“…The comparison demonstrated that all methods are very accurate (more than 90% of accuracy); however, the two-step method achieved the best results [147] Land change Proposed an unsupervised method with an OB approach to improve the detection of changes using high-resolution images. This methodology achieved better results in comparison to other methods [148] SGD 15 (Life on Land) Invasive plants Developed an unsupervised method to detect and map invasive plants using RFs, which proved to be a successful approach [149] Landslide Compared an unsupervised PB and OB approach for landslide detection using VHR images and concluded that OB performed better than PB [150] Land cover Compared four OB classifiers for the classification of a suburban area with data provided by Landsat-8 and proved that SVM had the best performance among all [151] Land use Proposed OB approach for urban land use classification using VHR images [152] SGD 15 (Life on Land) Land cover Tested the performance of PB and OB classification with a hyperspectral dataset and found that OB was better than PB approach [153] Land use Compared an OB and PB approach using aero photogrammetric images and the results showed that OB classifier performed better compared to PB [154] Disasters and Renewable Energy; the Regression category covers the SDGs 2, 3, 6, 7, 9, 11, 13, 14 and 15, and the fields Water Quality, Pollution and Freshwater; and the Dimension Reduction category covers the SDGs 3, 6, 7, 9, 11, 13 and 15, and the fields Land Cover, Electricity and Software. Thus, the overall findings confirm the significance of EO and ML in pursuing the goals of SD providing an overview of methods and techniques that sustain the achievement of SDGs.…”