Extreme Weather Nowcasting via Local Precipitation Pattern Prediction

TL;DR

This paper introduces exPreCast, a fast and accurate deterministic model for radar-based precipitation nowcasting, and presents a balanced radar dataset to improve generalization across normal and extreme weather events.

Contribution

The paper proposes a novel deterministic framework with local attention and texture-preserving upsampling, and creates a balanced radar dataset for better real-world applicability.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Demonstrates reliable nowcasting for both normal and extreme rainfall.

Outperforms diffusion-based models in computational efficiency.

Abstract

Accurate forecasting of extreme weather events such as heavy rainfall or storms is critical for risk management and disaster mitigation. Although high-resolution radar observations have spurred extensive research on nowcasting models, precipitation nowcasting remains particularly challenging due to pronounced spatial locality, intricate fine-scale rainfall structures, and variability in forecasting horizons. While recent diffusion-based generative ensembles show promising results, they are computationally expensive and unsuitable for real-time applications. In contrast, deterministic models are computationally efficient but remain biased toward normal rainfall. Furthermore, the benchmark datasets commonly used in prior studies are themselves skewed--either dominated by ordinary rainfall events or restricted to extreme rainfall episodes--thereby hindering general applicability in real-world settings. In this paper, we propose exPreCast, an efficient deterministic framework for generating finely detailed radar forecasts, and introduce a newly constructed balanced radar dataset from the Korea Meteorological Administration (KMA), which encompasses both ordinary precipitation and extreme events. Our model integrates local spatiotemporal attention, a texture-preserving cubic dual upsampling decoder, and a temporal extractor to flexibly adjust forecasting horizons. Experiments on established benchmarks (SEVIR and MeteoNet) as well as on the balanced KMA dataset demonstrate that our approach achieves state-of-the-art performance, delivering accurate and reliable nowcasts across both normal and extreme rainfall regimes.