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

TL;DR

RainNet is a comprehensive large-scale dataset of high and low-resolution precipitation maps spanning over 17 years, designed to advance deep learning models for spatial precipitation downscaling by providing diverse data and evaluation metrics.

Contribution

The paper introduces RainNet, the first large-scale, well-annotated dataset for precipitation downscaling, including diverse meteorological phenomena and a benchmark framework for model evaluation.

Findings

RainNet enables effective training of deep learning models for precipitation downscaling.

Evaluation of 14 models demonstrates RainNet's utility in model assessment.

The dataset improves generalization across various meteorological conditions.

Abstract

AI-for-science approaches have been applied to solve scientific problems (e.g., nuclear fusion, ecology, genomics, meteorology) and have achieved highly promising results. Spatial precipitation downscaling is one of the most important meteorological problem and urgently requires the participation of AI. 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 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 learning models in precipitation downscaling. Specifically, the precipitation maps carefully collected in RainNet cover various meteorological phenomena (e.g., hurricane, squall), 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, e.g., temporal misalignment, temporal sparse, and fluid properties. Furthermore, two deep-learning-oriented metrics are specifically introduced to evaluate or verify the comprehensive performance of the trained model (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 benchmark framework to learn the above characteristics. Extensive experiments demonstrate the value of RainNet in training and evaluating downscaling models. Our dataset is available at https://neuralchen.github.io/RainNet/.