A Survey and Analysis of Intelligent Forecasting and Decision-Making Evaluation of Urban Growth using Artificial Intelligence

Abstract

A dense concentration of human-made features such as residences, businesses, highways, bridges, and trains characterize urban areas, which are developed regions that encircle cities and are home to most of the population's non-agricultural labourers. Monitoring and modeling urban development have become critical for long-term urban planning and decision-making. Urban growth prediction models are crucial for understanding the causes and implications of urban land use patterns and predicting upcoming growth of city based on the current scenario, ensuring sustainable city development. The Cellular Automata (CA) approach has been used to simulate the urban growth in a hypothetical region, based on principles governing cell spatial interaction and parameters for exploring alternative urban shapes. However, CA faces numerous uncertainties and more research is requited to enhance its adaptability to urban environments. In recent times, Artificial Intelligence models like Machine Learning (ML) and Deep Learning (DL) are being utilized for urban growth prediction, enhancing decision-making and overcoming uncertainty. In order to help with future urban development planning, these models are essential for accurate management and control of urban expansion.  This article presents a comprehensive review of ML and DL models for urban prediction. The first step is a quick review of the many urban prediction models developed by various academics using ML and DL models.  The next step is to provide a new way for reliably projecting where cities will expand in the future by comparing current frameworks and determining their shortcomings