Prediction of geopolymer concrete compressive strength using novel machine learning algorithms
Authors:
- Ayaz Ahmad,
- Waqas Ahmad,
- Krisada Chaiyasarn,
- Krzysztof Adam Ostrowski,
- Fahid Aslam,
- Paulina Zajdel,
- Panuwat Joyklad
Abstract
The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. The application of supervised machine learning (ML) algorithms to forecast the mechanical properties of concrete also has a significant role in developing the innovative environment in the field of civil engineering. This study was based on the use of the artificial neural network (ANN), boosting, and AdaBoost ML approaches, based on the python coding to predict the compressive strength (CS) of high calcium fly-ash-based GPC. The performance comparison of both the employed techniques in terms of prediction reveals that the ensemble ML approaches, AdaBoost, and boosting were more effective than the individual ML technique (ANN). The boosting indicates the highest value of R2 equals 0.96, and AdaBoost gives 0.93, while the ANN model was less accurate, indicating the coefficient of determination value equals 0.87. The lesser values of the errors, MAE, MSE, and RMSE of the boosting technique give 1.69 MPa, 4.16 MPa, and 2.04 MPa, respectively, indicating the high accuracy of the boosting algorithm. However, the statistical check of the errors (MAE, MSE, RMSE) and k-fold cross-validation method confirms the high precision of the boosting technique. In addition, the sensitivity analysis was also introduced to evaluate the contribution level of the input parameters towards the prediction of CS of GPC. The better accuracy can be achieved by incorporating other ensemble ML techniques such as AdaBoost, bagging, and gradient boosting.
- Record ID
- CUT7a878df26a11479b8b3bbd8e46576ffa
- Publication categories
- ;
- Author
- Journal series
- Polymers, ISSN , e-ISSN 2073-4360, Biweekly
- Issue year
- 2021
- Vol
- 13
- No
- 19
- Pages
- [1-18]
- Article number
- 3389
- Other elements of collation
- tab.; wykr.; Bibliografia (na s.) - 15-18; Bibliografia (liczba pozycji) - 82; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 13, Iss. 19
- Substantive notes
- Topic: Multiple Application for Novel and Advanced Materials
- Keywords in English
- geopolymer concrete, compressive strength, environment, cement, machine learning, coefficient of determination, fly ash, predictions
- DOI
- DOI:10.3390/polym13193389 Opening in a new tab
- URL
- https://www.mdpi.com/2073-4360/13/19/3389/htm Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 100
- Publication indicators
- = 53
- Additional fields
- Indeksowana w: Web of Science, Scopus
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT7a878df26a11479b8b3bbd8e46576ffa/
- URN
urn:pkr-prod:CUT7a878df26a11479b8b3bbd8e46576ffa
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.