使用人工神经网络改进2022年北京冬奥会数值天气预报后处理过程的算法研究  

Develop an Objective Post-processing System with Artificial Neural Network to Improve Numerical Weather Prediction for the Olympic Winter Games Beijing 2022

作　　者：屈永霖 闻新宇[1] 张慕琪 刘喆[1,3] QU Yonglin;WEN Xinyu;ZHANG Muqi;LIU Zhe(Department of Atmospheric and Oceanic Sciences,School of Physics,Peking University,Beijing 100871;96941 PLA Troop,Beijing 102206;94926 PLA Troop,Wuxi 214000)

机构地区：[1]北京大学物理学院大气与海洋科学系,北京100871 [2]96941部队,北京102206 [3]94926部队,无锡214000

出　　处：《北京大学学报（自然科学版）》2022年第2期210-220,共11页Acta Scientiarum Naturalium Universitatis Pekinensis

基　　金：国家自然科学基金(41875088,41630527,4171101348)资助。

摘　　要：提出一种基于先进机器学习算法的纯客观、实时天气预报后处理方法。该方法使用历史数值天气预报结果和实况观测值,训练出一个人工神经网络模型,再将该模型应用于每日实时发布的数值天气预报结果中,得到台站级别的天气要素预报结果。于张家口市和北京市分别建立该模型,并使用2005—2020年的观测数据和模式数据进行训练、验证和调优。结果表明,该模型预报的5个常规气象要素的预报误差普遍优于一元线性回归、多元线性回归以及数值天气预报模式的原始输出值,尤其对3天以内的天气预报具有明显优势。基于该模型发展的全自动实时后处理系统已于2020年11月1日开始每日自动化地输出预报结果,并服务于2022年北京冬奥会的气象保障工作。A new objective post-processing system with cutting-edge machine learning algorithm for numerical weather prediction is presented.The core of the system,a matrix of artificial neural network trained by using historical in-situ observations and model results,can be applied on the latest numerical weather prediction results and produce real-time forecast for specific stations.The authors investigate the performance of post-processing system for two stations,Zhangjiakou and Beijing,for the period 2005-2020.It is shown that the forecasts produced by the new system are significantly more accurate than those produced by raw model forecasts,single-variable linear regression,and multi-variable linear regression,especially in terms of 3-day forecast.The authors developed all the core and auxiliary code by serving as Zhangjiakou and Beijing post-processing systems,which are routinely deployed since Nov.1,2020,to facilitate the weather service for the Olympic Winter Games at Beijing in 2022.

关 键 词：人工神经网络 实时天气预报 数值天气预报 后处理 

分 类 号：P456.7[天文地球—大气科学及气象学]