Search

This article addresses the class imbalance problem in urban gain modelling (UGM) of Tabriz and Isfahan megacities in Iran by proposing novel cost-sensitive machine learning models, namely costsensitive support vector machine (CSVM), random forest (CRF) and artificial neural network (CANN). Random sampling, a frequently utilized method, fails to effectively tackle this issue by biasing models towards no change samples, which outnumber change samples. The results showed that CRF exhibited the highest accuracy (AUC = 0.560), followed by CANN (AUC = 0.557) and CSVM (AUC = 0.448) in Isfahan. In Tabriz, CRF (AUC = 0.809) and CANN (AUC = 0.818) excelled, outperforming balanced sampling models constructed with ANN, RF and SVM with the AUROC of ANN and RF boosted by 15% and 2% in validation. By emphasizing the significance of addressing class imbalance appropriately, this research highlights the improvement in modelling outcomes achievable through the cost-sensitive models especially in Tabriz case. [ABSTRACT FROM AUTHOR]

The data employed in urban gain modeling classes are often imbalanced, negatively affecting the accuracy of traditional and standard data mining and machine learning models. This study presents a new framework on the basis of clustering-based modeling and ensemble models to deal with the class imbalance problem in urban gain modeling. The random forest (RF), artificial neural network (ANN) and support vector machine (SVM) models served as the base models for the generation and evaluation of the results within this framework. The changes in urban land-use pattern of Isfahan in Iran in two time intervals of 1994-2004 and 2004-2014 were considered for the modeling. The findings showed that the proposed sampling strategy yields higher Hits and Correct Rejections rates than the strategies applied in previous studies in all three models. In the second part of the proposed framework (ensemble models), there was no substantial difference in the confusion matrix entries. [ABSTRACT FROM AUTHOR]

Abstract: One of the main factors of land use change (LUC) modeling is the land use intersection (LUI) or neighborhood effect, which is normally modeled using cellular automata (CA) concept. The effects of LUI over distance are represented in terms of CA transition rules. In this paper, a new model for LUI process is developed that makes use of expert knowledge to define the transition rules. In this model, the region of influence is defined using a new radial structure; the transition rules are described by expert knowledge and spatial metrics in the form of linguistic variables; and finally, the neighborhood effect is classified into three groups of compactness, dependency and incompatibility. The model is implemented and evaluated using the data of Borkhar and Meymeh township, in Esfahan, Iran, for the two periods of 1986–1998 and 1998–2005. The results show that the model and its related concept are performing rather well. [Copyright &y& Elsevier]