With global climate change and the deterioration of the ecological environment, the safety of hydraulic engineering faces severe challenges, among which soil-dwelling termite damage has become an issue that cannot be ignored. Reservoirs and embankments in China, primarily composed of earth and rocks, are often affected by soil-dwelling termites, such as Odontotermes formosanus and Macrotermes barneyi. Identifying soil-dwelling termite damage is crucial for implementing monitoring, early warning, and control strategies. This study developed an improved YOLOv8 model, named MCD-YOLOv8, for identifying traces of soil-dwelling termite activity, based on the Monte Carlo random sampling algorithm and a lightweight module. The Monte Carlo attention (MCA) module was introduced in the backbone part to generate attention maps through random sampling pooling operations, addressing cross-scale issues and improving the recognition accuracy of small targets. A lightweight module, known as dimension-aware selective integration (DASI), was added in the neck part to reduce computation time and memory consumption, enhancing detection accuracy and speed. The model was verified using a dataset of 2096 images from the termite damage survey in hydraulic engineering within Hubei Province in 2024, along with images captured by drone. The results showed that the improved YOLOv8 model outperformed four traditional or enhanced models in terms of precision and mean average precision for detecting soil-dwelling termite damage, while also exhibiting fewer parameters, reduced redundancy in detection boxes, and improved accuracy in detecting small targets. Specifically, the MCD-YOLOv8 model achieved increases in precision and mean average precision of 6.4% and 2.4%, respectively, compared to the YOLOv8 model, while simultaneously reducing the number of parameters by 105,320. The developed model is suitable for the intelligent identification of termite damage in complex environments, thereby enhancing the intelligent monitoring of termite activity and providing strong technical support for the development of termite control technologies.

Intense precipitation infiltration and intricate excavation processes are crucial factors that impact the stability and security of towering and steep rock slopes within mining sites. The primary aim of this research was to investigate the progression of cumulative failure within a cracked rock formation, considering the combined effects of precipitation and excavation activities. The study was conducted in the Huangniuqian eastern mining area of the Dexing Copper Mine in Jiangxi Province, China. An engineering geological investigation was conducted, a physical model experiment was performed, numerical calculations and theoretical analysis were conducted using the matrix discrete element method (MatDEM), and the deformation characteristics and the effect of the slope angle of a fractured rock mass under different scenarios were examined. The failure and instability mechanisms of the fractured rock mass under three slope angle models were analyzed. The experimental results indicate that as the slope angle increases, the combined effect of rainfall infiltration and excavation unloading is reduced. A novel approach to simulating unsaturated seepage in a rock mass, based on the van Genuchten model (VGM), has been developed. Compared to the vertical displacement observed in a similar physical experiment, the average relative errors associated with the slope angles of 45 degrees, 50 degrees, and 55 degrees were 2.094%, 1.916%, and 2.328%, respectively. Accordingly, the combined effect of rainfall and excavation was determined using the proposed method. Moreover, the accuracy of the numerical simulation was validated. The findings contribute to the seepage field in a meaningful way, offering insight that can inform and enhance existing methods and theories for research on the underlying mechanism of ultra-high and steep rock slope instability, which can inform the development of more effective risk management strategies. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).