%0 Journal Article
%T A Comprehensive Review on the Development and Evolution of Urban Growth Models and Current Challenges
%A Manish Ratna Bhusal
%A Muhammad Atiq Ur Rehman Tariq
%A Chanulya Waruni Fonseka
%A Cheuk Yin Wai
%A Zohreh Rajabi
%J Current Urban Studies
%P 536-565
%@ 2328-4919
%D 2024
%I Scientific Research Publishing
%R 10.4236/cus.2024.123027
%X Prediction of urban growth is vital in planning for the future in terms of socio-economic indicators as well as ensuring growth of urban areas meet sustainability goals. The objective of this paper is to provide a comprehensive review on the evolution of various urban growth models and try to provide a narrative on why applicability and acceptability of such models remains limited. We explore and discuss the models since the first application in urban planning to currently used models. Through this discussion, analysis on reasons of evolution and improvement of these models has been done. Three popular models for urban growth modelling namely Cellular Automata (CA), Agent Based Model (ABM), and Artificial Neural Networks (ANN) have been described briefly. The explanation on why and how these models were improvised to better simulate urban growth has been discussed. The inefficiencies of these models as individual models and how integrated models have resolved these issues have been highlighted. This paper summarizes that evolution and development of models has mainly focused to improvise the model component inefficiencies and to reflect the true nature of growth. The inability of current urban growth models to incorporate policy scenarios as driving factors has been discussed and this has been highlighted as a reason for lack of global acceptability of such models. This paper thus recommends the application of different urban growth models based on the generalized objectives of modelling to enhance their credibility as well as bringing a uniformity in modelling approaches around globe.
%K Urban Growth Modelling
%K Land Use Change Modelling
%K Cellular Automata
%K Agent-Based Models
%K Neural Networks
%K Artificial Intelligence
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=136260