Comparison of Urban Growth Modeling Using Deep Belief and Neural Network Based Cellular Automata Model—A Case Study of Chennai Metropolitan Area, Tamil Nadu, India

Abstract

Urban Growth Models (UGMs) are very essential for a sustainable development of a city as they predict the future urbanization based on the present scenario. Neural Network based Cellular Automata models have proved to predict the urban growth more close to reality. Recently, deep learning based techniques are being used for the prediction of urban growth. In this current study, urban growth of Chennai Metropolitan Area (CMA) of 2017 was predicted using Neural Network based Cellular Automata (NN-CA) model and Deep belief based Cellular Automata (DB-CA) model using 2010 and 2013 urban maps. Since the study area experienced congested type of urban growth, "Existing Built-Up" of 2013 alone was used as the agent of urbanization to predict urban growth in 2017. Upon validating, DB-CA model proved to be the better model, as it predicted 524.14 km 2 of the study area as urban with higher accuracy (kappa coefficient: 0.73) when compared to NN-CA model which predicted only 502.42 km 2 as urban (kappa coefficient: 0.71), while the observed urban cover of CMA in 2017 was 572.11 km 2. This study also 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 of the urban growth, the study area was divided into five distance based zones with the State Secretariat as the center and entropy values were calculated for the zones. Results reveal that Chennai Corporation and its periphery experience congested urbanization whereas areas away from the Corporation boundary follow dispersed type of urban growth in 2017. How to cite this paper: Aarthi, A.D. and Gnanappazham, L.

Invited perspectives: How machine learning will change flood risk and impact assessment

“…These models assign cells as either urban or non-urban based on specific transition rules. Determining the optimum transition rules is a critical issue for CA modelling (Aarthi and Gnanappazham, 2019). This is sometimes difficult because of human bias, heterogeneity and non-linear relations between driving factors and urban expansion (Naghibi et al, 2016;Xu et al, 2019).…”

“…This is sometimes difficult because of human bias, heterogeneity and non-linear relations between driving factors and urban expansion (Naghibi et al, 2016;Xu et al, 2019). To overcome these limitations, machine learning algorithms such as artificial neural networks have been integrated with traditional CA to model urban growth (Aarthi and Gnanappazham, 2019;Naghibi et al, 2016). They then use historical land-use changes (e.g.…”

Invited perspectives: How machine learning will change flood risk and impact assessment

“…These models assign cells as either urban or non-urban based on specific transition rules. Determining the optimum transition rules is a critical issue for CA modelling (Aarthi and Gnanappazham, 2019). This is sometimes difficult because of human bias, heterogeneity and nonlinear relations between driving factors and urban expansion (Naghibi et al, 2016;Xu et al, 2019).…”

“…This is sometimes difficult because of human bias, heterogeneity and nonlinear relations between driving factors and urban expansion (Naghibi et al, 2016;Xu et al, 2019). To overcome these limitations, machine learning algorithms such as artificial neural networks have been integrated with traditional CA to model urban growth (Aarthi and Gnanappazham, 2019;Naghibi et al, 2016). They then use historical land-use changes (e.g.…”

Macro-level estimation of present and future seismic loss by modelling spatio-temporal dynamics of exposure

“…Artificial neural networks have a black box nature, and sometimes create overcomplex structures which result in over-fitting (Almeida et al, 2008). Determining the optimum transition rules is a challenging issue for cellular automata models (Aarthi and Gnanappazham, 2019). Genetic algorithms were observed to be computationally intensive for solution of small-scale problems (Naghibi et al, 2016).…”