Earth-rock dams are critical components of hydraulic engineering, undertaking core functions such as flood control and disaster mitigation. However, the potential occurrence of dam breach poses a severe threat to regional socioeconomic stability and ecological security. To address the limitations of traditional Bayesian network (BN) in capturing the complex nonlinear coupling and dynamic mutual interactions among risk factors, they are integrated with machine learning techniques, based on a collected dataset of earth-rock dam breach case samples, the PC structure learning algorithm was employed to preliminarily uncover risk associations. The dataset was compiled from public databases, including the U.S. Army Corps of Engineers (USACE) and Dam Safety Management Center of the Ministry of Water Resources of China, as well as engineering reports from provincial water conservancy departments in China and Europe. Expert knowledge was integrated to optimize the network topology, thereby correcting causal relationships inconsistent with engineering mechanisms. The results indicate that the established hybrid model achieved AUC, accuracy, and F1-Score values of 0.887, 0.895, and 0.899, respectively, significantly outperforming the data-driven model G1. Forward inference identified the key drivers elevating breach risk. Conversely, backward inference revealed that overtopping was the direct failure mode with the highest probability of occurrence and the greatest contribution. The integration of data-driven approaches and domain knowledge provides theoretical and technical support for the probabilistic quantification of earth-rock dam breach and risk prevention and control decision-making.

As dams age, operating costs increase and associated risks intensify. Addressing the mechanisms influencing dam economic life is crucial for accurate assessment and operation management. Dam economic life is affected by social and ecological environmental factors, whose types, relationships, and influence degree vary over time. In this study, influencing factors were identified across five dimensions: safety, cost, benefit, social impact, and ecological and environmental impact. Using the Random Forest method, the interaction degrees among individual factors were analyzed. Using on Markov theory, the Decision-making Trial and Evaluation Laboratory (DEMATEL) method, and the Interpretative Structural Modeling Method (ISM), a time-varying analysis model was constructed to reveal the mechanisms of these influencing factors. The model was applied to the Luhun Reservoir in Luoyang City, Henan Province, China. Results showed that during the first 20 years of dam operation, factors such as total reservoir capacity and management level considerably affected dam economic life. Over the next 20 years, total reservoir capacity and population protection became the dominant factors. Dam economic life can be extended using management measures, including improving storage capacity utilization, enhancing silt control, and increasing flood control storage capacity.