Random Forest Algorithm for the Strength Prediction of Geopolymer Stabilized Clayey Soil

Husein Ali Zeini, Duaa Al-Jeznawi, Hamza Imran, Luís Filipe Almeida Bernardo (), Zainab Al-Khafaji and Krzysztof Adam Ostrowski
Additional contact information
Husein Ali Zeini: Department of Civil Engineering, Najaf Technical Institute, Al-Furat Al-Awsat Technical University, Najaf Munazira Str., Najaf 54003, Iraq
Duaa Al-Jeznawi: Department of Civil Engineering, Al-Nahrain University, Baghdad 10081, Iraq
Hamza Imran: Department of Environmental Science, College of Energy and Environmental Science, Alkarkh University of Science, Baghdad 10081, Iraq
Luís Filipe Almeida Bernardo: Department of Civil Engineering and Architecture, University of Beira Interior, 6201-001 Covilhã, Portugal
Zainab Al-Khafaji: Building and Construction Techniques Engineering Department, Al-Mustaqbal University College, Hillah 51001, Iraq
Krzysztof Adam Ostrowski: Faculty of Civil Engineering, Cracow University of Technology, 24 Warszawska Str., 31-155 Cracow, Poland

Sustainability, 2023, vol. 15, issue 2, 1-15

Abstract: Unconfined compressive strength (UCS) can be used to assess the applicability of geopolymer binders as ecologically friendly materials for geotechnical projects. Furthermore, soft computing technologies are necessary since experimental research is often challenging, expensive, and time-consuming. This article discusses the feasibility and the performance required to predict UCS using a Random Forest (RF) algorithm. The alkali activator studied was sodium hydroxide solution, and the considered geopolymer source material was ground-granulated blast-furnace slag and fly ash. A database with 283 clayey soil samples stabilized with geopolymer was considered to determine the UCS. The database was split into two sections for the development of the RF model: the training data set (80%) and the testing data set (20%). Several measures, including coefficient of determination (R), mean absolute error (MAE), and root mean square error (RMSE), were used to assess the effectiveness of the RF model. The statistical findings of this study demonstrated that the RF is a reliable model for predicting the UCS value of geopolymer-stabilized clayey soil. Furthermore, based on the obtained values of RMSE = 0.9815 and R 2 = 0.9757 for the testing set, respectively, the RF approach showed to provide excellent results for predicting unknown data within the ranges of examined parameters. Finally, the SHapley Additive exPlanations (SHAP) analysis was implemented to identify the most influential inputs and to quantify their behavior of input variables on the UCS.

Keywords: Random Forest; machine learning; SHAP; geopolymer; clayey soil; unconfined compressive strength; prediction (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/2/1408/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/2/1408/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:2:p:1408-:d:1032621

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().