A Machine Learning Framework for Assessing Urban Growth of Cities and Suitability Analysis

Rural–urban immigration, regional wars, refugees, and natural disasters all bring to prominence the importance of studying urban growth. Increased growth rates are becoming a global phenomenon creating stress on agricultural land, spreading pollution, accelerating warming, increasing water run-off, which adds exponentially pressure resources impacts climate change. Based integration machine learning (ML) geographic information system (GIS), we employed framework delineate future boundaries for expansion agglomerations. We developed it based Time Delay Neural Network (TDNN) that depends equal time intervals Such an approach is used first in as predictive tool coupled with Land Suitability Analysis, incorporates both qualitative quantitative data propose evaluated Greater Irbid Municipality, Jordan. The results show recommended spatial proposed year 2025. more prevalent eastern, northern, southern areas less west. boundary map illustrates continuation these will slowly further encroach upon diminish land. By means suitability analysis, showed 51% region unsuitable growth, 43% moderately suitable only 6% TDNN methodology, ML dependent boundaries, can track predict trend thus develop policies protecting ecological lands optimizing directing