Analyzing Land Use/Land Cover Changes and its Dynamics Using Remote Sensing Data: A case study of Gabala, Azerbaijan

Abstract

To track global environmental change and evaluate the risk to sustainable development, analysts and decision-makers in government, civil society, finance, and industry need the fundamental geospatial data products known as Land Use and Land Cover Change (LULCC) maps. Our research studied LULCC variations in a timeframe of 5 years in the Gabala district. Sentinel 2 open-source products were used to compare and categorize the procedure over one-year time intervals. For this investigation, the discrete indexing method was developed and used. The approach we used was focused on obtaining multiple indices and using them to improve classification performance. The Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Bare Soil Index (BSI), Normalized Difference Tillage Index (NDTI), and Salinity Index (SI) are the indices evaluated. The most crucial variables were determined and classified using the random forest classifier in LULCC. The Sentinel Application Platform of the European Space Agency (SNAP ESA) algorithm was used to analyze the process and performed over 90% accurate predictions when applied to the testing dataset. Results revealed that using the RS technique, time and cost-efficient analyses are possible and reliable for developing socioeconomic and ecological growth strategies.