Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models
Geotechnical engineering relies heavily on predicting soil strength to ensure safe and efficient 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 predi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Geotechnics |
Subjects: | |
Online Access: | https://www.mdpi.com/2673-7094/3/3/48 |
_version_ | 1797579906004025344 |
---|---|
author | Abolfazl Baghbani Amin Soltani Katayoon Kiany Firas Daghistani |
author_facet | Abolfazl Baghbani Amin Soltani Katayoon Kiany Firas Daghistani |
author_sort | Abolfazl Baghbani |
collection | DOAJ |
description | Geotechnical engineering relies heavily on predicting soil strength to ensure safe and efficient 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<sub>value</sub>) (according to the in-situ cone penetrometer test). The GP proposed equations, in particular, demonstrated a superior performance in predicting the UCS and R<sub>value</sub> 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. |
first_indexed | 2024-03-10T22:42:40Z |
format | Article |
id | doaj.art-bd247ab808c64e1d838d3ac3d0d12b43 |
institution | Directory Open Access Journal |
issn | 2673-7094 |
language | English |
last_indexed | 2024-03-10T22:42:40Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Geotechnics |
spelling | doaj.art-bd247ab808c64e1d838d3ac3d0d12b432023-11-19T10:55:18ZengMDPI AGGeotechnics2673-70942023-09-013389492010.3390/geotechnics3030048Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning ModelsAbolfazl Baghbani0Amin Soltani1Katayoon Kiany2Firas Daghistani3School of Engineering, Deakin University, Waurn Ponds, VIC 3125, AustraliaInstitute of Innovation, Science and Sustainability, Future Regions Research Centre, Federation University, Churchill, VIC 3842, AustraliaMelbourne School of Design, The University of Melbourne, Parkville, VIC 3010, AustraliaDepartment of Civil Engineering, La Trobe University, Bundoora, VIC 3086, AustraliaGeotechnical engineering relies heavily on predicting soil strength to ensure safe and efficient 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<sub>value</sub>) (according to the in-situ cone penetrometer test). The GP proposed equations, in particular, demonstrated a superior performance in predicting the UCS and R<sub>value</sub> 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.https://www.mdpi.com/2673-7094/3/3/48hydrated limerice husk ashmachine learninggrey-box modelclassification and regression treesgenetic programming |
spellingShingle | Abolfazl Baghbani Amin Soltani Katayoon Kiany Firas Daghistani Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models Geotechnics hydrated lime rice husk ash machine learning grey-box model classification and regression trees genetic programming |
title | Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models |
title_full | Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models |
title_fullStr | Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models |
title_full_unstemmed | Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models |
title_short | Predicting the Strength Performance of Hydrated-Lime Activated Rice Husk Ash-Treated Soil Using Two Grey-Box Machine Learning Models |
title_sort | predicting the strength performance of hydrated lime activated rice husk ash treated soil using two grey box machine learning models |
topic | hydrated lime rice husk ash machine learning grey-box model classification and regression trees genetic programming |
url | https://www.mdpi.com/2673-7094/3/3/48 |
work_keys_str_mv | AT abolfazlbaghbani predictingthestrengthperformanceofhydratedlimeactivatedricehuskashtreatedsoilusingtwogreyboxmachinelearningmodels AT aminsoltani predictingthestrengthperformanceofhydratedlimeactivatedricehuskashtreatedsoilusingtwogreyboxmachinelearningmodels AT katayoonkiany predictingthestrengthperformanceofhydratedlimeactivatedricehuskashtreatedsoilusingtwogreyboxmachinelearningmodels AT firasdaghistani predictingthestrengthperformanceofhydratedlimeactivatedricehuskashtreatedsoilusingtwogreyboxmachinelearningmodels |