How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915594460200960 |
|---|---|
| author | Zhang, Yifang Xiong, Shengwu Wang, Henan Yin, Wenjie Peng, Jiawang Zhang, Yuqiang Zhou, Chen Chen, Hua Zhao, Qile Duan, Pengfei |
| author_facet | Zhang, Yifang Xiong, Shengwu Wang, Henan Yin, Wenjie Peng, Jiawang Zhang, Yuqiang Zhou, Chen Chen, Hua Zhao, Qile Duan, Pengfei |
| contents | Precipitation Nowcasting, which aims to predict precipitation within the next 0 to 6 hours, is critical for disaster mitigation and real-time response planning. However, most time series forecasting benchmarks in meteorology are evaluated on variables with strong periodicity, such as temperature and humidity, which fail to reflect model capabilities in more complex and practically meteorology scenarios like precipitation nowcasting. To address this gap, we propose RainfallBench, a benchmark designed for precipitation nowcasting, a highly challenging and practically relevant task characterized by zero inflation, temporal decay, and non-stationarity, focusing on predicting precipitation within the next 0 to 6 hours. The dataset is derived from five years of meteorological observations, recorded at hourly intervals across six essential variables, and collected from more than 140 Global Navigation Satellite System (GNSS) stations globally. In particular, it incorporates precipitable water vapor (PWV), a crucial indicator of rainfall that is absent in other datasets. We further design specialized evaluation protocols to assess model performance on key meteorological challenges, including multi-scale prediction, multi-resolution forecasting, and extreme rainfall events, benchmarking 17 state-of-the-art models across six major architectures on RainfallBench. Additionally, to address the zero-inflation and temporal decay issues overlooked by existing models, we introduce Bi-Focus Precipitation Forecaster (BFPF), a plug-and-play module that incorporates domain-specific priors to enhance rainfall time series forecasting. Statistical analysis and ablation studies validate the comprehensiveness of our dataset as well as the superiority of our methodology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25263 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting Zhang, Yifang Xiong, Shengwu Wang, Henan Yin, Wenjie Peng, Jiawang Zhang, Yuqiang Zhou, Chen Chen, Hua Zhao, Qile Duan, Pengfei Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Precipitation Nowcasting, which aims to predict precipitation within the next 0 to 6 hours, is critical for disaster mitigation and real-time response planning. However, most time series forecasting benchmarks in meteorology are evaluated on variables with strong periodicity, such as temperature and humidity, which fail to reflect model capabilities in more complex and practically meteorology scenarios like precipitation nowcasting. To address this gap, we propose RainfallBench, a benchmark designed for precipitation nowcasting, a highly challenging and practically relevant task characterized by zero inflation, temporal decay, and non-stationarity, focusing on predicting precipitation within the next 0 to 6 hours. The dataset is derived from five years of meteorological observations, recorded at hourly intervals across six essential variables, and collected from more than 140 Global Navigation Satellite System (GNSS) stations globally. In particular, it incorporates precipitable water vapor (PWV), a crucial indicator of rainfall that is absent in other datasets. We further design specialized evaluation protocols to assess model performance on key meteorological challenges, including multi-scale prediction, multi-resolution forecasting, and extreme rainfall events, benchmarking 17 state-of-the-art models across six major architectures on RainfallBench. Additionally, to address the zero-inflation and temporal decay issues overlooked by existing models, we introduce Bi-Focus Precipitation Forecaster (BFPF), a plug-and-play module that incorporates domain-specific priors to enhance rainfall time series forecasting. Statistical analysis and ablation studies validate the comprehensiveness of our dataset as well as the superiority of our methodology. |
| title | How Effective Are Time-Series Models for Precipitation Nowcasting? A Comprehensive Benchmark for GNSS-based Precipitation Nowcasting |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2509.25263 |