Self-training AI for geopolymer strength prediction from microstructure
Establishing quantitative link between microstructural features and macroscopic properties remains a challenge in cementitious materials, particularly for reducing reliance on destructive large-scale testing and coring. Recent advances in machine learning show improved predictive capability; however, their effectiveness is constrained by data scarcity, exhaustive labelling and limited interpretability. This study introduces a self-training framework for achieving high-performance strength prediction in data-constrained scenarios on a model metakaolin-based geopolymer system. The framework employs a two-stage approach: first, a robust segmentation model is achieved through self-training, complemented by an adversarially generated synthetic dataset. Second, high dimensional quantitative microstructural descriptors, including phase fractions and particle-level geometric features, were extracted from the microstructure to train a classification model. The proposed framework achieved a classification accuracy of over 95% for predicting the geopolymer strength. By bridging the gap between microstructural imaging and data-driven predictive modelling, the framework enables scalable and quantitative linkage between microstructural descriptors and macroscopic performance, establishing a rigorous basis for microstructure-informed design and evaluation of cementitious materials.
Authors
- Navid Ranjbar (ORCID: https://orcid.org/0000-0002-1485-3931)
- Kazi Sazzad Hossen
- Toms Valdemārs Eiduks (ORCID: https://orcid.org/0009-0008-6034-2420)
- Dan Meng (ORCID: https://orcid.org/0000-0001-6874-3220)
- Andrei Shishkin (ORCID: https://orcid.org/0000-0002-5697-9903)
- Dheeraj Dhruva Kumar
Institutions
- Riga Technical University (LV)
- Technical University of Denmark (DK)
Publication Details
- Journal
- Cement and Concrete Research
- Published
- 2026-11-15
- DOI
- https://doi.org/10.1016/j.cemconres.2026.108460
- Primary Topic
- Concrete and Cement Materials Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00