您好，欢迎访问山东省农业科学院文献资源数据库平台

Comparison of the Applicability of J-M Distance Feature Selection Methods for Coastal Wetland Classification

文献类型： 外文期刊

作者： Zhang, Xianmei 1 ; Lin, Xiaofeng 1 ; Fu, Dongjie 3 ; Wang, Yang 2 ; Sun, Shaobo 4 ; Wang, Fei 5 ; Wang, Cuiping 1 ; Xiao, Zhongyong 1 ; Shi, Yiqiang 1 ;

作者机构： 1.Jimei Univ, Coll Harbour & Coastal Engn, Xiamen 361021, Peoples R China

2.Fujian Normal Univ, Sch Geog Sci, Fuzhou 350007, Peoples R China

3.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China

4.Tianjin Univ, Inst Surface Earth Syst Sci, Sch Earth Syst Sci, Tianjin 300072, Peoples R China

5.Shandong Acad Agr Sci, Inst Agr Informat & Econ, 23788 Ind North Rd, Jinan 250010, Peoples R China

关键词： remote sensing; feature selection; J-M distance; wetland classification; random forest; GEE

期刊名称：WATER （ 影响因子：3.4； 五年影响因子：3.5 ）

ISSN：

年卷期： 2023 年 15 卷 12 期

页码：

收录情况： SCI

摘要： Accurate determination of the spatial distribution of coastal wetlands is crucial for the management and conservation of ecosystems. Feature selection methods based on the Jeffries-Matusita (J-M) method include J-M distance with simple average ranking (JM(ave)), J-M distance based on weights and correlations (JM(improved)), and heuristic J-M distance (JM(mc)). However, as the impacts of these methods on wetland classification are different, their applicability has rarely been investigated. Based on the Google Earth Engine (GEE) and random forest (RF) classifier, this is a comparative analysis of the applicability of the JM(ave), JM(improved), and JM(mc) methods. The results show that the three methods compress feature dimensions and retain all feature types as much as possible. JM(mc) exhibits the most significant compression from a value of 35 to 15 (57.14%), which is 37.14% and 40% more compressed than JM(ave) and JM(improved), respectively. Moreover, they produce comparable classification results, with an overall classification accuracy of 90.20 & PLUSMN; 0.19% and a Kappa coefficient of 88.80 & PLUSMN; 0.22%. However, different methods had their own advantages for the classification of different land classes. Specifically, JM(ave) has a better classification only in cropland, while JM(mc) is advantageous for recognizing water bodies, tidal flats, and aquaculture. While JM(improved) failed to retain vegetation and mangrove features, it enables a better depiction of the mangroves, salt pans, and vegetation classes. Both JM(ave) and JM(improved) rearrange features based on J-M distance, while JM(mc) places more emphasis on feature selection. As a result, there can be significant differences in feature subsets among these three methods. Therefore, the comparative analysis of these three methods further elucidates the importance of J-M distance in feature selection, demonstrating the significant potential of J-M distance-based feature selection methods in wetland classification.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：山东省农业科学院文献资源数据库平台

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台