaches, achieving substantial improvements in accuracy, efficiency, and precipitation detection capabilities. Our work establishes new benchmarks for multimedia-based precipitation nowcasting and provides practical tools for operational weather prediction systems. The source code is available at https://github.com/Sanjeev97/M3Rain