Cellular automata model based on machine learning methods for simulating land use change

This paper presents an approach combining machine learning (ML), cross-validation methods and cellular automata (CA) model for simulating land use changes in Luxembourg and the areas adjacent to its borders. Throughout this article, we emphasize the interest in using ML methods as a base of CA model transition rule. The proposed approach shows promising results for prediction of land use changes over time. We validate the various models using cross-validation technique and Receiver Operating Characteristic (ROC) curve analysis, and compare the results with those obtained using a standard logit model. The application described in this paper highlights the interest of integrating ML methods in CA based model for land use dynamic simulation.