arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.02676cs.LGcs.CV
收藏

PostRainBench：降水预报的综合基准与一个新模型

PostRainBench: A comprehensive benchmark and a new model for precipitation forecasting

AI Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）AI方向）；School of Atmospheric Science, Nanjing University（南京大学大气科学学院）；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）

Yujin Tang, Jiaming Zhou, Xiang Pan, Zeying Gong, Junwei Liang

备注：
16 pages, 6 figures, ICLR24 Tackling Climate Change with Machine Learning Workshop
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对降水预报物理建模局限，提出综合基准PostRainBench及通道注意力增强多任务学习框架CAMT，结合加权损失函数，首次在暴雨条件下优于NWP方法。

摘要：

准确的降水预报是一个具有重要社会意义的重大挑战。尽管数据驱动方法已成为广泛使用的解决方案，但仅依赖数据驱动方法在底层物理建模方面存在局限性，难以做出准确预测。我们关注基于数值天气预报（NWP）后处理的降水预报任务，将机器学习技术与传统NWP相结合。由于降水数据不平衡以及多个气象变量之间的复杂关系，该任务仍具挑战性。为解决这些局限性，我们引入了PostRainBench，一个综合的多变量NWP后处理基准，以及CAMT，一个简单有效的通道注意力增强多任务学习框架，并配有专门设计的加权损失函数。在所提基准上的广泛实验结果表明，我们的方法在各自数据集上的降雨CSI分别比最先进方法高出6.3%、4.7%和26.8%，在暴雨CSI上比NWP预测分别提升了15.6%、17.4%和31.8%。最值得注意的是，我们的模型是首个在暴雨条件下优于NWP方法的基于深度学习的方法。这些结果突显了我们的模型在减轻极端降雨事件严重后果方面的潜在影响。我们的数据集和代码可在https://github.com/yyyujintang/PostRainBench获取。

英文摘要：

Accurate precipitation forecasting is a vital challenge of societal importance. Though data-driven approaches have emerged as a widely used solution, solely relying on data-driven approaches has limitations in modeling the underlying physics, making accurate predictions difficult. We focus on the Numerical Weather Prediction (NWP) post-processing based precipitation forecasting task to couple Machine Learning techniques with traditional NWP. This task remains challenging due to the imbalanced precipitation data and complex relationships between multiple meteorological variables. To address these limitations, we introduce the \textbf{PostRainBench}, a comprehensive multi-variable NWP post-processing benchmark, and \textbf{CAMT}, a simple yet effective Channel Attention Enhanced Multi-task Learning framework with a specially designed weighted loss function. Extensive experimental results on the proposed benchmark show that our method outperforms state-of-the-art methods by 6.3\%, 4.7\%, and 26.8\% in rain CSI and improvements of 15.6\%, 17.4\%, and 31.8\% over NWP predictions in heavy rain CSI on respective datasets. Most notably, our model is the first deep learning-based method to outperform NWP approaches in heavy rain conditions. These results highlight the potential impact of our model in reducing the severe consequences of extreme rainfall events. Our datasets and code are available at https://github.com/yyyujintang/PostRainBench.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑