|
| Ref. | Approaches | Datasets | Accuracy |
|
| Kantakumar et al. [149] | Maximum likelihood supervised, decision tree, and ISODATA clustering technique | Landsat-8’s dataset for dry period and wet period | Dry: 84.54%; wet: 91.10% |
| Nguyen et al. [11] | Fuzzy C-means clustering and multiple kernel interval-valued fuzzy C-means clustering | LANDSAT-7 Ba Ria area and Hanoi area | 98.2% and 94.13% |
| Qayyum et al. [150] | DRT hybrid dictionary with Ricker wavelet function | UAS operating system recorded data for nearly 2 h without flight interruptions | 85.70% |
| Zhang et al. [151] | CNN and MLP (multilayer perceptron) | Urban and rural scenes of aerial imagery of Southampton | 90.93% for urban and 89.64% for rural |
| Nijhawan et al. [152] | Hybrid of CNN integrated with handcrafted (LBP + GIST) features | Satellite images of Uttarakhand, northern part of India | 88.43% |
| Prasad et al. [153] | Landsat-8 satellite images | SVM and ANN | SVM: 93.15%; ANN:89.92% |
| Yang et al. [154] | UAV images of rice fields in Chianan Plain and Taibao City, Chiayi County | DSM and texture information | 90.67% |
| Alimjan et al. [148] | SVM and KNN | DS-1: ALOS data of the Yitong River in Changchun
DS-2: the ortho image of a factory region in Jiangsu Province | DS-1: 92.4%; DS-2: 97.9% |
| Akshya et al. [155] | SVM and K-means | A dataset containing 200 flooded and non-flooded images | 92% |
| Hua et al. [156] | Class-wise attention-based convolutional and bidirectional LSTM network | UCM and DFC15 multilabel datasets | |
| Schuegraf et al. [157] | U-Net on top of the Caffe deep learning framework | World View-2 imagery of Munich, Germany | 97.40% |
|
