Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study

Abstract Expansive soils present substantial challenges for construction projects, particularly in arid regions where their swelling and shrinking behavior can result in structural damage. This research conducted an in-depth analysis of 195 soil samples, investigating six crucial factors, including...

Full description

Saved in:
Bibliographic Details
Main Authors: Sultan Almuaythir, Muhammad Syamsul Imran Zaini, Rida Hameed Lodhi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-09279-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399977480028160
author Sultan Almuaythir
Muhammad Syamsul Imran Zaini
Rida Hameed Lodhi
author_facet Sultan Almuaythir
Muhammad Syamsul Imran Zaini
Rida Hameed Lodhi
author_sort Sultan Almuaythir
collection DOAJ
description Abstract Expansive soils present substantial challenges for construction projects, particularly in arid regions where their swelling and shrinking behavior can result in structural damage. This research conducted an in-depth analysis of 195 soil samples, investigating six crucial factors, including clay content, liquid and plastic limit, specific gravity, plasticity index, and swell percentage, influencing soil compaction. The study used five computational models to predict optimal water content and maximum dry density. Among the models, XG-Boost exhibited exceptional performance with high predictive accuracy, scoring 0.941 and 0.912 for water content and density, respectively. Random Forest method also performed well, whereas Long Short-Term Memory Network (LSTMN) and k-Nearest Neighbors methods achieved moderate success. Detailed performance metrics, including correlation coefficients (r), mean absolute error (MAE), root mean squared error (RMSE), relative root mean squared error (RRMSE), and performance index (PI), were analyzed for each model across the training, testing, and validation datasets. XG-Boost consistently outperformed other models, demonstrating its robust and reliable predictive power. The analysis of absolute error highlighted the accuracy and consistency of XG-Boost and Random Forest in predicting the maximum dry density.
format Article
id doaj-art-4e0f02a2f9474afaa77d078988f05f8b
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4e0f02a2f9474afaa77d078988f05f8b2025-08-20T03:38:12ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-09279-2Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative studySultan Almuaythir0Muhammad Syamsul Imran Zaini1Rida Hameed Lodhi2Department of Civil Engineering, College of Engineering in Al-Kharj, Prince Sattam Bin Abdulaziz UniversityFaculty of Civil Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah, Lebuh Persiaran Tun Khalil YaakobDepartment of Urban and Regional Planning, National University of Sciences and Technology (NUST)Abstract Expansive soils present substantial challenges for construction projects, particularly in arid regions where their swelling and shrinking behavior can result in structural damage. This research conducted an in-depth analysis of 195 soil samples, investigating six crucial factors, including clay content, liquid and plastic limit, specific gravity, plasticity index, and swell percentage, influencing soil compaction. The study used five computational models to predict optimal water content and maximum dry density. Among the models, XG-Boost exhibited exceptional performance with high predictive accuracy, scoring 0.941 and 0.912 for water content and density, respectively. Random Forest method also performed well, whereas Long Short-Term Memory Network (LSTMN) and k-Nearest Neighbors methods achieved moderate success. Detailed performance metrics, including correlation coefficients (r), mean absolute error (MAE), root mean squared error (RMSE), relative root mean squared error (RRMSE), and performance index (PI), were analyzed for each model across the training, testing, and validation datasets. XG-Boost consistently outperformed other models, demonstrating its robust and reliable predictive power. The analysis of absolute error highlighted the accuracy and consistency of XG-Boost and Random Forest in predicting the maximum dry density.https://doi.org/10.1038/s41598-025-09279-2Compaction characteristicsExpansive clay soilMachine learing approachesPrediction model
spellingShingle Sultan Almuaythir
Muhammad Syamsul Imran Zaini
Rida Hameed Lodhi
Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
Scientific Reports
Compaction characteristics
Expansive clay soil
Machine learing approaches
Prediction model
title Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
title_full Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
title_fullStr Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
title_full_unstemmed Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
title_short Predicting soil compaction parameters in expansive soils using advanced machine learning models: a comparative study
title_sort predicting soil compaction parameters in expansive soils using advanced machine learning models a comparative study
topic Compaction characteristics
Expansive clay soil
Machine learing approaches
Prediction model
url https://doi.org/10.1038/s41598-025-09279-2
work_keys_str_mv AT sultanalmuaythir predictingsoilcompactionparametersinexpansivesoilsusingadvancedmachinelearningmodelsacomparativestudy
AT muhammadsyamsulimranzaini predictingsoilcompactionparametersinexpansivesoilsusingadvancedmachinelearningmodelsacomparativestudy
AT ridahameedlodhi predictingsoilcompactionparametersinexpansivesoilsusingadvancedmachinelearningmodelsacomparativestudy