Rainy: Unlocking Satellite Calibration for Deep Learning in Precipitation

Precipitation plays a critical role in the Earth's hydrological cycle, directly affecting ecosystems, agriculture, and water resource management. Accurate precipitation estimation and prediction are crucial for understanding climate dynamics, disaster preparedness, and environmental monitoring. In recent years, the rise of large language models has drawn significant attention to the application of artificial intelligence (AI) in quantitative remote sensing (QRS). Although traditional methods have been widely used for precipitation estimation, they face limitations in handling large-scale data and complex environmental conditions. Furthermore, the lack of standardized multi-source satellite datasets, and in most cases, the exclusive reliance on station data, significantly hinders the effective application of advanced AI models. To address these challenges, we propose the Rainy dataset, a multi-source spatio-temporal dataset that integrates pure satellite data with station data, and propose Taper Loss, designed to fill the gap in tasks where only in-situ data is available without area-wide support. The Rainy dataset supports five key tasks: (1) satellite calibration, (2) precipitation event prediction, (3) precipitation level prediction, (4) spatiotemporal prediction, and (5) precipitation downscaling. For each task, we selected benchmark models and evaluation metrics to provide valuable references for researchers. Using precipitation parameters as an example, the Rainy dataset and Taper Loss demonstrate the seamless collaboration between QRS and computer vision, offering data support for ``AI for Science'' in the field of QRS and providing valuable insights for interdisciplinary collaboration and integration.