Automatic recognition of environmental hazards in river and lake ecosystems using deep learning

Introduction Accurate identification of environmental issues in river and lake ecosystems is essential for the protection, management, and sustainable use of water resources. Traditional inspection-based approaches are limited by their extensive spatial scope, high labor demands, prolonged execution time, and increased likelihood of overlooking hazards. Methods To overcome these limitations, this study investigates intelligent methods for detecting environmental hazards in river and lake settings. Images representing 12 common types of water-related hazards were collected. Using image augmentation techniques, including rotation, transformation, and annotation, a dataset comprising over 1,500 samples of river and lake environmental hazards was constructed. An intelligent recognition model was then developed based on the YOLOv11 algorithm, incorporating transfer learning techniques to enable the detection of pollution categories, pollutant types, sewage outfalls, and shoreline encroachments. Results The experimental results demonstrate that, with adequate training data, appropriate categorization, and accurate annotation, the proposed method achieves reliable performance, yielding a balanced F1 score of 0.72. Discussion This approach can be deployed on devices such as smartphones, cameras, and unmanned aerial vehicles, offering practical tools for water pollution surveillance, shoreline monitoring, and the broader management of aquatic ecosystems.