Self-Supervised Pre-Training for Precipitation Post-Processor
Abstract
Obtaining a sufficient forecast lead time for local precipitation is essential in preventing hazardous weather events. Global warming-induced climate change increases the challenge of accurately predicting severe precipitation events, such as heavy rainfall. In this paper, we propose a deep learning-based precipitation post-processor for numerical weather prediction (NWP) models. The precipitation post-processor consists of (i) employing self-supervised pre-training, where the parameters of the encoder are pre-trained on the reconstruction of the masked variables of the atmospheric physics domain; and (ii) conducting transfer learning on precipitation segmentation tasks (the target domain) from the pre-trained encoder. In addition, we introduced a heuristic labeling approach to effectively train class-imbalanced datasets. Our experiments on precipitation correction for regional NWP show that the proposed method outperforms other approaches.
Cite
@article{arxiv.2310.20187,
title = {Self-Supervised Pre-Training for Precipitation Post-Processor},
author = {Sojung An and Junha Lee and Jiyeon Jang and Inchae Na and Wooyeon Park and Sujeong You},
journal= {arXiv preprint arXiv:2310.20187},
year = {2024}
}
Comments
7 pages, 3 figures, 1 table, accepted to NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning at [this http URL](https://www.climatechange.ai/papers/neurips2023/18)