Limestone calcined clay cement (LC3) is a sustainable alternative to ordinary Portland cement, capable of reducing the binder’s carbon footprint by 40% while satisfying all key performance metrics. The inherent compositional heterogeneity in select components of LC3, combined with their convoluted chemical interactions, poses challenges to conventional analytical models when predicting mechanical properties. Although some studies have employed machine learning (ML) to predict the mechanical properties of LC3, many have overlooked the pivotal role of feature selection. Proper feature selection not only refines and simplifies the structure of ML models but also enhances these models’ prediction performance and interpretability. This research harnesses the power of the random forest (RF) model to predict the compressive strength of LC3. Three feature reduction methods—Pearson correlation, SHapley Additive exPlanations, and variable importance—are employed to analyze the influence of LC3 components and mixture design on compressive strength. Practical guidelines for utilizing these methods on cementitious materials are elucidated. Through the rigorous screening of insignificant variables from the database, the RF model conserves computational resources while also producing high-fidelity predictions. Additionally, a feature enhancement method is utilized, consolidating numerous input variables into a singular feature while feeding the RF model with richer information, resulting in a substantial improvement in prediction accuracy. Overall, this study provides a novel pathway to apply ML to LC3, emphasizing the need to tailor ML models to cement chemistry rather than employing them generically.
Belite calcium sulfoaluminate cement (CSAB), an alternative to Portland cement, exhibits excellent strength at both early and later ages. However, due to its high belite content, the carbon reduction from this type of cement is not sufficient when compared to other alternative cements. To further enhance CSAB’s sustainability, this study investigates the performance of CSAB when partially replaced by low-carbon mineral additives (i.e., limestone and gypsum). The primary objective is to identify the optimal mixture design by incorporating gypsum and limestone to formulate a sustainable binder that maintains high compressive strength. The CSAB is replaced (with both additives) by up to 51% at two different liquid-to-solid ratios of 0.4 and 0.5. gypsum replacements ranging from 0% to 27%, resulting in three unique gypsum-to-ye’elimite molar ratios (M). Limestone replacements range from 0% to 30% in 10% increments. The investigation focuses on the development of hydrates, hydration kinetics, and compressive strength of the sustainable binders after 3 days. The results indicate that a higher replacement level of limestone provides more free water to react with ye’elimite and belite, thereby enhancing the hydration kinetics, but decreasing the compressive strength. It also shows that the addition of gypsum enhances the formation of ettringite, enabling the maintenance of great compressive strength within the binder even at high limestone replacement levels. The binder containing 12% gypsum and 20% limestone was identified as the optimal mixture, yielding a compressive strength of 39 MPa. This performance, when compared to the plain CSAB (compressive strength of 49 MPa), demonstrates that the optimized binder achieves adequate sustainability while maintaining mechanical properties without significant compromise.
15 October 2025 in Journal of the American Ceramic Society
Chloride diffusion in reinforced concrete is a crucial factor in assessing infrastructure degradation, especially in marine environments where prolonged exposure to chloride-rich seawater accelerates deterioration. However, obtaining accurate time-dependent measurements of chloride concentration in RC presents a significant challenge due to constraints in both available workers and advanced instrumentation; in addition, replicating real-world environmental conditions in a laboratory setting is inherently difficult. The inherent complexity of concrete mixture designs—coupled with the variability of environmental parameters—further complicates the development of a practical model capable of reliably estimating chloride concentration at varying concrete depths. This study develops a data-driven approach to predict chloride concentrations at different depths and chloride diffusion coefficients in marine concrete formulated with common supplementary cementitious materials under varied environmental conditions and exposure durations. Additionally, a transfer learning technique is developed to accurately predict the compressive strength of marine concrete using a limited data set. This approach allows the model to extract broad correlations from a comprehensive concrete database while simultaneously capturing customized patterns specific to marine concrete. By doing so, it enhances the generalizability of existing models while significantly reducing the time required to develop new ones. Furthermore, this study leverages capillary porosity—obtained from thermodynamic simulations—as a critical intermediary for establishing correlations between compressive strength and chloride diffusion coefficients. This feature can be integrated into existing machine learning models for concrete compressive strength to enable prediction of both compressive strength and chloride diffusion coefficients.
16 September 2026 in Journal of the American Ceramic Society
The partial replacement of Portland cement (PC) with supplementary cementitious materials (SCMs) presents an effective strategy to reduce CO2 emissions associated with cement production while preserving essential mechanical properties and durability. SCMs, such as fly ash, blast furnace slag, calcined clays, and other aluminosilicate-rich materials, enhance sustainability through their pozzolanic and hydraulic reactivity. Despite their significant potential, the widespread adoption of SCMs has been limited by the absence of straightforward and quantitative methods to assess their reactivity‒a crucial property influenced by chemical composition, amorphous content, and particle fineness. To overcome these challenges, this study proposes a novel, simplified quantitative method for evaluating the time- and composition-dependent reactivity of SCMs in a PC-like environment. The approach combines isothermal calorimetry with detailed composition-based reaction enthalpy calculations, providing a robust framework for reactivity assessment. The method was applied to 17 chemically diverse SCMs, yielding reactivity values ranging from 9.3% to 63.2% at 7 days. Analytical models developed in the study reveal the relationships between the chemo-structural parameter (number of constraints, nc), heat release, and reactivity, enabling preliminary predictions based on chemical composition or calorimetric data. Validation across a broad spectrum of SCMs, including slags and calcined clays, confirms the reliability and versatility of this proposed methodology. This cost-effective and straightforward approach offers quantitative insights into SCM reactivity, enabling better control over binder properties and supporting the advancement of sustainable cementitious materials. The findings hold significant implications for optimizing SCM usage and advancing the design of environmentally sustainable construction materials.