Landslide dams have a high risk of overtopping failure compared to that of artificial dams. In this study, based on dam morphological characteristics, field investigations, and model tests, a numerical calculation method for overtopping-induced landslide dam breach is proposed. Highlights of the method include consideration of surface erosion rather than headcut erosion as well as a wide variety of dam deposits used to simulate the dam breach process. Variations in soil erodibility with depth as well as erosion mode (one- and two-sided breach) are also considered in the proposed dam breach model. Two landslide dam breaches, Tangjiashan and Xiaogangjian, are examined as case studies to test the proposed model. A comparison of the calculated and measured results shows that the relative errors in peak discharge, final breach width, and time to peak of the two breach cases are all within $\pm 10\%$ . Sensitivity analysis shows that the aforementioned parameters are more or less sensitive to soil erodibility and erosion mode, with soil erodibility being more important than erosion mode. Three other typical landslide dam breach models are compared to the proposed model for the Tangjiashan landslide dam case. All four models can reasonably simulate the breach process, but the proposed model has the smallest relative errors.

The safety monitoring information of the dam is an indicator reflecting the operational status of the dam. It is a crucial source for analyzing and assessing the safety state of reservoir dams, possessing strong real-time capabilities to detect anomalies in the dam at the earliest possible time. When using neural networks for predicting and warning dam safety monitoring data, there are issues such as redundant model parameters, difficulty in tuning, and long computation times. This study addresses real-time dam safety warning issues by first employing the Empirical Mode Decomposition (EMD) method to decompose the effective time-dependent factors and construct a dam in a service state analysis model; it also establishes a multi-dimensional time series analysis equation for dam seepage monitoring. Simultaneously, by combining the Sparrow Optimization Algorithm to optimize the LSTM neural network computation process, it reduces the complexity of model parameter selection. The method is compared to other approaches such as RNN, GRU, BP neural networks, and multivariate linear regression, demonstrating high practicality. It can serve as a valuable reference for reservoir dam state prediction and engineering operation management.

Reservoir dams are mostly built in alpine valley areas. The water surface of the river valley is narrow and the geometric features of hydraulic structures are complex, which result in different absorption, reflection, and diffraction effects on sound waves for various propagation media. Further, for relatively narrow underwater water space where the underwater detection equipment is located, there is significant interference to the underwater acoustic communication signal. This is a major challenge to underwater positioning technology. Therefore, in this study, the scattering effect of different markers placed on a dam face on the sound waves emitted by sonar carried by a remote control unmanned submersible in a reservoir environment was investigated. The singular boundary method was used to develop a simulation model of the scattering effect on the sound waves of three different markers (i.e., cross boards, spherical bodies, and square plates) placed on a dam face in the deepwater environment of a reservoir. The scattering effect of typical geometrical markers was also investigated with respect to the sound waves of different frequencies and different incident angles. The sound pressure level (SPL) was used as an indicator for determining the scattering effect, so that the geometry of the marker with well scattering effect could be determined. In this study, the Guanyinyan hydropower dam was considered as the research area. The results show that the scattering SPL of the cross board is higher than those of the spherical body and the square plate, i.e., using the cross board as a marker produces the most accurate positioning of the underwater detection remote control unmanned submersible of a dam project in the deepwater environment of a reservoir.

Detecting underwater structural defects is vital for hydraulic engineering safety. Diverse patterns of underwater structural defects, i.e., the morphology and scale characteristics, pose difficulties on feature representability during detection. Any single feature morphology is insufficient to fully characterize diverse types of underwater defect patterns. This paper proposes a novel hybrid neural network to enhance feature representation of underwater structural multi-defects, which in turn improves the accuracy and adaptability of underwater detection. Three types of convolution operations are combined to build Hybrid Aggregation Network (HanNet), enhancing the morphological representation for diverse defects. Considering the scale difference of diverse defects, the Multi-Scale Shared Feature Pyramid (MSFP) is proposed, facilitating adaptive representation for diverse sizes of structural defects. The defect detection module leverages an Adaptive Spatial-Aware Attention (ASAA) at the backend, enabling selective enhancement of salient defect features. For model training and evaluation, we, for the first time, build an underwater structural multi-defects sonar image dataset containing a wide range of typical defect types. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods, significantly improving defect detection accuracy, and provides an effective solution for detecting diverse structural defects in complex underwater environments.

In recent years, underwater image super-resolution (SR) reconstruction has increasingly become a core focus of underwater machine vision. Light scattering and refraction in underwater environments result in images with blurred details, low contrast, color distortions, and multiple visual artifacts. Despite the promising results achieved by deep learning in underwater SR tasks, global and frequency-domain information remain poorly addressed. In this study, we introduce a novel underwater SR method based on the Vision State-Space Model, dubbed MambaUSR. At its core, we design the Frequency State-Space Module (FSSM), which integrates two complementary components: the Visual State-Space Module (VSSM) and the Frequency-Assisted Enhancement Module (FAEM). The VSSM models long-range dependencies to enhance global structural consistency and contrast, while the FAEM employs Fast Fourier Transform combined with channel attention to extract high-frequency details, thereby improving the fidelity and naturalness of reconstructed images. Comprehensive evaluations on benchmark datasets confirm that MambaUSR delivers superior performance in underwater image reconstruction.

Underwater crack detection in dam structures is of significant importance to ensure structural safety, assess operational conditions, and prevent potential disasters. Traditional crack detection methods face various limitations when applied to underwater environments, particularly in high dam underwater environments where image quality is influenced by factors such as water flow disturbances, light diffraction effects, and low contrast, making it difficult for conventional methods to accurately extract crack features. This study proposes a dual-stage underwater crack detection method based on Cycle-GAN and YOLOv11 called Edge-Enhanced Underwater CrackNet (E²UCN) to overcome the limitations of existing image enhancement methods in retaining crack details and improving detection accuracy. First, underwater concrete crack images were collected using an underwater remotely operated vehicle (ROV), and various complex underwater environments were simulated to construct a test dataset. Then, an improved Cycle-GAN image style transfer method was used to enhance the underwater images. Unlike conventional GAN-based underwater image enhancement methods that focus on global visual quality, our model specifically constrains edge preservation and high-frequency crack textures, providing a novel solution tailored for crack detection tasks. Subsequently, the YOLOv11 model was employed to perform object detection on the enhanced underwater crack images, effectively extracting crack features and achieving high-precision crack detection. The experimental results show that the proposed method significantly outperforms traditional methods in terms of crack detection accuracy, edge clarity, and adaptability to complex backgrounds, effectively improving underwater crack detection accuracy (precision = 0.995, F1 = 0.99762, mAP@0.5 = 0.995, and mAP@0.5:0.95 = 0.736) and providing a feasible technological solution for intelligent inspection of high dam underwater cracks.