Land Use and Land Cover Analysis of Koppal District Using ArcGIS and Machine Learning Techniques

This study presents a LULC classification of Koppal district for 2024 using Landsat-8 and Sentinel-2 imagery, Random Forest and SVM classifiers, and ArcGIS-based spatial analysis. Agriculture remains the dominant land-use category at approximately 50% of the district area, but its share has declined steadily since 2000 as settlement and, more significantly, mining activity have expanded, the latter now accounting for over one-fifth of the district. The classification achieved an overall accuracy of about 86% and a Kappa coefficient of approximately 0.83, confirming the reliability of the adopted machine-learning workflow.   The results highlight encroachment of settlements into agricultural land, continuing loss of forest and grazing land, and the growing environmental footprint of mining, all of which call for integrated, GIS-supported land-use planning that balances agricultural sustainability, controlled urban growth, and mineral resource development. The methodology developed here — combining multi-sensor satellite imagery, spectral and textural feature extraction, and machine-learning classification within ArcGIS — offers a replicable and scalable framework for LULC monitoring in other semi-arid, agriculture-dependent districts facing similar developmental pressures.

[1] S. Gopalakrishnan et al., “Land use and land cover change analysis in an urban expansion zone using remote sensing and GIS,” 2015. [2] R. Patil et al., “Land suitability analysis for agriculture using GIS and multi-criteria decision analysis,” 2017. [3] V. Sharma et al., “Assessment of deforestation trends and their impact on water resources using remote sensing,” 2018. [4] A. Kumar et al., “Mapping urban sprawl and its environmental impact using machine learning and GIS,” 2019. [5] P. Mehta et al., “GIS-based hydrological modeling for identification of flood-prone areas,” 2020. [6] S. Reddy et al., “Land degradation assessment using remote sensing and GIS techniques,” 2021. [7] J. R. Anderson, E. E. Hardy, J. T. Roach, and R. E. Witmer, “A Land Use and Land Cover Classification System for Use with Remote Sensor Data,” U.S. Geological Survey Professional Paper 964, 1976. [8] R. G. Congalton and K. Green, Assessing the Accuracy of Remotely Sensed Data: Principles and Practices, 3rd ed. Boca Raton, FL, USA: CRC Press, 2019. [9] G. M. Foody, “Status of land cover classification accuracy assessment,” Remote Sensing of Environment, vol. 80, no. 1, pp. 185–201, 2002. [10] J. R. Jensen, Introductory Digital Image Processing: A Remote Sensing Perspective, 4th ed. Boston, MA, USA: Pearson Education, 2016.