연구성과
더 나은 예측을 향한 연구의 결실
수치예보의 발전을 위해 쌓아 온 KIAPS의 연구성과를 소개합니다.
논문부터 기술과 소프트웨어까지, 더 정확한 예측을 위한 지식과
경험을 나눕니다.
[논문] Self-Supervised Pre-Training for Precipitation Post-Processor
- 작성자
- 마스터관리자
- 작성일
- 조회수
- 75
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.
Citation:
An, S., Lee, J., Jang, J., Na, I., Park, W., & You, S. (2023). Self-supervised Pre-training for Precipitation Post-processor. arXiv preprint arXiv:2310.20187.
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.
Citation:
An, S., Lee, J., Jang, J., Na, I., Park, W., & You, S. (2023). Self-supervised Pre-training for Precipitation Post-processor. arXiv preprint arXiv:2310.20187.