![Sample our Geography journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/5937/TOC-Subject-Sample-2021-Geography.jpg"})
ABSTRACT
Waterbody extraction from satellite imagery plays a crucial role in various environmental monitoring and management applications. Accurate identification and delineation of water bodies are essential for assessing water resources, monitoring changes in aquatic ecosystems, and supporting decision-making processes. This review presents a comprehensive analysis of different methods used for waterbody extraction from satellite images, highlighting their strengths, limitations, and recent advancements. This review begins by discussing traditional methods, such as thresholding-based methods, machine learning methods, and object-based image analysis, which have been widely employed in the past. Consequently, the focus shifts towards, how deep learning models, such as convolutional neural networks (CNNs) have been applied to improve waterbody extraction accuracy and address challenges posed by spectral variations, cloud cover, and sensor limitations. Overall, this review serves as a valuable resource for researchers, practitioners, and decision-makers involved in water resource management and environmental monitoring.
Disclosure statement
No potential conflict of interest was reported by the author(s).
Abbreviations
| The manuscript contains the following abbreviations (alphabetically listed): | = | |
| AMPSO | = | Adaptive Mutation Particle Swarm Optimization |
| ANDWI | = | Augmented Normalized Difference Water Index |
| AUC | = | Area Under the Curve |
| AWEI | = | Automatic Water Extraction Index |
| BOA | = | Boundary Overall Accuracy |
| CNN | = | Convolutional Neural Network |
| CRF | = | Conditional Random Field |
| DBO | = | Differential Bat Optimization |
| DLFC | = | Dense-Local-Feature-Compression |
| DNN | = | Deep Neural Networks |
| DT | = | Decision Tree |
| ETM | = | Enhanced Thematic Mapper |
| ELM | = | Extreme Learning machines |
| ESA | = | European Space Agency |
| FCN | = | Fully Convolutional Network |
| FWR | = | False Water Rate |
| GLCM | = | Grey Level Co-occurrence Matrix |
| HS | = | Hue Saturation |
| IEEE | = | Institute of Electrical and Electronics Engineers |
| IoU | = | Intersection over Union |
| ISPRS | = | International Society for Photogrammetry and Remote Sensing |
| KC | = | Kappa Coefficient |
| KNN | = | k-nearest neighbour |
| LiDAR | = | Light Detection and Ranging |
| LORSAL | = | Logistic Regression via Variable Splitting and Augmented Lagrangian |
| mIoU | = | Mean Intersection Over Union |
| mIoU | = | Mean Intersection over Union |
| MIoU | = | Mean Intersection over Union |
| MIR | = | Medium Infrared |
| MNDWI | = | Modified Normalized Difference Water Index |
| MS | = | Multi-scale extraction |
| MSR | = | Multi-Scale Residual Network |
| MC-WBDN | = | Multi-Channel Water Body Detection Network |
| MS-NLAC | = | Multi-Scale Nonlinear Active Contour |
| MWEN | = | Multi-scale Water Extraction Convolutional Neural Network |
| NASA | = | National Aeronautics and Space Administration |
| NDWI | = | Normalized Difference Water Index |
| NIR | = | Near Infrared |
| OA | = | Overall Accuracy |
| PCC | = | Percentage Correctly Classified |
| RADAR | = | Radio Detection and Ranging |
| RF | = | Random Forest |
| ROC | = | Receiver Operating Characteristics |
| RS | = | Remote Sensing |
| RR | = | Recurrent Refinement |
| RRF | = | Restricted Receptive Field |
| SAR | = | Synthetic Aperture Radar |
| SMA | = | Spectral Mixture Analysis |
| SSIM | = | Structural Similarity Index Measure |
| SVM | = | Support Vector Machine |
| SWIR | = | Shortwave Infrared |
| TWR | = | True Water Rate |
| USGS | = | United States Geological Survey |
| VH | = | Vertical-Horizontal |
| WIoU | = | Weighted Intersection over Union |
| WNDWI | = | Weighted Normalized Difference Water Index |
| WRI | = | Water Ratio Index |