APPLYING THE METHOD OF MACHINE LEARNING - DECISION TREE IN ASSESSING THE MANGROVE FOREST CHANGES IN DAT MUI COMMUNE

Abstract

Method of machine learning - decision tree is used for classification, regression and other tasks by building many decision trees. Decision trees are now a popular method in data mining. The decision tree then describes a tree structure, where the leaves represent the categories and the branches represent the combinations of attributes that lead to that classification [1]. Within the scope of this paper, the research team tested an algorithm of machine learning method (Machine Learning) - decision tree in classifying land use objects, especially mangrove forests on LANDSAT satellite images with The test area is Dat Mui commune, Ngoc Hien district, Ca Mau province. The research results have successfully classified the land use classes for the period 1995 - 2020 with a high total accuracy of 88.8 %, respectively, and a Kappa coefficient of 0.85 which is very good for Landsat images with medium resolution.