Meshless Surface Wind Speed Field Reconstruction Based on Machine Learning

作     者：Nian LIU Zhongwei YAN Xuan TONG Jiang JIANG Haochen LI Jiangjiang XIA Xiao LOU Rui REN Yi FANG Nian LIU;Zhongwei YAN;Xuan TONG;Jiang JIANG;Haochen LI;Jiangjiang XIA;Xiao LOU;Rui REN;Yi FANG

作者机构：Key Laboratory of Regional Climate-Environment for Temperate East Asia(RCE-TEA)Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China University of Chinese Academy of SciencesChinese Academy of SciencesBeijing 100049China Center for Artificial Intelligence in Atmospheric ScienceInstitute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Qi Zhi InstituteShanghai 200232China Beijing Meteorological Service CenterBMSCBeijing 100089China School of Mathematical SciencesPeking UniversityBeijing 100871China School of ScienceBeijing University of Posts and TelecommunicationsBeijing 100876China Lab of Meteorological Big DataBeijing 100086China 

出 版 物：《Advances in Atmospheric Sciences》 (大气科学进展（英文版）)

年 卷 期：2022年第39卷第10期

页      面：1721-1733页

核心收录：

学科分类：07[理学] 0706[理学-大气科学] 

基　　金：supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19030402) the Key Special Projects for International Cooperation in Science and Technology Innovation between Governments(Grant No.2017YFE0133600 the Beijing Municipal Natural Science Foundation Youth Project 8214066:Application Research of Beijing Road Visibility Prediction Based on Machine Learning Methods. 

主　　题：data reconstruction meshless machine learning surface wind speed random forest 

摘      要：We propose a novel machine learning approach to reconstruct meshless surface wind speed fields,i.e.,to reconstruct the surface wind speed at any location,based on meteorological background fields and geographical information.The random forest method is selected to develop the machine learning data reconstruction model(MLDRM-RF)for wind speeds over Beijing from 2015-19.We use temporal,geospatial attribute and meteorological background field features as inputs.The wind speed field can be reconstructed at any station in the region not used in the training process to cross-validate model performance.The evaluation considers the spatial distribution of and seasonal variations in the root mean squared error(RMSE)of the reconstructed wind speed field across Beijing.The average RMSE is 1.09 m s^(−1),considerably smaller than the result(1.29 m s^(−1))obtained with inverse distance weighting(IDW)interpolation.Finally,we extract the important feature permutations by the method of mean decrease in impurity(MDI)and discuss the reasonableness of the model prediction results.MLDRM-RF is a reasonable approach with excellent potential for the improved reconstruction of historical surface wind speed fields with arbitrary grid resolutions.Such a model is needed in many wind applications,such as wind energy and aviation safety assessments.