Self-Supervised Pre-Training for Precipitation Post-Processor (2310.20187v3)
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.
- Sojung An. Nowcast-to-forecast: Token-based multiple remote sensing data fusion for precipitation forecast. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023.
- Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
- Deep learning for twelve hour precipitation forecasts. Nature communications, 13(1):1–10, 2022.
- Multiscale vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6824–6835, 2021.
- Masked autoencoders as spatiotemporal learners. Advances in neural information processing systems, 35:35946–35958, 2022.
- A novel hybrid artificial neural network-parametric scheme for postprocessing medium-range precipitation forecasts. Advances in Water Resources, 151:103907, 2021.
- Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
- Benchmark dataset for precipitation forecasting by post-processing the numerical weather prediction. arXiv preprint arXiv:2206.15241, 2022.
- Increasing frequencies and changing characteristics of heavy precipitation events threatening infrastructure in europe under climate change. Natural Hazards and Earth System Sciences, 17(7):1177–1190, 2017.
- Classification accuracy score for conditional generative models. Advances in neural information processing systems, 32, 2019.
- Postprocessing of nwp precipitation forecasts using deep learning. Weather and Forecasting, 38(3):487–497, 2023.
- Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems, 28, 2015.
- Deep learning for precipitation nowcasting: A benchmark and a new model. Advances in neural information processing systems, 30, 2017.
- Internimage: Exploring large-scale vision foundation models with deformable convolutions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14408–14419, 2023.
- Unified perceptual parsing for scene understanding. In Proceedings of the European conference on computer vision (ECCV), pages 418–434, 2018.
- Machine learning for precipitation forecasts postprocessing: Multimodel comparison and experimental investigation. Journal of Hydrometeorology, 22(11):3065–3085, 2021.