Prediction of compressive strength of fly ash-based geopolymers concrete based on machine learning

Hesong Hu, Mingye Jiang, Mengxiong Tang, Huqing Liang, Hao Cui, Chunlin Liu, Chunjie Ji, Yaozeng Wang, Simin Jian, Chaohai Wei, Siqi Song,
Prediction of compressive strength of fly ash-based geopolymers concrete based on machine learning,
Results in Engineering,
Volume 27,
2025,
106492,
ISSN 2590-1230,
https://doi.org/10.1016/j.rineng.2025.106492.
(https://www.sciencedirect.com/science/article/pii/S2590123025025617)
Abstract: The utilization of fly ash in the preparation of geopolymer concrete has emerged as a viable alternative to cement concrete due to its diminished carbon emissions, lower energy consumption, and superior performance. Nevertheless, the widespread application of geopolymers is hindered by the complexity and time intensity of experimental designs. Therefore, this study employs the use of machine learning models including Random Forest (RF), Artificial Neural Network (ANN), Gradient Boosting Decision Tree (GBDT), and Support Vector Machine (SVM) to predict the compressive strength of alkali-activated fly ash geopolymer concrete. The performance of the four machine learning models is systematically evaluated, and a comprehensive analysis is conducted to elucidate the influence of 12 different input variables on the compressive strength of fly ash-based geopolymer concrete (FA-GPC). The results suggest that all four machine learning models are proficient in accurately predicting the compressive strength of FA-GPC, with the GBDT model displaying superior predictive performance. Curing temperature and water content are identified as the most crucial controlling factors affecting FA-GPC compressive strength, followed by Si/Al molar ratios and alkali activator modulus. Additionally, this study employs partial dependence analysis to provide optimal ranges for these different input parameters, offering guidance for the rapid experiment design of fly ash based geopolymer, facilitating the widespread and environmentally friendly application of low-carbon geopolymer concrete, which possesses significant economic and environmental value.
Keywords: Geopolymer concrete; Machine learning; Fly ash; Environmentally friendly