Modeling urban regions: Comparing random forest and support vector machines for cellular automata

Abstract

Cellular automat​on (CA) are important tools that provide insight into urbanization dynamics and possible future patterns. The calibration process is the core theme of these models. This study compares the performance of two common machine‐learning classifiers, random forest (RF), and support vector machines (SVM), to calibrate CA. It focuses on the sensitivity analysis of the sample size and the number of input variables for each classifier. We applied the models to the Wallonia region (Belgium) as a case study to demonstrate the performance of each classifier. The results highlight that RF produces a land‐use pattern that simulates the observed pattern more precisely than SVM especially with a low sample size, which is important for study areas with low levels of land‐use change. Although zoning information notably enhances the accuracy of SVM‐based probability maps, zoning marginally influences the RF‐derived probability maps. In the case of the SVM, the CA model did not significantly improve due to the increased sample size. The performance of the 5,000 sample size was observed to be better than the 15,000 sample size. The RF‐driven CA had the best performance with a high sample, while zoning information was excluded.

Integrating a deep forest algorithm with vector‐based cellular automata for urban land change simulation

“…Compared to the forest model (RF), ANN cannot extract diversified conversion rules accurately (Zhai et al., 2020). The RF model can efficiently mine the conversion rules of land‐use changes in different regions, which several previous studies have confirmed (Kamusoko & Gamba, 2015; Rienow et al., 2021; Yao et al., 2017; Zhang, Liu, et al., 2019). The DF algorithm is an ensemble of forests with characteristics of in‐model feature transformation, level‐by‐level processing, and sufficient adaptive model complexity (Zhou & Feng, 2019).…”

“…The natural environmental conditions, such as elevation and slope, which restrict the use of land parcels, were chosen as driving factors of urban land change (Rienow, Mustafa, Krelaus, & Lindner, 2021). The geometry attributes of land parcels may influence urban land‐use change were also considered in urban land‐use change, including the area, perimeter, and shape of land parcels.…”

“…Compared to the forest model (RF), ANN cannot extract diversified conversion rules accurately (Zhai et al, 2020). The RF model can efficiently mine the conversion rules of land-use changes in different regions, which several previous studies have confirmed (Kamusoko & Gamba, 2015;Rienow et al, 2021;Yao et al, 2017;.…”

Land-Use Change Prediction in Dam Catchment Using Logistic Regression-CA, ANN-CA and Random Forest Regression and Implications for Sustainable Land–Water Nexus

“…In applying the different LULC change prediction models, ref [50] utilized hybrid LR-MC-CA and obtained an accuracy of 89% between simulated and actual land use for case study of Tehran. For urban growth modeling, ref [51] employed RF-CA and SVM-CA models which exhibited a high certainty for modeling complex urban growth in the Wallonia region (Belgium). For forecasting LULC change in Attica (Greece), ref [52] applied RF-CA with notably high overall accuracy of 88.4%.…”

On the spatiotemporal generalization of machine learning and ensemble models for simulating built‐up land expansion

“…Integration of machine learning models and cellular automata (CA) is a typical approach to simulate urban growth (Rienow & Goetzke, 2015; Rienow, Mustafa, Krelaus, & Fragkias, 2021; Shafizadeh‐Moghadam, 2019). Over the past three decades, simulating LULC changes using CA has gained increasing popularity among scholars (Gounaridis, Chorianopoulos, Symeonakis, & Koukoulas, 2019; Mirbagheri & Alimohammadi, 2018; Munshi, Zuidgeest, Brussel, & Van Maarseveen, 2014; Rienow & Goetzke, 2015).…”