After rocks are damaged under stress loading, the changes of their microstructural and mechanical properties are major factors that affect construction safety in geotechnical engineering projects. Studying the microstructures and mechanical behaviors of stress‐damaged rocks can help better guide construction and reduce construction risks for geotechnical engineering projects. In this study, a sandstone was first artificially predamaged and then subsequently subjected to scanning electron microscopy (SEM) analysis, computed tomography (CT) scanning, and uniaxial compression testing. Afterwards, the rock microstructures were three‐dimensionally (3D) reconstructed, and the pores were classified and characterized based on their diameters. Moreover, the microstructural and mechanical parameters of the rock were subjected to significance analysis. The results showed that as the stress‐induced damage (σ_i) increased, the uniaxial compressive strength (σ_c) of the soft rock decreased by 13.7–31.8%; as σ_i increased from 11.2 to 19.6 MPa, the elastic modulus (E) of the soft rock increased by up to 28.8%; and as σ_i increased beyond 19.6 MPa, there was a significant (22.3%) decrease in E. Stress‐induced damage significantly affected the spatial distribution of the pores’ structure of the soft rock. Changes in the spatial structure of the pores led to the formation of cracks. The microstructural parameters of the stress‐damaged soft rock were correlated with its mechanical parameters.

Mine tailings disposal has been a serious environmental issue for decades. The wide application of cemented tailings backfill (CTB) technology could indirectly abate tailings pollution by recycling the tailings for backfilling. CTB constitutive modeling helps with design by improving the understanding of its compressive behavior. This study focused on CTB intelligent constitutive modeling considering the coupled effects of the cement content and saturation state. An artificial intelligence model was established and utilized based on particle swarm optimization (PSO) and the support vector machine (SVM). CTB samples with different cement contents and water saturation states were prepared, and unconfined compression tests were conducted to obtain the dataset. We verified the feasibility of using integrated PSO and SVM (P-S) in the CTB constitutive model using experimental data. We analyzed model errors. The results showed that the CTB stress strain curve was complex and nonlinear and could be significantly affected by the saturation states. PSO was feasible and efficient for tuning the SVM hyperparameters. The lowest minimum MSE value of 0.0108 was achieved in the eighth iteration. The PSO and SVM modeling was indicated to be accurate in the CTB constitutive model (a high R-square value of 0.9935 and a low mean squared error value of 0.001664 were achieved on the testing set). This model may accelerate the CTB structure design process.