Detection of Landuse Land Cover Changes by using Maximum Likelihood Algorithm Application on Landsat Satellite Images
Authors:-Priyanka Gupta, Sharda Haryani, V.B. Gupta
Abstract-The identification of the LULC classes for the Mandsaur district Madhya Pradesh, India is the main objective of this research. The satellite images used in the analysis. Based on pixel-by-pixel supervised categorization of Landsat satellite images taken between 2003 and 2023 using the Arc-GIS tool across 20 year period, the work makes use of maximum likelihood approach. Various classifications of land use and land cover features are considered to predict overall changes, including populated areas, water bodies, agricultural land, forests and desert terrain. Landsat 8 photos from 2023 and remotely sensed Landsat 5 images from 2003 were used to detect changes inorder to accomplish this goal. The five LULC classes for the Mandsaur region are explained in this paper. The maximum likelihood algorithm is used in this work to compare the LULC classes for the Mandsaur region. The validation of the results for the supervised classification using MLC yielded kappa coefficients of 0.8263 and 0.7841 for 2023 and 2003 respectively. Land cover classification should benefit greatly from the application of MLC algorithms.
