Comparison of deep LSTM and machine learning models for predicting compressive strength of fly ash/slag-based geopolymer concrete
Open Access
- 25 September 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-25
Abstract
In the production of geopolymer concrete (GPC), using ground granulated blast furnace slag (GGBFS) and fly ash (FA) can reduce the carbon dioxide footprint and decrease the amount of waste materials released into the environment. Finding the compressive strength (fc) of GPC through experiments is time-consuming and costly; thus, applying artificial intelligence models can expedite this process. This study aims to compare the performance of deep Long Short-Term Memory (LSTM) and the machine learning (ML)-based algorithms in predicting the fc of FA/GGBFS-based GPC. Artificial neural networks (ANN), Bootstrap aggregating (Bagging), Least-Squares Boosting (LSBoost) and K-Nearest-Neighbours (kNN) were used for ML-based algorithms. For this goal, data were collected from the previous studies in the literature. The selected input characteristic variables included the chemical composition and quantities of FA and GGBFS, fine and coarse aggregates, sodium hydroxide molarity, alkaline activators, superplasticizer dosage, and curing temperature. Based on sensitivity analysis, the most influential parameter in the fc of FA/GGBFS-based GPC was the fine aggregate content. Performance metrics, error percentage distribution, and Taylor diagrams indicate that the highest accuracy was achieved by LSTM, which had an R-squared value of 0.98. This was followed by ANN, LSBoost, Bagging, and kNN. Notably, LSBoost and ANN also demonstrated strong performance, with R-squared values of 0.94 and 0.95, respectively. Also, Bagging showed acceptable ability for fc estimation of FA/GGBFS-based GPC due to having an R-squared value of 0.88, but kNN had very poor performance.Keywords
Funding Information
- European Commission (689857-PRIGeoC-RISE-2015, 689857-PRIGeoC-RISE-2015)
This publication has 110 references indexed in Scilit:
- Prediction of mechanical properties of high‐performance concrete and ultrahigh‐performance concrete using soft computing techniques: A critical reviewStructural Concrete, 2024
- Data‐driven approach for investigating and predicting of compressive strength of fly ash–slag geopolymer concreteStructural Concrete, 2023
- Influence of input motion and surface layer properties on seismic site response: A stochastic simulation method–based MLR modelNear Surface Geophysics, 2023
- Deep learning and machine learning‐based prediction of capillary water absorption of hybrid fiber reinforced self‐compacting concreteStructural Concrete, 2022
- Estimation of strengths of hybrid FR‐SCC by using deep‐learning and support vector regression modelsStructural Concrete, 2022
- Prediction of compressive strength of geopolymer concrete using machine learning techniquesStructural Concrete, 2021
- Sodium hydroxide effect on the mechanical properties of flyash‐slag based geopolymer concreteStructural Concrete, 2020
- Emotion Recognition from EEG Using RASM and LSTM2018
- Mix Design of Fly Ash Based Geopolymer Concrete2015
- Ensemble Methods in Machine Learning2000