文献类型：期刊文献

英文题名：A novel information changing rate and conditional mutual information-based input feature selection method for artificial intelligence drought prediction models

作者：Li, Qiongfang Han, Xingye Liu, Zhennan He, Pengfei Shi, Peng Chen, Qihui Du, Furan

第一作者：Li, Qiongfang

通信作者：Han, XY[1];Liu, ZN[2]

机构：[1]Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Peoples R China;[2]Yangtze Inst Conservat & Dev, Nanjing, Peoples R China;[3]Guizhou Inst Technol, Sch Civil Engn, Guiyang, Peoples R China;[4]Hydrol & Water Resource Bur Henan Prov, Zhengzhou, Peoples R China

第一机构：Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Peoples R China

通信机构：corresponding author), Hohai Univ, Coll Hydrol & Water Resources, Nanjing, Peoples R China;corresponding author), Guizhou Inst Technol, Sch Civil Engn, Guiyang, Peoples R China.|贵州理工学院土木工程学院;贵州理工学院;

年份：0

外文期刊名：CLIMATE DYNAMICS

收录：;Scopus(收录号：2-s2.0-85123890045);WOS:【SCI-EXPANDED(收录号:WOS:000748472600003)】；

基金：Financial support is gratefully acknowledged from the National Natural Science Foundation Commission of China under Grant Numbers 51879069 and 41961134003, and the Jiangsu Provincial Collaborative Innovation Center of World Water Valley and Water ecological civilization, China.

语种：英文

外文关键词：Feature selection; Information changing rate; Conditional mutual information; Drought-driving factors; Yunnan-Guizhou Plateau

摘要：The efficient and accurate selection of primary drought-driving factors as the independent variables of drought prediction model is critical in improving drought prediction accuracy. In this study, a novel feature selection method based on information changing rate and conditional mutual information (ICR-CMIFS) was proposed and evaluated by the comparison with other feature selection methods from feature selection, simulation, and classification aspects; two artificial intelligence drought prediction models, which treated the factors selected by ICR-CMIFS, correlation analysis (CA) and mutual information maximum (MIM) respectively as independent variables and standardized precipitation evapotranspiration index (SPEI) in 3/6/12-month time scales as dependent variables, were established; the superiority of ICR-CMIFS over CA and MIM methods in the selection of primary climatic drought-driving factors in Yunnan-Guizhou Plateau (YGP) was tested by the performance of the two models. The results revealed: the ICR-CMIFS was superior to the other feature selection methods; both artificial intelligence drought prediction models with the independent variables selected by ICR-CMIFS performed better in terms of correlation coefficient, Nash-Sutcliffe coefficient, root-mean square error and model computing time than by the MIM and CA methods. The outputs can provide an innovative approach in selecting primary drought-driving factors and improving drought prediction accuracy.