Machine learning for urban land use/ cover mapping: Comparison of artificial neural network, random forest and support vector machine, a case study of Dilla town

Melion Kasahun; Abiyot Legesse

doi:10.1016/j.heliyon.2024.e39146

Machine learning for urban land use/ cover mapping: Comparison of artificial neural network, random forest and support vector machine, a case study of Dilla town

Heliyon. 2024 Oct 12;10(20):e39146. doi: 10.1016/j.heliyon.2024.e39146. eCollection 2024 Oct 30.

Authors

Melion Kasahun^{1

2}, Abiyot Legesse¹

Affiliations

¹ Department of Geography and Environmental Studies, College of Social Science and Humanities, Dilla University, P.O. Box: 419, Dilla, Ethiopia.
² Department of Geography and Environmental Studies, College of Social Science and Humanities, Borana University, P.O. Box: 85, Yabello, Ethiopia.

Abstract

The ability to accurately classify land use/cover (LULC) is critical for environmental monitoring and land use planning. This study compares three machine learning algorithms: Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) for LULC classification using Google Earth images from the years 2006, 2014, and 2022. The objective of this study is to evaluate and identify the best classifier for LULC classification and change detection. Four LULC categories (Built-up, Open area, Farmland, and Agroforestry) were identified. The evaluation criteria included overall accuracy, kappa coefficient, producer's accuracy, user's accuracy, computing time, algorithm stability, and visual quality. The results showed that the RF algorithm outperformed both SVM and ANN algorithms with an average overall accuracy of 0.97, kappa coefficient of 0.98, producer's accuracy of 0.99, and user's accuracy of 0.97, surpassing the accuracies achieved by SVM (0.96, 0.97, 0.98, and 0.97) and ANN (0.89, 0.81, 0.94, and 0.88), with corresponding computing times of 6.33, 15, and 30 s. All classifiers performed stably with different training sizes. Visual quality assessment revealed that RF had the highest precision. Consequently, the built-up change detection result shows, the net change in built-up area between 2006 and 2022 was increased by 0.74 Km² for ANN, 1.74 Km2 for SVM, and 1.66 Km² for RF. The comparison reveals that the RF algorithm showcasing high precision in detecting change, consistent with the data (increased by 1.65 Km² ) obtained from Dilla town land administration office. To validate the results, the study considered field surveys, reference images, local experts, and previous studies. Based on the findings, the study concludes that using RF classifier with an object-based approach is an effective way to map LULC and detect changes in the study area over time. Future researchers are recommended to utilize this effective algorithm for addressing LULC related problems in the study area.

Keywords: ANN; Accuracy assessment; Algorithm stability; Computing time; LULC; RF; SVM; Visual quality.