Meshless Surface Wind Speed Field Reconstruction Based on Machine Learning

查看全文 作　　者：Nian [1,2,3]LIU;Zhongwei [1,2,3]YAN;Xuan [4]TONG;Jiang [5]JIANG;Haochen [6,7]LI;Jiangjiang [1,2,3]XIA;Xiao [8]LOU;Rui [1]REN;Yi [1]FANG

机构地区：[1]Key Laboratory of Regional Climate-Environment for Temperate East Asia(RCE-TEA),Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing 100029,China;[2]University of Chinese Academy of Sciences,Chinese Academy of Sciences,Beijing 100049,China;[3]Center for Artificial Intelligence in Atmospheric Science,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing 100029,China;[4]Qi Zhi Institute,Shanghai 200232,China;[5]Beijing Meteorological Service Center,BMSC,Beijing 100089,China;[6]School of Mathematical Sciences,Peking University,Beijing 100871,China;[7]School of Science,Beijing University of Posts and Telecommunications,Beijing 100876,China;[8]Lab of Meteorological Big Data,Beijing 100086,China

出　　处：《Advances in Atmospheric Sciences》索引2022年第39卷第10期,共13页

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. 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. 关键词：data reconstruction MESHLESS machine learning surface wind speed random forest

相关文献

参考文献（46）
引证文献（1）
耦合文献（4）

参考文献(46)

引证文献(1)

耦合文献(4)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Meshless Surface Wind Speed Field Reconstruction Based on Machine Learning

参考文献(46)

引证文献(1)

耦合文献(4)

用户提示