Modelling built-up expansion and densification with multinomial logistic regression, cellular automata and genetic algorithm

Abstract

This is a repository copy of Modelling built-up expansion and densification with multinomial logistic regression, cellular automata and genetic algorithm.

Benefits of a multiple‐solution approach in land change models

“…The model allocates new urban cells based on a transition rule which has two components according to Wu () and Mustafa, Heppenstall et al (). The first component depends on a set of urbanization driving forces.…”

“…The assessment of different models depends on the quality of their outcomes, and therefore model calibration is a critical step in the construction of the model (van Vliet et al, ). Several methods have been proposed in the literature to calibrate spatial LC models, including a visual test (e.g., Clarke, Hoppen, & Gaydos, ; Ward, Murray, & Phinn, ), multi‐criteria evaluation (e.g., Mahiny & Clarke, ), reusing parameters from other studies (e.g., Mustafa, Saadi, Cools, & Teller, ), statistical analysis (e.g., García, Santé, Boullón, & Crecente, ), machine learning (e.g., Mileva, Suzana, Miloš, & Branislav, ), artificial neural networks (e.g., Basse, Omrani, Charif, Gerber, & Bódis, ; Pijanowski et al, ), and search algorithms for optimization such as genetic algorithms (e.g., Mustafa, Heppenstall et al, ), particle swarm optimization (e.g., Feng, Liu, Tong, Liu, & Deng, ), and a combination of various methods (e.g., Mustafa, Cools, Saadi, & Teller, ). Although there is no standard calibration method, statistical analysis is one of the most frequently applied calibration approaches (van Vliet et al, ).…”

“…They have already been successfully applied to many LC models (e.g., Al‐Ahmadi, See, Heppenstall, & Hogg, ; García et al, ; Liu et al, ). Pareto front methods are often integrated with GAs to illustrate the trade‐off among conflicting optimization objectives, which assists in optimizing the allocation of different, conflicting, land uses simultaneously (Mustafa, Heppenstall et al, ). A typical GA consists of a genetic representation of the problem space, an objective function to evaluate each candidate solution, and selection, crossover, and mutation operators.…”

“…Many LC models use an independent validation process such that the data used in the validation is different from the data used in the model calibration, by covering different time periods. For example, Mustafa, Heppenstall et al () calibrated their LC model using data for the 1990–2000 reference period and the calibration results were subsequently used to validate the model performance using 2000–2010 data. When divergent sets of spatial parameters are identified during the calibration of the LC model, these can be tested at the validation stage.…”

Examining the Relationship between Urban Land Expansion and Economic Linkage Using Coupling Analysis: A Case Study of the Yangtze River Economic Belt, China

“…In addition, some studies have argued that regional urban land expansion could impact regional carbon storage. Models have been used to simulate urban land expansion, considering the factors of intra-urban social segregation and the potential for densification within already urban land areas when their present density allows it [17][18][19]. Moreover, some externalities and features of the dynamic evolution of economic activities have an impact on ULE.…”