# M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention

Source: [M3R: Localized Rainfall Nowcasting with Meteorology-Informed MultiModal Attention](<https://www.sota2.com/research/paper/69e5b3037d0172140ec7df24>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-21T05:00:04.784Z

Authors: Sanjeev Panta, Rhett M Morvant, Xu Yuan, Li Chen, Nian-Feng Tzeng

Published: 2026-04-15T21:02:51.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Binary Rain Classification on Lake Charles (LA) (test)](<https://www.sota2.com/research/sota/binary-rain-classification-on-lake-charles-la-test.md>): Binary Rain Classification; Lake Charles (LA) (test); CSI (Threshold 0.1): 41.

- [Binary Rain Classification on Jackson MS (test)](<https://www.sota2.com/research/sota/binary-rain-classification-on-jackson-ms-test.md>): Binary Rain Classification; Jackson MS (test); CSI (Threshold 0.1): 41.4.

- [Time Series Forecasting on Lake Charles (LA) (test)](<https://www.sota2.com/research/sota/time-series-forecasting-on-lake-charles-la-test.md>): Time Series Forecasting; Lake Charles (LA) (test); RMSE: 2.87.

- [Time Series Forecasting on Montgomery (AL) (test)](<https://www.sota2.com/research/sota/time-series-forecasting-on-montgomery-al-test.md>): Time Series Forecasting; Montgomery (AL) (test); RMSE: 3.03.

- [Time Series Forecasting on Jackson MS (test)](<https://www.sota2.com/research/sota/time-series-forecasting-on-jackson-ms-test.md>): Time Series Forecasting; Jackson MS (test); RMSE: 3.28.

- [Binary Rain Classification on Montgomery (AL) (test)](<https://www.sota2.com/research/sota/binary-rain-classification-on-montgomery-al-test.md>): Binary Rain Classification; Montgomery (AL) (test); CSI 0.1: 30.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.15377>)

[PDF](<https://arxiv.org/pdf/2604.15377.pdf>)