Predicting undrained shear strength in marine sediments using a physics-informed neural network (PINN)

Abstract

Undrained shear strength ($S_U$) is a key parameter for evaluating slope stability, offshore foundation design, and submarine geohazards in marine environments. Conventional methods for predicting $S_U$ often fall short in accuracy because they fail to account for the complex and nonlinear relationships among sediment properties. Here, we propose a physics-informed neural network (PINN) framework to predict the three-dimensional structure of $S_U$ using various observed physical parameters, including bulk density, porosity, P-wave velocity, gamma ray attenuation, and natural gamma ray. The framework embeds governing physical laws—total vertical stress $\sigma \left(z\right)$, pore water pressure $u\left(z\right)$, and effective stress σ′(z)—as constraints within the loss function to ensure physically consistent and accurate predictions. The results show that our physics-informed model significantly improves prediction accuracy and stability, achieving R² up to 0.91 (mean ≈ 0.85) and reducing prediction error by more than 18% for marine sediments compared to purely data-driven models. Sensitivity analysis highlights that bulk density and porosity are the most influential inputs for predicting $S_U$, consistent with their fundamental role in sediment consolidation and strength. The predicted $S_U$ exhibits a northwest–southeast gradient, with the strongest increase at depths of approximately 100–200 m below the seafloor. The proposed model provides spatially continuous $S_U$ maps and demonstrates that embedding first-order physical laws in network training greatly improves the reliability and interpretability of $S_U$ predictions, offering a practical tool for marine geotechnical applications in areas with complex stratigraphy.