Ai/Ml Based Urban Growth Monitoring Using Remote Sensing Images and Deep Learning

Abstract

Urbanization has become one of the most significant drivers of environmental and infrastructural transformation across the globe. Continuous monitoring of urban expansion is essential for effective city planning, resource management, environmental conservation, and sustainable development. Conventional methods of analyzing satellite imagery involve manual interpretation and traditional image processing techniques, which are labor-intensive, timeconsuming, and often unable to handle the growing volume of remote sensing data. To address these challenges, this project proposes an AI/ML Based Urban Growth Monitoring System that automatically detects urban growth using deep learning techniques applied to satellite and remote sensing images. The proposed web-based application provides separate administrator and user interfaces, enabling efficient dataset management, model training, prediction, and report generation. Advanced deep learning architectures such as Convolutional Neural Networks (CNN), VGG16, and ResNet50 are utilized to classify satellite images with high accuracy. The system incorporates image preprocessing, Grad-CAM visualization for explainable artificial intelligence, confidence score generation, geospatial mapping, and downloadable PDF reports to improve transparency and usability. By integrating artificial intelligence, machine learning, computer vision, and remote sensing technologies, the proposed solution minimizes manual effort, enhances prediction accuracy, and provides valuable decision support for urban planners, government agencies, environmental researchers, and smart city initiatives. The system offers a scalable and intelligent approach for monitoring urban growth while promoting efficient land-use management and sustainable urban development.