Application of Projection Pursuit Evaluation Model Based on Real-Coded Accelerating Genetic Algorithm in Evaluating Wetland Soil Quality Variations in the Sanjiang Plain, China

作     者：FUQIANG XIEYONGGANG WEIZIMIN FU QIANG, XIE YONGGANG2 and WEI ZIMIN Sichuan University, Chengdu 610065 (China) Heilongjiang University, Harbin 150080 (China) Northeast Agricultural University, Harbin 150030 (China)

作者机构：SichuanUniversityChengdu610065(China) HeilongjiangUniversityHarbin150080(China) NortheastAgriculturalUniversityHarbin150030(China) 

出 版 物：《Pedosphere》 (土壤圈（英文版）)

年 卷 期：2003年第13卷第3期

页      面：249-256页

核心收录：

学科分类：082802[工学-农业水土工程] 08[工学] 0828[工学-农业工程] 09[农学] 0903[农学-农业资源与环境] 090301[农学-土壤学] 

基　　金：Project supported by the China Postdoctoral Science Foundation the Youth Foundation of Sichuan University(No.432028)and the National High-Tech Research and Development Program of China(863 Program)(No.2002AA2Z4251) 

主　　题：evaluation projection pursuit evaluation model real-coded acceleratinggenetic algorithm soil quality variations 

摘      要：A new technique of dimension reduction named projection pursuit is applied to model and evaluatewetland soil quality variations in the Sanjiang Plain, Helongjiang Province, China. By adopting the im-proved real-coded accelerating genetic algorithm (RAGA), the projection direction is optimized and multi-dimensional indexes are converted into low-dimensional space. Classification of wetland soils and evaluationof wetland soil quality variations are realized by pursuing optimum projection direction and projection func-tion value. Therefore, by adopting this new method, any possible human interference can be avoided andsound results can be achieved in researching quality changes and classification of wetland soils.