Urban Growth Models (UGMs) are very essential for a sustainable development of a city as they predict the future urbanization based on the presentscenario. Neural Network based Cellular Automata models have proved topredict the urban growth more close to reality. Recently, deep learning basedtechniques are being used for the prediction of urban growth. In this currentstudy, urban growth of Chennai Metropolitan Area (CMA) of 2017 was predicted using Neural Network based Cellular Automata (NN-CA) model andDeep belief based Cellular Automata (DB-CA) model using 2010 and 2013urban maps. Since the study area experienced congested type of urbangrowth, “Existing Built-Up” of 2013 alone was used as the agent of urbanization to predict urban growth in 2017. Upon validating, DB-CA model provedto be the better model, as it predicted 524.14 km2 of the study area as urbanwith higher accuracy (kappa co-efficient: 0.73) when compared to NN-CAmodel which predicted only 502.42 km2 as urban (kappa co-efficient: 0.71),while the observed urban cover of CMA in 2017 was 572.11 km2. This studyalso aimed at analyzing the effects of different types of neighbourhood configurations (Rectangular: 3 × 3, 5 × 5, 7 × 7 and Circular: 3 × 3) on the prediction output based on DB-CA model. To understand the direction and type ofthe urban growth, the study area was divided into five distance based zoneswith the State Secretariat as the center and entropy values were calculated forthe zones. Results reveal that Chennai Corporation and its periphery experience congested urbanization whereas areas away from the Corporationboundary follow dispersed type of urban growth in 2017.