Predictive Modeling of Mechanical Properties in Sustainable Concrete Materials

Predictive modelling of mechanical properties in sustainable concrete materials has become indispensable for the design of low-carbon mixes that meet performance requirements without extensive empirical testing. By integrating vast experimental datasets with advanced computational techniques, researchers can capture the complex, non-linear interactions between supplementary cementitious materials, aggregate characteristics, fibre reinforcements and curing regimes. Machine learning frameworks, such as gene expression programming and ensemble methods, now enable the rapid generation of predictive equations and surrogate models for properties including compressive strength, elastic modulus and tensile performance. These approaches support global efforts to reduce cement usage and embodied carbon by optimising mix proportions, assessing novel industrial by-products and tailoring formulations to local resources. In practice, predictive tools facilitate pre-design validation, real-time quality control and adaptive use of waste materials, thereby accelerating the sustainable transformation of the concrete sector.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Predictive Modeling of Mechanical Properties in Sustainable Concrete Materials publication trend

The graph below shows the total number of articles in predictive modeling of mechanical properties in sustainable concrete materials across all publications each year (not limited to Nature Index journals).

Technical terms

Gene Expression Programming (GEP): An evolutionary algorithm that evolves computer programs or equations to model complex relationships between input variables and target properties.

Machine Learning (ML): A suite of algorithms that learn patterns and correlations in data to make predictions or decisions without explicit programming for each scenario.

Supplementary Cementitious Materials (SCMs): Industrial by-products or natural materials, such as fly ash or bagasse ash, used to replace a portion of cement in concrete to reduce environmental impact.

Compressive Strength: The maximum axial load a concrete specimen can bear before failure, a key indicator of material performance under service conditions.

Stacked Model: An ensemble learning technique that combines multiple base learners to improve generalisation and predictive accuracy over individual algorithms.

References

1. Applications of Gene Expression Programming and Regression Techniques for Estimating Compressive Strength of Bagasse Ash based Concrete. Crystals (2020).
2. Data-driven compressive strength prediction of steel fiber reinforced concrete (SFRC) subjected to elevated temperatures using stacked machine learning algorithms. Journal of Materials Research and Technology (2022).