BOxCrete: A Bayesian Optimization Open-Source AI Model for Concrete Strength Forecasting and Mix Optimization

TL;DR

BOxCrete is an open-source Bayesian optimization framework utilizing Gaussian Processes to predict concrete strength, quantify uncertainty, and optimize mix designs for strength and sustainability, based on a new publicly available dataset.

Contribution

It introduces an open-source probabilistic modeling and optimization framework for concrete mix design, trained on a novel open-access dataset, enabling reproducible AI-driven optimization.

Findings

Achieves high prediction accuracy with R² = 0.94

Provides uncertainty quantification for strength predictions

Enables multi-objective optimization of strength and embodied carbon

Abstract

Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets and closed-source implementations. Here we introduce BOxCrete, an open-source probabilistic modeling and optimization framework trained on a new open-access dataset of over 500 strength measurements (1-15 ksi) from 123 mixtures - 69 mortar and 54 concrete mixes tested at five curing ages (1, 3, 5, 14, and 28 days). BOxCrete leverages Gaussian Process (GP) regression to predict strength development, achieving average R$^2$ = 0.94 and RMSE = 0.69 ksi, quantify uncertainty, and carry out multi-objective optimization of compressive strength and embodied carbon. The dataset and model establish a reproducible open-source foundation for data-driven development of AI-based optimized mix designs.