Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
复制标题
DOI：
10.1609/aaai.v35i1.16090
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Sijie He;Xinyan Li;T. DelSole;Pradeep Ravikumar;A. Banerjee
中科院分区：
文献类型：
--
作者：
Sijie He;Xinyan Li;T. DelSole;Pradeep Ravikumar;A. Banerjee
次季节预报 (SSF) 侧重于预测 2 周至 2 个月时间范围内的关键变量，例如温度和降水量。熟练的 SSF 将在农业生产力、水资源管理和极端天气事件应急计划等领域具有巨大的社会价值。然而，SSF 被认为比天气预报甚至季节性预测更具挑战性，并且仍然是一个很大程度上未被充分研究的问题。在本文中，我们根据收集的 SSF 数据集仔细研究了美国本土次季节温度预测的 10 种机器学习 (ML) 方法，包括来自大气、海洋和陆地的各种气候变量。尽管各个领域最近取得了进展，但由于复杂的大气-陆地-海洋耦合和高质量观测数据的有限，SSF给机器学习带来了巨大的挑战。我们的结果表明，合适的机器学习模型（例如 XGBoost）在某种程度上可以捕获次季节时间尺度的可预测性，并且可以超越气候基线，而深度学习（DL）模型几乎无法与精心设计的架构相匹配的最佳结果。此外，我们的分析和探索为提高次季节预测质量的重要方面提供了见解，例如特征表示和模型架构。 SSF 数据集和代码随本文一起发布，供更广泛的研究社区使用。
Sub-seasonal forecasting (SSF) focuses on predicting key variables such as temperature and precipitation on the 2-week to 2-month time scale. Skillful SSF would have immense societal value in such areas as agricultural productivity, water resource management, and emergency planning for extreme weather events. However, SSF is considered more challenging than either weather prediction or even seasonal prediction, and is still a largely understudied problem. In this paper, we carefully investigate 10 Machine Learning (ML) approaches to sub-seasonal temperature forecasting over the contiguous U.S. on the SSF dataset we collect, including a variety of climate variables from the atmosphere, ocean, and land. Because of the complicated atmosphere-land-ocean couplings and the limited amount of good quality observational data, SSF imposes a great challenge for ML despite the recent advances in various domains. Our results indicate that suitable ML models, e.g., XGBoost, to some extent, capture the predictability on sub-seasonal time scales and can outperform the climatological baselines, while Deep Learning (DL) models barely manage to match the best results with carefully designed architecture. Besides, our analysis and exploration provide insights on important aspects to improve the quality of sub-seasonal forecasts, e.g., feature representation and model architecture. The SSF dataset and code are released with this paper for use by the broader research community.