Kerogen micropores in shale are crucial for gas sorption; nevertheless, their formation and evolution have been insufficiently studied. To qualitatively and quantitatively analyze changes in the molecular structure and associated micropores of kerogen throughout natural maturation, a series of experiments were performed on collected kerogen samples with varying maturity levels. The results demonstrated that the evolution of the chemical structure and associated micropores of kerogen can be divided into three stages during thermal evolution. When Ro < 1.43%, micropores are primarily controlled by the aliphatic composition of kerogen, resulting in a reduction in the micropore volume with decreasing numbers of aliphatic functional groups. When 1.43% < Ro < 1.93%, the micropore structure is primarily governed by the aromatic composition of kerogen and the micropore volume exhibits a gradual increment with increasing aromatic ring size. When Ro > 1.93%, the micropore volume rapidly increases with increasing aromatic composition of kerogen, and the aromatic rings become more orderly. Moreover, molecular simulations also show that the adsorption curves of CO₂ and CH₄ are type I isotherms, and that the adsorption capacity of CO₂ is greater than that of CH₄ under the same conditions, which indicates that the microscopic adsorption mechanism of CH₄ and CO₂ is gas competitive adsorption. This research offers new perspectives on the formation and evolution of kerogen micropores, and the carbon sequestration process.

Predicting the unconfined compressive strength (UCS) of alkali-activated stabilized soft soil under coupled acid attack and wetting–drying cycles requires evaluation across correlated laboratory observations. This study analyzed 689 records from 53 complete mixtures, with seven material and environmental inputs, using four machine-learning models (DT, RF, SVM, and XGBoost) and four neural models (PINN, BPNN, CNN, and LSTM). Generalization to previously unseen mixtures was evaluated by five-fold outer GroupKFold with three-fold mixture-grouped tuning. Each original record contributed one out-of-fold prediction. The pooled grouped-CV $R^2$ values ranged from 0.5043 to 0.7605, with RMSEs of 0.3579–0.5148 MPa. XGBoost attained the highest point estimate ($R^2=0.7605$; RMSE = 0.3579 MPa), followed by SVM ($R^2=0.7362$; RMSE = 0.3756 MPa). PINN and its architecture-matched BPNN produced identical grouped-CV predictions and no demonstrated incremental benefit. A prospective penalty-activation diagnostic confirmed that soft penalties can affect training trajectories but did not reconstruct the archived model-selection runs. A separately tuned, five-step, structure-matched ablation found no additional predictive gain from preceding design covariates in CNN and LSTM. Historical fixed-configuration random-CV comparisons were removed because the original hyperparameter-selection provenance could not be verified. SHAP and partial dependence analyses describe model-learned associations, and SEM offers qualitative morphological context. These models provide preliminary screening aids within the tested materials and factor levels, not engineering design tools; independent batch and field validation remains necessary.