Comparison of the Applicability of J-M Distance Feature Selection Methods for Coastal Wetland Classification
Author:
Zhang Xianmei12, Lin Xiaofeng1ORCID, Fu Dongjie3ORCID, Wang Yang2, Sun Shaobo4ORCID, Wang Fei5, Wang Cuiping1, Xiao Zhongyong1, Shi Yiqiang1
Affiliation:
1. College of Harbour and Coastal Engineering, Jimei University, Xiamen 361021, China 2. School of Geographical Sciences, Fujian Normal University, Fuzhou 350007, China 3. State Key Laboratory of Resources and Environment Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China 4. Institute of Surface-Earth System Science, School of Earth System Science, Tianjin University, Tianjin 300072, China 5. Institute of Agricultural Information and Economics, Shandong Academy of Agricultural Sciences, No. 23788, Industrial North Road, Jinan 250010, China
Abstract
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 (JMave), J-M distance based on weights and correlations (JMimproved), and heuristic J-M distance (JMmc). 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 JMave, JMimproved, and JMmc methods. The results show that the three methods compress feature dimensions and retain all feature types as much as possible. JMmc exhibits the most significant compression from a value of 35 to 15 (57.14%), which is 37.14% and 40% more compressed than JMave and JMimproved, respectively. Moreover, they produce comparable classification results, with an overall classification accuracy of 90.20 ± 0.19% and a Kappa coefficient of 88.80 ± 0.22%. However, different methods had their own advantages for the classification of different land classes. Specifically, JMave has a better classification only in cropland, while JMmc is advantageous for recognizing water bodies, tidal flats, and aquaculture. While JMimproved failed to retain vegetation and mangrove features, it enables a better depiction of the mangroves, salt pans, and vegetation classes. Both JMave and JMimproved rearrange features based on J-M distance, while JMmc 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.
Funder
Young Scientists Fund of the National Natural Science Foundation of China Natural Science Foundation for Young Scientists of Fujian Province Education Department of the Fujian Province Science and Technology Project Scientific Project from Fujian Provincial Department of Science and Technology
Subject
Water Science and Technology,Aquatic Science,Geography, Planning and Development,Biochemistry
Reference49 articles.
1. Mitsch, W., and Gosselink, J. (1993). Wetlands, John Wiley and Sons. Inc.. [2nd ed.]. 2. Remote sensing for wetland classification: A comprehensive review;Mahdavi;GIScience Remote Sens.,2018 3. Can wetlands maintained for human use also help conserve biodiversity? Landscape-scale patterns of bird use of wetlands in an agricultural landscape in north India;Sundar;Biol. Conserv.,2013 4. Banks, S., White, L., Behnamian, A., Chen, Z., Montpetit, B., Brisco, B., Pasher, J., and Duffe, J. (2019). Wetland Classification with Multi-Angle/Temporal SAR Using Random Forests. Remote Sens., 11. 5. Tian, S., Zhang, X., Tian, J., and Sun, Q. (2016). Random Forest Classification of Wetland Landcovers from Multi-Sensor Data in the Arid Region of Xinjiang, China. Remote Sens., 8.
|
|