Search

Managing water resources amidst the pressures of climate change and human activities is a significant challenge, especially in regions experiencing shrinking lakes, deteriorating water quality, and ecological degradation. This review focuses on achieving integrated river basin management by learning from the governance experiences of typical watersheds globally, using the Hulun Lake Basin as a case study. Hulun Lake, China’s fifth-largest lake, experienced severe ecological problems from 2000 to 2009 but saw improvements after comprehensive management efforts from 2012 onward. This review systematically explores methods to address water resource, environment, and ecological challenges through the lenses of data acquisition, mechanism identification, model simulation, and regulation and management. Drawing lessons from successful basins such as the Rhine, Ganges, Mississippi, and Murray–Darling, the review proposes key goals for comprehensive management, including establishing extensive monitoring networks, developing predictive models, and creating contingency plans for routine and emergency management. Leveraging advanced technologies like satellite imagery and IoT sensors, alongside continuous improvement mechanisms, will ensure the sustainable use and protection of river basins. This review provides a detailed roadmap for achieving comprehensive watershed management in Hulun Lake, summarizing effective strategies and outcomes from data acquisition to regulation, thus serving as a model for similar regions globally.

ABSTRACTTimely and accurate wetland information is necessary for wetland resource management. Recent advances in machine learning and remote sensing have facilitated cost-effective monitoring of wetlands. However, reliable methods for fine-grained and rapid wetland mapping are still lacking. To address the issue, a wetland sample set with 20 categories for China was collected based on a sampling strategy that combines automatic sample generation and visual interpretation. Simultaneously, a novel multi-stage method for fine-grained wetland classification was proposed, which integrates pixel-based and object-based strategies using ensemble learning algorithms and multi-source remote sensing data. First, a pixel-based ensemble learning algorithm was implemented to classify five rough wetland categories and six non-wetland categories. Second, an object-based ensemble learning approach was designed to separate the water cover in the pixel-based classification results into eight detailed categories. Third, the merged pixel-based and object-based classification results were refined with knowledge-based post-processing procedures to identify 14 fine-grained wetland categories. Results using the Pixel Information Expert Engine (PIE-Engine) cloud platform proved the effectiveness of the proposed wetland classification method. The overall accuracy, kappa, and weighted F1 reached 87.39%, 82.80%, and 86.02%, respectively. The adopted ensemble learning algorithm yielded better performance than classifiers such as CatBoost, random forest, and XGBoost. The incorporation of spectral, texture, shape, topographic, and geographic features from multi-source data contributed to differentiating wetland categories. According to the relative contribution, spectral indexes (NDVI and NDWI), texture features (sum average and contrast), and topographic features (slope and elevation) were identified as important leading predictors for the first-stage pixel-based classification. Shape features (shape index and compactness) and auxiliary features (geographic location) were crucial predictors for the second-stage object-based classification. Compared with other products, our 10-m wetland mapping results for national wetland reserves were rich in detail and fine in categories. Overall, the constructed sample set and developed classification method show promise in laying a foundation for large-scale wetland mapping. The derived wetland maps can provide support for wetland protection and restoration.