As the world is moving more towards urban planning, one of the challenges is creating sustainable and livable cities. One of the key issues faced is optimizing green spaces, which have a significant impact on biodiversity, urban quality of life, and environmental health. This work leverages advanced image analytics and use of machine learning algorithms to automate tree enumeration, estimate green cover, and compute optimal paths in forested regions. Geographic Information Systems based images are processed using the Convolutional Neural Networks to identify the relevant features. It used high-resolution satellite imagery, and it put together all the mentioned technology into an integrated web application. Mask Region-based Convolutional Neural Network is used to identify the tree density factor. This application supports efficient forest monitoring, conservation planning, and environmental assessments, offering accurate data-driven insights while reducing operational costs and manual labor.