Analyzing land use land cover change in the city of Delhi, India

Abstract

This study examines the spatial-temporal dynamics of land use land cover (LULC) in the city of Delhi, India, from 2000 to 2020. Multi-dated medium resolution imagery from Landsat 7 (ETM+) for 2000 and Landsat 8 (OLI) for 2020 was used for the study. Support vector machine algorithm was used for the land use land cover classification. Spectral indices such as NDVI, NDBI, NDWI, NDBSI and road index were generated and integrated to improve the accuracy of the classification. These indices helped the differentiation of vegetation, built-up areas, water bodies, bare soil, agriculture, fallow land, Ridge and open land. ArcGIS Pro was used as part of post-classification change detection and accuracy assessment. The overall accuracy of the classification for 2000 and 2020 was 80% and 83% respectively. The results showed a substantial urban expansion in the outskirts of the city, and an increase in built up areas with vegetation in the central part of Delhi. The study links these changes to elements like infrastructure development, population increase, and policy interventions, emphasizing the necessity of integrated land management techniques in urban settings.