Green spaces are becoming widely degraded as a result of the massive urbanization that is occurring worldwide. Urban Green Spaces (UGS) are vital for improving urban quality of life because they provide vital ecosystem services. These include a variety of vegetated areas found inside cities, such as parks, green roofs, and street vegetation. This chapter describes a pilot project that used geographic information systems (GIS) and remote sensing to map and delineate urban green cover in the Siliguri municipal region of India. The study’s objective was to create mapping and evaluation methods that are suitable and scalable for measuring the amount of green plant cover in the area. Tests were conducted using Landsat OLI and TM satellite images to identify the vegetation cover and a consistent technique for measuring the vegetation’s extent. In an effort to distinguish vegetation cover from remotely sensed images, image processing techniques, including various vegetation indices, were used. For such procedures, specialized GIS scripts were created to make them quick, automated, and repeatable. Lastly, the urban green space has been implemented utilizing an artificial neural network (ANN), a machine learning technique, with various vegetation indices utilized as an input parameter. At a five-year temporal interval, the vegetation cover was evaluated and mapped from 1990 to 2020. The accuracy of the categorization was evaluated in comparison to field observations and aerial picture interpretation. Depending on the year, the photo-based classification’s overall kappa accuracy ranged from 68% to 82%.