Evaluating Land Use Land Cover Classification Based on Machine Learning Algorithms

Abstract

Image classification depends substantially on the remote sensing method to generate maps of land use and land cover. This study used machine learning algorithms for classifying land cover, evaluating algorithms, and choosing the best way based on accuracy assessment matrices for land cover classifications. Satellite images from the Landsat by the United States Geological Survey (USGS) were used to classify the Babylon Governorate Land Use Land Cover (LULC). This study employed multispectral satellite images utilizing a spatial resolution of 30 meters and organized the data using three different algorithms to see the most accuracy. The process of categorization was carried out with the use of three distinct algorithms, which are as follows: Support Vector Machine (SVM), Mahalanobis Distance (MD), and Maximum Likelihood Classification (MLC). The classification algorithms utilized ArcGIS 10.8 and ENVI 5.3 software to detect four LULC classes: (Built-up Land, Water, Barren Land, and Agricultural Land). When applied to Landsat images, the results showed that the SVM approach gives greater overall accuracy and a larger kappa coefficient than the MD and MLC methods. SVM, MD, and MLC algorithms each have respective overall accuracy values of 86.88%, 85.00%, and 79.38%, respectively.

Keywords

• machine learning, lulc
• maximum likelihood classification
• mahalanobis distance
• support vector machine