RainBalance: Alleviating Dual Imbalance in GNSS-based Precipitation Nowcasting via Continuous Probability Modeling

2026-01-05

arXiv.org

AI Summary

This study addresses the dual imbalance challenges in GNSS-based precipitation nowcasting—namely, the dominance of non-precipitation events and the scarcity of extreme rainfall samples—which severely degrade model performance. To tackle this, we propose RainBalance, a novel framework that, for the first time, introduces continuous probabilistic modeling to this task. RainBalance constructs a precipitation probability distribution via clustering and learns it within the latent space of a variational autoencoder (VAE), effectively mitigating data imbalance. Designed as a plug-and-play module, RainBalance is compatible with diverse existing model architectures. Extensive experiments demonstrate that integrating RainBalance consistently and significantly improves the performance of multiple state-of-the-art models on precipitation forecasting, with its efficacy validated through statistical significance tests and ablation studies.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Global navigation satellite systems (GNSS) station-based Precipitation Nowcasting aims to predict rainfall within the next 0-6 hours by leveraging a GNSS station's historical observations of precipitation, GNSS-PWV, and related meteorological variables, which is crucial for disaster mitigation and real-time decision-making. In recent years, time-series forecasting approaches have been extensively applied to GNSS station-based precipitation nowcasting. However, the highly imbalanced temporal distribution of precipitation, marked not only by the dominance of non-rainfall events but also by the scarcity of extreme precipitation samples, significantly limits model performance in practical applications. To address the dual imbalance problem in precipitation nowcasting, we propose a continuous probability modeling-based framework, RainBalance. This plug-and-play module performs clustering for each input sample to obtain its cluster probability distribution, which is further mapped into a continuous latent space via a variational autoencoder (VAE). By learning in this continuous probabilistic space, the task is reformulated from fitting single and imbalance-prone precipitation labels to modeling continuous probabilistic label distributions, thereby alleviating the imbalance issue. We integrate this module into multiple state-of-the-art models and observe consistent performance gains. Comprehensive statistical analysis and ablation studies further validate the effectiveness of our approach.

Problem

• precipitation nowcasting
• class imbalance
• extreme precipitation
• GNSS
• time-series forecasting

Innovation

• continuous probability modeling
• dual imbalance
• variational autoencoder
• precipitation nowcasting
• GNSS-PWV