Comparison of Machine Learning Classifiers for Multitemporal and Multisensor Mapping of Urban Lulc Features

Abstract

Abstract. This study compares four machine-learning algorithms comprising of Classification And Regression Trees (CART), Random Forest (RF), Gradient Tree Boosting (GTB) and Support Vector Machine (SVM) for the classification of urban land-use and land-cover (LULC) features. Using multitemporal and multisensor Landsat data from 1984-2020 at 5-year intervals for the Greater Gaborone Planning Area (GGPA) in Botswana, the aim of the study is to determine the performance of the classifiers in the extraction of different urban LULC features as built-up, bare-soil, water, grass, shrubs and forest. The results show that for mapping built-up areas, RF and SVM presented the best results with overall accuracy of 85%. Bare soil is best mapped using RF and CART with accuracy of up to 98%, while SVM and GTB were most suitable for mapping water bodies. The suitable classifiers for mapping the vegetation classes were RF for grass (94.5%), SVM for shrubland (81.5%) and GTB for forest (84.3%). In terms of class specific accuracy, RF achieved the highest performance with average overall accuracy (OA) of 95.9%, SVM (95.8%), GTB (95.6%) and CART (95.1%). The same performance pattern was observed from the F1-score, True Positive Rate (TPR), False Positive Rate (FPR) and Area under ROC curve (AUC) metrices for the class classification accuracies. The overall accuracy for the eight-epoch years were RF (87.8%), SVM (87.5%), GTB (86.4%) and CART (85.3%). To improve on the urban LULC mapping, the study proposes the post-classification feature fusion of the best classifier results.

Comparison of Three Machine Learning Algorithms Using Google Earth Engine for Land Use Land Cover Classification

“…RF classifier distinguished vegetation from other classes of LULC more accurately than SVM and CART algorithms. RF and CART algorithm performance is better than SVM for built mapping of LULC because SVM underestimates the urban region ( Ouma et al 2022 ). In the present study, we observed the same trend that RF and CART classifiers had performed well in mapping the built class of the study area while SVM confused it with bare soil.…”

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

“…RFC minimizes the classification overfitting problem and increases the class prediction accuracy and control. As such, the RFC learning model with multiple decision trees is typically more accurate than a single decision-tree-based model, especially in detecting different LULC classes [70,71]. The overall advantage of RFC is that it can produce stable and accurate results even with minimal tuning of the hyperparameters.…”

Dual Path Attention Network (DPANet) for Intelligent Identification of Wenchuan Landslides

“…To evaluate the experimental results objectively, four evaluation metrics, including pixel accuracy (PA), overall classification accuracy (OA), recall (Recall), and F1 score [55,56], are selected in this paper to measure the performance of the different baseline models in the landslide recognition task to select the most suitable recognition model. PA is the proportion of the number of pixels that are true landslides among all of the pixels that were predicted to be landslides.…”