Monitoring Urban Expansion in Moradabad District: An Evaluation of Classification Techniques in LULC Change Detection

Since adopting globalization in 1991, India's economy has become the fifth-largest in the world. This is due to technological advancements and the modernization of industries. Consequently, many people have moved from rural areas to cities in pursuit of jobs and modern conveniences. This rapid population shift has greatly influenced Land-Use and LandCover (LULC). Monitoring these LULC changes is vital for understanding landscape transformations. Moradabad District, Uttar Pradesh, was selected to study the changes in LULC for current research work. Landsat 8 OLI data for years 2014, 2019, and 2024 for the same season i.e. summer, was taken to minimize variations in environmental factors. However, to ensure optimal spectral information, the Optimum Index Factor (OIF) was chosen to get the best possible combination of satellite image bands for each year to minimize data redundancy. Moreover, various indices like the Biophysical Composition-Index (BCI), Normalized-Difference-Vegetation Index (NDVI), and Modified-Normalized-Difference-Water-Index (MNDWI), were used for assessing enhanced features in LULC changes. ArcGIS Pro 2.9.0 software was used to perform supervised classification using Maximum-Likelihood Classification (MLC), Support-Vector-Machine (SVM), and Random-Tree (RT) algorithms for all mentioned years individually. Besides of it, the results of the above-mentioned algorithms were compared. Further, the results of the LULC maps revealed a significant shift in urbanization between 2014-2019 and 2019-2024. It will provide valuable insights for future agriculture and urban planning.