Argillaceous siltstone forms water-sensitive weak layers in red-bed slopes, but its multiscale deterioration under wet–dry cycling remains incompletely understood. Specimens subjected to 0, 1, 3, 5, 7, and 9 cycles were examined through uniaxial compression, energy analysis, digital image correlation (DIC), and microst...
The prediction of shear strength in seasonally frozen silty clay is restricted by complex physical mechanisms and sparse experimental data. A self-supervised contrastive physics-informed neural network is proposed to overcome these limitations. Robust latent features are extracted from limited datasets via contrastive...