Qile Ding

One-part geopolymers (OPG) offer a low-carbon alternative to Portland cement, yet mix design remains largely empirical. This study couples machine learning with SHAP (Shapley Additive Explanations) to quantify how mix and curing factors govern performance in Ca-containing OPG. We trained six regressors—Random Forest, ExtraTrees, SVR, Ridge, KNN, and XGBoost—on a compiled dataset and selected XGBoost as the primary model based on prediction accuracy. Models were built separately for four targets: compressive strength at 3, 7, 14, and 28 days. SHAP analysis reveals four dominant variables across targets—Slag, Na₂O, Ms, and the water-to-binder ratio (w/b)—while the sand-to-binder ratio (s/b), temperature, and humidity are secondary within the tested ranges. Strength evolution follows a reaction–densification logic: at 3 days, Slag dominates as Ca accelerates C–(N)–A–S–H formation; at 7–14 days, Na₂O leads as alkalinity/soluble silicate controls dissolution–gelation; by 28 days, Slag and Na₂O jointly set the strength ceiling, with w/b continuously regulating porosity. Interactions are strongest for Slag × Na₂O (Ca–alkalinity synergy). These results provide actionable guidance: prioritize Slag and Na₂O while controlling w/b for strength. The XGBoost+SHAP workflow offers transparent, data-driven decision support for OPG mix optimization and can be extended with broader datasets and formal validation to enhance generalization.

Analyzing geological profiles is of great importance for various applications such as natural resource management, environmental assessment, and mining engineering projects. This study presents a novel geostatistical approach for subsurface geological profile interpolation using a fractional kriging method enhanced by random forest regression. Using bedrock elevation data from 49 boreholes in a study area in southeast China, we first use random forest regression to predict and optimize variogram parameters. We then use the fractional kriging method to interpolate the data and analyze the variability. We also compare the proposed model with traditional methods, including linear regression, K-nearest neighbors, ordinary kriging, and fractional kriging, using cross-validation metrics. The results indicate that the proposed model reduces prediction errors and enhances spatial prediction reliability compared to other models. The MSE of the proposed model is 25% lower than that of ordinary kriging and 10% lower than that of fractional kriging. In addition, the execution time of the proposed model is slightly higher than other models. The findings suggest that the proposed model effectively captures complex subsurface spatial relationships, offering a reliable and precise solution for performing spatial interpolation tasks.

In this study, the Lagrange element strength reduction method is used to explore slope stability and as an evaluation method of underground mining of end-slope coal in a rock-stability analysis. A numerical analysis model is established herein using the geological conditions for mining in a coordinated open pit with an underground mining area of the Anjialing Open-Pit Mine and Underground No. 2 Mine. Additionally, the evolution law of slope stability in open-pit end-slope mining is studied using the proposed numerical simulation method. According to our findings, the steps show obvious horizontal movement and deformation under the influence of underground mining disturbances. Taking the horizontal displacement at the slope tops of the steps as the deformation index, the entire disturbed slope is divided into four regions: upper, middle-upper, middle-lower, and lower steps. When a step is fully affected by underground mining, its subsidence value first increases rapidly and then slowly. An exponential function is used to reflect the change rule in the step-subsidence value as the working face advances. In the underground mining process, the critical sliding surface of the slope develops along the soft rock or coal seam, showing an L-shaped or a W (double L)-shaped broken line. As the working face advances, the initial position of the sliding mass is unchanged while the cutting position alternately changes up and down in the weak plane. The safety factor suddenly drops when the advancing distance exceeds a certain value.

The construction of sponge city is a major green innovation to implement the concept of sustainable development. In this study, the road performance of permeable asphalt concrete (PAC), which displays pronounced water permeability and noise reduction that are favorable for sponge cities, has been improved with a two-fold modification using styrene–butadiene–styrene (SBS) and crumb rubber (CR). Four percent SBS and three different ratios (10%, 15%, and 20%) of CR have been used to modify the virgin asphalt binder. The Marshall design has been followed to produce PAC samples. To evaluate the asphalt binder performance, multiple-stress creep-recovery (MSCR) test, linear amplitude sweep (LAS) test, and engineering property test programs including softening point test, penetration test, and rotational viscosity test have been conducted. Freeze–thaw splitting test, Hamburg wheel-tracking test, resilient modulus test, and permeability coefficient test have been performed to evaluate the asphalt mixture performance. The test results show that the addition of SBS and CR reduces the permeability coefficient, but significantly improves the high temperature performance, fatigue performance, and rutting resistance as well as the resilient modulus. However, the optimum rubber content should not exceed 15%. Meanwhile, after adding CR and SBS modifier, the indirect tensile strength (ITS) and tensile strength ratio (TSR) increase. It indicates that the moisture stability and crack resistance have been improved by the composite modification effect.