Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models - read online free

Aug 5, 2026

Upload by Finn

Geotechnical engineering depends on accurate prediction of soil strength to support safe and efficient construction. This study develops two grey-box machine learning approaches to model the strength behavior of hydrated-lime activated rice husk ash (HARHA) treated soil. Classification and regression trees (CART) and genetic programming (GP) produce interpretable equations and trees. Using a laboratory dataset with seven inputs and three outputs, the models are evaluated on CBR, unconfined compressive strength (UCS), and in-situ cone resistance (R value).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages27

Reading Time1 h 8 min

AccessFree to download

Introduction

Soil stabilization and traditional limitations

Hydrated lime: properties and reactions

Rice husk ash: pozzolanic behavior and benefits

Article Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models Abolfazl Baghbani 1, *, Amin Soltani 2, Katayoon Kiany 3 and Firas Daghistani 4,5 Citation: Baghbani, A.; Soltani, A.; Kiany, K.; Daghistani, F. Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models. Geotechnics 2023, 3, 894–920. [https://](https://)[ ](https://)[doi.org/10.3390/geotechnics3030048](doi.org/10.3390/geotechnics3030048) Academic Editor: Raffaele Di Laora Received: 29 July 2023 Revised: 13 August 2023 Accepted: 1 September 2023 Published: 11 September 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 School of Engineering, Deakin University, Waurn Ponds, VIC 3125, Australia 2 Institute of Innovation, Science and Sustainability, Future Regions Research Centre, Federation University, Churchill, VIC 3842, Australia; [a.soltani@federation.edu.au](a.soltani@federation.edu.au) 3 Melbourne School of Design, The University of Melbourne, Parkville, VIC 3010, Australia; [kianyk@student.unimelb.edu.au](kianyk@student.unimelb.edu.au) 4 Department of Civil Engineering, La Trobe University, Bundoora, VIC 3086, Australia; [f.daghistani@latrobe.edu.au](f.daghistani@latrobe.edu.au) 5 Civil Engineering Department, University of Business and Technology, Jeddah 23435, Saudi Arabia * Correspondence: [abaghbani@deakin.edu.au](abaghbani@deakin.edu.au) Abstract: Geotechnical engineering relies heavily on predicting soil strength to ensure safe andefﬁcient construction projects. This paper presents a study on the accurate prediction of soil strength properties, focusing on hydrated-lime activated rice husk ash (HARHA) treated soil. To achieve precise predictions, the researchers employed two grey-box machine learning models—classiﬁcation and regression trees (CART) and genetic programming (GP) . These models introduce innovative equations and trees that readers can readily apply to new databases. The models were trained and tested using a comprehensive laboratory database consisting of seven input parameters and three output variables. The results indicate that both the proposed CART trees and GP equations exhibited excellent predictive capabilities across all three output variables—California bearing ratio (CBR), unconﬁned compressive strength (UCS), and resistance value (R value) (according to the in-situ cone penetrometer test) . The GP proposed equations, in particular, demonstrated a superior performance in predicting the UCS and Rvalue parameters, while remaining comparable to CART in predicting the CBR. This research highlights the potential of integrating grey-box machine learning models with geotechnical engineering, providing valuable insights to enhance decision-making processes and safety measures in future infrastructural development projects. Keywords: hydrated lime; rice husk ash; machine learning; grey-box model; classiﬁcation and regression trees; genetic programming 1. Introduction Soil stabilization techniques play an important role in geotechnical engineering to improve the engineering properties of weak or problematic soils [1] . Traditional methods, such as soil replacement or compaction, have limitations in terms of cost, implementation, and environmental impact [2,3] . As a sustainable and economical alternative, soil stabilization using supplementary materials/additives has attracted considerable attention. One of these approaches includes adding hydrated lime and rice husk ash to the soil [4] . Because of its unique properties, hydrated lime is a

FAQs

What two grey-box machine learning models are used to predict soil strength?

The study uses classification and regression trees (CART) and genetic programming (GP). Both aim to provide usable, interpretable models for new data.

Which soil strength outputs are predicted in the research?

The models predict three outputs: California bearing ratio (CBR), unconfined compressive strength (UCS), and resistance value (R value) from the in-situ cone penetrometer test.

How do CART and GP compare in predictive performance?

Both CART and GP show excellent prediction capability across all three outputs. GP equations perform particularly better for UCS and R value, while remaining comparable to CART for CBR.

Aug 5, 2026

Upload by Finn