A Dynamic Framework for a GeoAI-Driven Updatable Master Planning System

Abstract

Traditional master planning often relies on decadal, static documents that fail to account for the rapid spatio-temporal dynamics of modern urban environments. This divergence between planned and actual land use creates systemic inefficiencies in urban governance. This research proposes a GeoAI-driven framework—a formal systems approach that integrates Geomatics, Artificial Intelligence (AI), and Deep Learning (DL) into a live, updatable “City Engine.” The framework utilises Convolutional Neural Networks (CNN) for automated change detection and GIS-based heuristic rules for instant plan versioning. By shifting the master plan from a static atlas to a dynamic “body of knowledge,” the proposed system enables real-time monitoring, evaluation, and publishing of urban development strategies. The results demonstrate that such a system can significantly bridge the implementation gap, offering a scalable model for smart city governance and sustainable regional development.