Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2310.20187 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909111693606912 |
|---|---|
| author | An, Sojung Lee, Junha Jang, Jiyeon Na, Inchae Park, Wooyeon You, Sujeong |
| author_facet | An, Sojung Lee, Junha Jang, Jiyeon Na, Inchae Park, Wooyeon You, Sujeong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_20187 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Self-Supervised Pre-Training for Precipitation Post-Processor An, Sojung Lee, Junha Jang, Jiyeon Na, Inchae Park, Wooyeon You, Sujeong Machine Learning Artificial Intelligence 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. |
| title | Self-Supervised Pre-Training for Precipitation Post-Processor |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2310.20187 |