用自监督学习提升暴雨概率预测准确率，延长预警时间。
Self-Supervised Learning with Probabilistic Density Labeling for Rainfall Probability Estimation
- 通过掩码建模自监督训练，捕捉气象变量间依赖关系。
- 在多个区域上优于现有模型，预报提前量更具优势。
- 适合气象预报、灾害预警领域研究人员参考。
数值天气预报（NWP）模型是气象学中模拟和预测大气变量行为的基础。降水预报的准确性及足够长的提前期对防范灾害性天气至关重要。然而，极端天气现象受时序动态影响，具有非线性和不可预测性，限制了NWP模型性能。为此，我们提出一种自监督学习与概率密度标签结合的方法（SSLPDL），用于后处理NWP降水预报，估计降雨概率。该方法利用自监督学习（SSL）中的掩码建模重建大气物理变量，使模型学习变量间的依赖关系；预训练编码器随后通过迁移学习应用于降水分割任务。此外，我们提出基于概率密度的简单标注策略，缓解暴雨等极端天气事件中的类别不平衡问题。实验表明，SSLPDL在区域降水后处理中表现优于其他模型，并在延长预报提前期方面具备竞争力。代码已开源：https://github.com/joonha425/SSLPDL。
原文摘要 · Abstract (English)
Numerical weather prediction (NWP) models are fundamental in meteorology for simulating and forecasting the behavior of various atmospheric variables. The accuracy of precipitation forecasts and the acquisition of sufficient lead time are crucial for preventing hazardous weather events. However, the performance of NWP models is limited by the nonlinear and unpredictable patterns of extreme weather phenomena driven by temporal dynamics. In this regard, we propose a \textbf{S}elf-\textbf{S}upervised \textbf{L}earning with \textbf{P}robabilistic \textbf{D}ensity \textbf{L}abeling (SSLPDL) for estimating rainfall probability by post-processing NWP forecasts. Our post-processing method uses self-supervised learning (SSL) with masked modeling for reconstructing atmospheric physics variables, enabling the model to learn the dependency between variables. The pre-trained encoder is then utilized in transfer learning to a precipitation segmentation task. Furthermore, we introduce a straightforward labeling approach based on probability density to address the class imbalance in extreme weather phenomena like heavy rain events. Experimental results show that SSLPDL surpasses other precipitation forecasting models in regional precipitation post-processing and demonstrates competitive performance in extending forecast lead times. Our code is available at https://github.com/joonha425/SSLPDL
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。