The use of machine learning algorithm in the analysis of the urban sprawl has gained considerable importance in scholars in urban planning and environmental sustainability studies. It is associated with the fast and indeed, at times, uncontrolled growth. This papers seeks to examine the applicability of machine learning algorithms in the task of analyzing and quantifying map urban pattern expansion, which includes the issues of land and temperature changes between the urban and non-urban, densities of urban growth and expansion rate from the year of 2004 to 2023. The examined methods include support vector machines (SVM) and clustering algorithms with the geographic information techniques in the form of Geographical Information Systems (GIS) to improve on spatial quantification. The application of efficiency in data interpretation towards sustainable urban development. We synthesize the current research; we detect the construction area change from 2004 to 2023 is 30.24sq.km to 41.31sq.km and the change in temperature from 27.5 degrees to 34.5 degrees.