Computationally-efficient deep learning models for nowcasting of precipitation: A solution for the Weather4cast 2025 challenge

TL;DR

This paper introduces a transfer-learning ConvGRU framework for short-term rainfall nowcasting using satellite data, achieving high accuracy and competitive results in the Weather4Cast 2025 challenge.

Contribution

It presents a novel two-stage training approach combining ConvGRU with nonlinear transformation for rainfall prediction from satellite imagery.

Findings

Achieved 2nd place in the Weather4Cast 2025 rainfall task.

Model effectively predicts rainfall up to four hours ahead.

Out-of-the-box application yields competitive event detection results.

Abstract

This study presents a transfer-learning framework based on Convolutional Gated Recurrent Units (ConvGRU) for short-term rainfall prediction in the Weather4Cast 2025 competition. A single SEVIRI infrared channel (10.8 {\mu}m wavelength) is used as input, which consists of four observations over a one-hour period. A two-stage training strategy is applied to generate rainfall estimates up to four hours ahead. In the first stage, ConvGRU is trained to forecast the brightness temperatures from SEVIRI, enabling the model to capture relevant spatiotemporal patterns. In the second stage, an empirically derived nonlinear transformation maps the predicted fields to OPERA-compatible rainfall rates. For the event-prediction task, the transformed rainfall forecasts are processed using 3D event detection followed by spatiotemporal feature extraction to identify and characterize precipitation events. Our submission achieved 2nd place in the cumulative rainfall task. Further, the same model was used out-of-the-box for the event prediction task, and resulted in similar scores as the baseline model to the competition.