Accurate Precipitation Forecast by Efficiently Learning from Massive Atmospheric Variables and Unbalanced Distribution

2026-03-27

AI Summary

This work addresses key challenges in short-term precipitation nowcasting, including the complex spatiotemporal dynamics of rainfall evolution, severe class imbalance due to rare extreme events, and inefficient utilization of multi-source atmospheric observations. To overcome these limitations, we propose a novel deep learning architecture that automatically extracts latent features strongly correlated with precipitation evolution and iteratively refines predictions, enabling effective fusion of massive heterogeneous observational data. Furthermore, we introduce a weighted multi-class cross-entropy (WMCE) loss function to enhance the model’s sensitivity to infrequent yet critical precipitation events and improve the accuracy of intensity forecasting. Experiments on two real-world datasets demonstrate that our method significantly outperforms state-of-the-art baselines in both predictive accuracy and computational efficiency, substantially reducing the cost of high-value nowcasting operations.

Abstract

Short-term (0-24 hours) precipitation forecasting is highly valuable to socioeconomic activities and public safety. However, the highly complex evolution patterns of precipitation events, the extreme imbalance between precipitation and non-precipitation samples, and the inability of existing models to efficiently and effectively utilize large volumes of multi-source atmospheric observation data hinder improvements in precipitation forecasting accuracy and computational efficiency. To address the above challenges, this study developed a novel forecasting model capable of effectively and efficiently utilizing massive atmospheric observations by automatically extracting and iteratively predicting the latent features strongly associated with precipitation evolution. Furthermore, this study introduces a 'WMCE' loss function, designed to accurately discriminate extremely scarce precipitation events while precisely predicting their intensity values. Extensive experiments on two datasets demonstrate that our proposed model substantially and consistently outperforms all prevalent baselines in both accuracy and efficiency. Moreover, the proposed forecasting model substantially lowers the computational cost required to obtain valuable predictions compared to existing approaches, thereby positioning it as a milestone for efficient and practical precipitation forecasting.

Problem

• precipitation forecasting
• imbalanced data
• atmospheric variables
• short-term prediction
• computational efficiency

Innovation

• precipitation forecasting
• massive atmospheric variables
• imbalanced data
• WMCE loss function
• computational efficiency