南京信息工程大学学报2025，Vol.17Issue(3)：363-373,11.DOI:10.13878/j.cnki.jnuist.20240225001
基于BP典型相关分析和多变量SOM聚类的区划算法研究
Regionalization algorithm based on BP canonical correlation analysis and multivariate SOM clustering
摘要
Abstract
Here,we propose a data-driven regionalization algorithm based on machine learning and modern statisti-cal methods to address current issues such as limited climate regionalization variables,underutilized information,and insufficient consideration of climate change impacts.Firstly,we use the Mann-Kendall test and sliding t-test to iden-tify change points of time series of primary variables and segment the study period accordingly.Next,we employ Bar-nett-Preisendorfer Canonical Correlation Analysis(BPCCA)to select covariates and establish a multivariate Self-Or-ganizing Map(SOM)clustering algorithm to achieve climate regionalization for different stages.Finally,we analyze the practical significance of regionalization results in combination with climate zone profiles,and assess the impact of climate change on climate regionalization.Experimental results demonstrate that the proposed regionalization algo-rithm,driven by data rather than contour lines of primary variables or manually setting thresholds,improves data uti-lization and ensures a more objective and rational regionalization process.By incorporating multiple covariates and climate change impacts into the algorithm,the efficiency and reliability of regionalization are effectively enhanced without considering climate background during the regionalization process.关键词
区划/Mann-Kendall检验/BP典型相关分析/多变量SOM聚类Key words
regionalization/Mann-Kendall test/Barnett-Preisendorfer canonical correlation analysis(BPCCA)/multivariate self-organizing map(SOM)clustering分类
大气科学引用本文复制引用
吴香华,金芯如,黎亚少,任苗苗,王巍巍..基于BP典型相关分析和多变量SOM聚类的区划算法研究[J].南京信息工程大学学报,2025,17(3):363-373,11.基金项目
国家自然科学基金(42075068,41975176,41975087) （42075068,41975176,41975087）
国家重点研发计划重点专项(2018YFC1507905) （2018YFC1507905）
2024江苏应用数学(南京信息工程大学)中心开放课题 （南京信息工程大学）
