Hang Lin

Estimation of Rock Shear Strength Parameters from Geophysical Indicators Using an Equilibrium-Optimized Multilayer Perceptron

Accurate and scalable estimation of rock shear strength parameters is essential for remote-sensing-supported geological hazard assessment, slope stability evaluation, and engineering geological mapping. However, determining cohesion and internal friction angle requires multiple triaxial tests under different confining pressures, which are time-consuming, costly, and difficult to apply widely. To support remote-sensing-oriented geoscience and civil engineering applications, this study develops a hybrid machine learning framework for estimating cohesion and internal friction angle from geophysical and mechanical indicators. A cross-source database was compiled from published rock records collected from the Jinchuan mining area in China and the Luhri area in India. After completeness screening and unit harmonization, 213 mixed-lithology cases were retained for modeling, with P-wave velocity, density, uniaxial compressive strength, and tensile strength used as input variables. An Equilibrium Optimizer was coupled with a multilayer perceptron to optimize the network weights and biases, and model performance was evaluated using five-fold cross-validation, independent testing, repeated runs, and comparisons with conventional MLP and several typical machine learning models. The proposed EO–MLP model achieved high prediction accuracy, with test-set coefficient of determination values of 0.946 for internal friction angle and 0.983 for cohesion and corresponding RMSE values of 1.072 and 0.671, respectively. Robust scaler normalization produced the best performance among the three tested normalization strategies. SHapley Additive exPlanations analysis indicated that density was the dominant predictor of cohesion, whereas uniaxial compressive strength and P-wave velocity made the largest contributions to internal friction angle prediction. The proposed framework provides an indirect data-driven tool for estimating shear strength parameters and can complement engineering-geological investigation and rock engineering design.

Transmission of Seismic Waves With Tensile Components Across Cemented Rock Discontinuities Exhibiting Tension‐Softening Behavior

Fault slip involves not only shear but also tensile motions, causing repeated opening and closure of fault‐zone discontinuities. This cyclic deformation progressively changes the mechanical stiffness, fundamentally impacting seismic wave transmission. However, most existing analytical models neglect tensile components. This study develops a unified analytical framework combining the established Barton‐Bandis (BB) model for compressive deformation with a proposed inverse hyperbolic‐linear (iHL) model to describe tensile loading and unloading behaviors of cemented rock fractures. Integrating this model into a displacement discontinuity model and method of characteristics, we present the analytical solution that simultaneously accounts for compression‐hardening and tension‐softening effects on stress wave propagation. The BB‐iHL model uses an effective stiffness evolving dynamically with the instantaneous stress state, enabling quantitative prediction of stress wave transmission during earthquake cycles. Validation against split Hopkinson pressure and tension bar experiments confirms the model's ability to reproduce more realistic wave propagation. Results demonstrate that tensile stiffness degradation strongly influences wave transmission coefficients, particularly at low frequencies and amplitudes, and that ignoring tensile effects underestimates transmitted energy and waveform complexity. A case study based on seismic data from the 2008 Wenchuan earthquake illustrates the potential of the proposed framework for analyzing field‐scale seismic wave transmission. These findings underscore the critical role of tensile deformation in fault‐zone dynamics and highlight the proposed model as a tool for more accurate seismic wave modeling and earthquake hazard assessment.

Factor of safety prediction for open-pit slope using IoT-enabled hybrid machine learning digital twin with real-time adaptive updating