Abstract
Abstract. The importance of spatial accuracy of land use/cover change maps necessitates the use of high performance models. To reach this goal, calibrating machine learning (ML) approaches to model land use/cover conversions have received increasing interest among the scholars. This originates from the strength of these techniques as they powerfully account for the complex relationships underlying urban dynamics. Compared to other ML techniques, random forest has rarely been used for modeling urban growth. This paper, drawing on information from the multi-temporal Landsat satellite images of 1985, 2000 and 2015, calibrates a random forest regression (RFR) model to quantify the variable importance and simulation of urban change spatial patterns. The results and performance of RFR model were evaluated using two complementary tools, relative operating characteristics (ROC) and total operating characteristics (TOC), by overlaying the map of observed change and the modeled suitability map for land use change (error map). The suitability map produced by RFR model showed 82.48% area under curve for the ROC model which indicates a very good performance and highlights its appropriateness for simulating urban growth.
Highlights
Around 2% or 3% of the Earth’s land surface is covered by urban land (Poelmans and van Rompaey 2010)
The spatial accuracy of urban change simulation map is of great importance to urban planners and policy makers which highlights the importance of developing more accurate models
On the basis of the extracted land use classes from the Landsat imageries, random forest regression (RFR) model was calibrated for modeling and understanding the importance of urban growth factors
Summary
Around 2% or 3% of the Earth’s land surface is covered by urban land (Poelmans and van Rompaey 2010). Information with respect to the intensity and future direction of urban expansion is of great importance for urban planners, policy makers and scholars. In this regard, using satellite images to monitor, identify and analyze urban expansion is the initial step. A number of statistical (e.g., logistic regression and auto-logistic regression) and machine learning approaches (e.g., neural networks and support vector machines) have been calibrated and developed for modelling urban dynamics Kamusoko and Gamba (2015) compared the random forest-cellular automata (RF-CA) with support vector machine cellular automata (SVM-CA) and logistic regression cellular automata (LR-CA) models for Relaxation of normal distribution assumption, robustness to over-fitting, less required training time and providing information regarding variable importance are the main characteristics of this method. Kamusoko and Gamba (2015) compared the random forest-cellular automata (RF-CA) with support vector machine cellular automata (SVM-CA) and logistic regression cellular automata (LR-CA) models for
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
