RainNet: A Large-Scale Imagery Dataset for Spatial Precipitation Downscaling

Contemporary deep learning frameworks have been applied to solve meteorological problems (\emph{e.g.}, front detection, synthetic radar generation, precipitation nowcasting, \emph{e.t.c.}) and have achieved highly promising results. Spatial precipitation downscaling is one of the most important meteorological problems. However, the lack of a well-organized and annotated large-scale dataset hinders the training and verification of more effective and advancing deep-learning models for precipitation downscaling. To alleviate these obstacles, we present the first large-scale spatial precipitation downscaling dataset named \emph{RainNet}, which contains more than $62,400$ pairs of high-quality low/high-resolution precipitation maps for over $17$ years, ready to help the evolution of deep models in precipitation downscaling. Specifically, the precipitation maps carefully collected in RainNet cover various meteorological phenomena (\emph{e.g.}, hurricane, squall, \emph{e.t.c}.), which is of great help to improve the model generalization ability. In addition, the map pairs in RainNet are organized in the form of image sequences ($720$ maps per month or 1 map/hour), showing complex physical properties, \emph{e.g.}, temporal misalignment, temporal sparse, and fluid properties. Two machine-learning-oriented metrics are specifically introduced to evaluate or verify the comprehensive performance of the trained model, (\emph{e.g.}, prediction maps reconstruction accuracy). To illustrate the applications of RainNet, 14 state-of-the-art models, including deep models and traditional approaches, are evaluated. To fully explore potential downscaling solutions, we propose an implicit physical estimation framework to learn the above characteristics. Extensive experiments demonstrate that the value of RainNet in training and evaluating downscaling models.