Applied AI & Engineering

Materials have their limits; engineering has its bounds; speak only after testing.

We explore applications of AI to engineering science, materials design, and practical technical challenges. In sustainable concrete research, we integrate experimental data, machine learning, and environmental assessment to investigate the relationships among material composition, mechanical performance, and embodied carbon, and to support data-driven decisions under engineering constraints.

AI for Materials & Engineering Research

Applying experimental data and computational methods to understand engineering materials and environmental performance.

Recycled Aggregate & Carbon–Strength Trade-offs

Examining how recycled fine aggregate replacement and thermal exposure relate to concrete strength and material embodied carbon, with attention to the practical boundaries of low-carbon substitution.

Machine Learning for Concrete Performance

Studying strength prediction using multi-source concrete datasets and assessing model generalization and predictive reliability across heterogeneous sources.

AI-Driven Engineering Optimization

Investigating materials design and optimization by integrating machine learning, emission factors, and engineering constraints.

Low-Carbon Concrete Mix Optimization

Exploring lower-carbon concrete mix design under strength and mixture constraints, while accounting for prediction error and emission-factor uncertainty.