To support the achievement of the carbon peaking and carbon neutrality goals and promote the resource utilization of industrial solid waste, a ternary solid waste composite cementitious material was prepared by blending ground granulated blast-furnace slag (GGBFS), fly ash (FA), and carbide slag (CS) with cement. The optimal mix ratio was determined through single-factor experiments and response surface methodology. The synergistic hydration mechanism was elucidated using microstructural characterization techniques, including XRD, FTIR, TG-DTG, and SEM. The composite material was then applied to a semirigid base course, and its mechanical properties and durability were systematically evaluated. The results indicate that the optimal levels of FA, GGBFS, and CS investigated in the single-factor experiments are 20–40%, 30–50%, and 2–6%, respectively. The optimal mix ratio of the ternary solid waste composite is 21.0% FA, 36.3% GGBFS, and 5.7% CS. The underlying microstructural mechanism is that carbide slag creates a highly alkaline environment, which activates the pozzolanic activity of GGBFS and fly ash, leading to the formation of hydration products dominated by C-(A)-S-H gel. With increasing curing age, the gel structure evolves from a loose and disordered state to a dense and ordered state, ultimately forming a compact microstructure based on a highly polymerized C-(A)-S-H gel matrix. The 7-day unconfined compressive strength of the stabilized gravel using the solid waste-based composite cementitious material reached 5.93 MPa, and the 28-day drying shrinkage coefficient was reduced by 18.3% compared with that of cement-stabilized gravel. After 18 freeze–thaw cycles, the compressive strength increased by 2.4%, with the pore structure characterized by a “macropores decreasing, micropores increasing” refinement pattern. After 18 wetting–drying cycles, the cumulative strength loss was 11.26%, outperforming cement-stabilized gravel. Combined with SEM observations, these performance improvements are attributed to the densely intertwined hydration products, particularly C-S-H gel, which effectively fill the voids between aggregate particles and significantly enhance the volume stability, freeze–thaw resistance, and wetting–drying durability of the stabilized gravel. The application of this cementitious material in a semirigid base course demonstrates excellent mechanical and durability properties, providing a theoretical basis and technical support for the widespread application of industrial solid waste in road engineering.

This study combined experimental analysis with deep learning to investigate the effects of curing age, steel slag content, and gradation composition on the mechanical properties of cement-stabilized steel slag (CSSS). The strength evolution patterns and underlying microscopic mechanisms were systematically elucidated. Experimental results showed that CSSS strength grows nonlinearly with curing age, with optimal mechanical performance achieved at a 60% steel slag content. The microstructural evolution characterized by SEM-EDS and XRD revealed that steel slag incorporation promotes the formation of AFt and densifies the gel network. In later curing stages, natural carbonation of Ca(OH)₂ and secondary hydration of reactive steel slag components produce CaCO₃ and additional C-S-H gel, which fill pores and significantly enhance long-term strength. A CNN-GRU-Attention model was developed to predict the unconfined compressive strength (UCS) and splitting tensile strength (STS) of CSSS. In a single data split, the model achieved R² values of 0.9875 for UCS and 0.9911 for STS, with RMSEs of 0.2577 MPa and 0.0234 MPa, and MAEs of 0.2059 MPa and 0.0184 MPa, outperforming all benchmark models. Under rigorous 5 × 5 repeated cross-validation, it maintained the highest average R² (UCS: 0.9417, STS: 0.9329) and the lowest error metrics, confirming its robustness and generalization capability. SHAP and Pearson correlation analyses identified cement content as the primary strength determinant, while steel slag content exhibited a threshold effect, highlighting the importance of prudent gradation control in practical engineering. This study provides both a theoretical foundation and a methodological framework for analyzing variable interactions and predicting the strength development of CSSS.

In an effort to overcome the problems of modified asphalt mixture using the typical wet process, the dry process was used to modify 70# base asphalt with the SBS/crumb rubber composite modified masterbatch. Box–Behnken response surface methodology was used to create a regression model with the interactions of five factors, which gave the optimum preparation parameters. The results show that there are many factors that have substantial influence on the laboratory performance of asphalt mixture, and the created quadratic regression model has good fitting accuracy and predictive capability. The optimum preparation parameters were an asphalt–aggregate ratio of 4.5%, modifier dosage of 2%, dry mixing time of 65 s, wet mixing time of 107 s, and mixing temperature of 189 °C. Compared to the 70# base asphalt mixture and the wet-process asphalt mixtures, the dynamic stability of the dry-process asphalt mixtures is significantly improved by 503% and 36.6%, respectively. The TSR increased by 11.4% and 4.8%, respectively, as did the residual stability by 9.6% and 2%, respectively. Compared to the 70# base asphalt mixture, the maximum flexural strain increased by 46%, though it was slightly lower under the dry process than under the traditional wet process. The results confirm the practicality of the proposed optimization strategy for the dry process.

Public geopolymer concrete (GPC) databases can support retrospective screening of records with lower reported CO₂ emissions under strength constraints, but reliable ranking also requires correct response matching and stable threshold-based eligibility. Using 274 records, this study reconstructed the strength–CO₂ correspondence from 19 mix proportion and preparation fields, yielding 273 mix design identifiers (MixIDs). Eight regression algorithms were evaluated under MixID-grouped validation, and CatBoost with derived descriptors was retained as the primary model. It achieved R² = 0.969 and RMSE = 2.096 MPa on the fixed test set; across 30 repeated holdouts, mean RMSE was 2.390 ± 0.234 MPa. Because observed strength was available for every record, the model served as an internal consistency filter rather than a predictor of untested formulations. At 40, 50, and 60 MPa, 176, 65, and four records met the observed strength and mean prediction criteria, while 174, 62, and three records also satisfied the empirical fifth-percentile (Q05) criterion. Q05 was treated as a descriptive measure of partition sensitivity, and the 60 MPa result was regarded as exploratory. A CO₂ assignment negative control showed weak agreement between row-wise and key-matched values (Pearson r = 0.065) and low Pareto-set overlap (Jaccard = 0.045–0.105). Thus, prediction accuracy alone does not ensure valid lower-CO₂ ranking. The workflow provides an auditable basis for screening observed records within the database domain.

To enhance the comprehensive performance of crumb rubber (CR)/SBS-composite-modified bitumen, an orthogonal experimental design was first adopted to analyze the effects of process parameters—including the addition sequence, shearing duration, shearing temperature and shearing speed—on the conventional properties of bitumen. Furthermore, based on the Box–Behnken response surface methodology, quadratic regression predictive models for the dosages of SBS, waste crumb rubber and aromatic oil were constructed, and the entropy-weighted TOPSIS method was introduced to comprehensively evaluate and multi-objectively optimize the proportioning schemes. The results indicate that a reasonable preparation process can significantly promote the uniform dispersion of modifiers, distinct non-linear interactions exist among the dosages of each modifier, and the optimal proportion balancing both high- and low-temperature performance was obtained through optimization. The constructed models exhibit good predictive accuracy, and the optimized CR/SBS-composite-modified bitumen showed excellent conventional properties and storage stability, which can provide a theoretical reference for the recycling of waste tires and the engineering application of composite-modified bitumen.