基于深度学习改进数值天气预报模式和预报的研究及挑战  

Advances and Challenges for Improving Numerical Weather Prediction Models and Forecasting Using Deep Learning

作　　者：李扬[1,2] 刘玉宝[1,2] 许小峰[3] Li Yang;Liu Yubao;Xu Xiaofeng(Precision Regional Earth Modeling and Information Center,Nanjing University of Information Science and Technology,Nanjing 210044;Key Laboratory for Aerosol-Cloud-Precipitation of China Meteorological Administration,Joint International Research Laboratory of Climate and Environment Change,Nanjing University of Information Science and Technology,Nanjing 210044;China Meteorological Administration,Beijing 100081)

机构地区：[1]南京信息工程大学,精细化区域地球模拟和信息中心,南京210044 [2]南京信息工程大学,中国气象局气溶胶-云-降水重点开放实验室,气候与环境变化国际合作联合实验室,南京210044 [3]中国气象局,北京100081

出　　处：《气象科技进展》2021年第3期103-112,共10页Advances in Meteorological Science and Technology

基　　金：国家电网科技项目(5200-201955490A-0-0-00)。

摘　　要：随着高分辨率数值天气模式以及新一代地球观测系统的发展,气象领域的数据量在迅速增加,为天气和气候的理论研究和业务应用提供了丰富的信息,同时也对传统的数据处理方法及天气分析和预报技术带来了新的挑战。深度学习具有从大量的高维时空分布气象数据中提取复杂时空特征的能力,且具备计算效率高、可迁移性强、协同性和灵活性优的特点。目前深度学习已经在对流短时临近预报、极端事件检测和改进数值天气模式及其预报误差订正等方面得到了较为广泛的研究。首先概述目前气象领域所应用的深度学习方法和模型,然后聚焦介绍和讨论数据驱动的深度学习在理论驱动的数值天气预报模式方面的应用。深度学习在数值天气预报模式的资料同化、次网格物理过程参数化、数值天气模式后处理等方面展现出很好的应用前景,但仍需要进一步改善深度学习模型的可解释性和不确定性量化问题。构建数据驱动的深度学习和理论驱动的数值天气模式混合模型,发挥深度学习和数值天气模式的协同作用,将是进一步改善数值天气预报能力的新途径。With the development of high-resolution numerical weather models and new-generation Earth observation systems,the amount of data in the field of meteorology is rapidly increasing.The rapid increase of meteorological data provides rich information for weather and climate theoretical research and operational applications,but also brings new challenges to traditional data processing methods and weather analysis and forecasting techniques.Deep learning could extract complex spatiotemporal features from a large amount of high-dimensional spatiotemporal distributed meteorological data with high computational efficiency and transferability,and excellent synergy and flexibility.Deep learning has been widely applied in convective nowcasting,extreme event detection,and improving numerical weather models and their prediction.In this paper,we firstly introduce the main deep learning methods and models currently applied in meteorology,and then discuss the applications of the data-driven deep learning to the theory-driven numerical weather prediction models in detail.Deep learning presents significant impacts on improving data assimilation,parameterization of sub-grid physical processes,and numerical weather model output post-processing.Meanwhile,the interpretability and uncertainty quantification of the deep learning models are highly desirable and challenging.Developing hybrid models of data-driven deep learning and theory-driven numerical weather models to exploit the synergy between deep learning and numerical weather models present a new way to further improve numerical weather models.

关 键 词：深度学习 数值天气模式 资料同化 可解释性 不确定性量化 混合模型 

分 类 号：P456.7[天文地球—大气科学及气象学] TP18[自动化与计算机技术—控制理论与控制工程]