Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models

Thermal conductivity is a crucial factor for the soil, which is significantly affected by environmental conditions. Based on the variation in the thermal conductivity and the influencing factors of silty clay obtained by the freeze–thaw cycle test, this paper adopted four machine learning models opt...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuwei Chen, Yadi Min, Haiqiang Jiang, Jing Luo, Mengxin Liu, Enliang Wang, Xingchao Liu, Ke Shi, Xiaoqi Li
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/5/750
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050667200118784
author Yuwei Chen
Yadi Min
Haiqiang Jiang
Jing Luo
Mengxin Liu
Enliang Wang
Xingchao Liu
Ke Shi
Xiaoqi Li
author_facet Yuwei Chen
Yadi Min
Haiqiang Jiang
Jing Luo
Mengxin Liu
Enliang Wang
Xingchao Liu
Ke Shi
Xiaoqi Li
author_sort Yuwei Chen
collection DOAJ
description Thermal conductivity is a crucial factor for the soil, which is significantly affected by environmental conditions. Based on the variation in the thermal conductivity and the influencing factors of silty clay obtained by the freeze–thaw cycle test, this paper adopted four machine learning models optimized by particle swarm optimization (PSO), including the artificial neural network model (ANN), random forest model (RF), support vector machine model (SVM), and extreme gradient boosting model (XGBoost) to predict the thermal conductivity of the soil. Meanwhile, mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient(R<sup>2</sup>) were used to evaluate the accuracy of the models. The accuracy of the machine learning model and empirical model were also compared. Then, the Monte Carlo simulation was used to analyze the stability of the models. The research results showed that the predicted performance of the machine learning models is significantly better than the empirical models. Among all the machine learning models, the R<sup>2</sup> of the PSO-ANN model is above 0.95, while both RMSE and MAE values are below 0.02 (W·m⁻¹·K⁻¹). In addition, the stability order of the machine learning models is PSO-XGBoost, PSO-ANN, PSO-RF, and PSO-SVM. Therefore, comprehensively considering the accuracy and stability of the four machine learning models, the PSO-ANN model is recommended to predict soil’s thermal conductivity under freeze–thaw action.
format Article
id doaj-art-e132de0aa5f44e0db705b3f29bfc54d5
institution DOAJ
issn 2075-5309
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-e132de0aa5f44e0db705b3f29bfc54d52025-08-20T02:53:22ZengMDPI AGBuildings2075-53092025-02-0115575010.3390/buildings15050750Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning ModelsYuwei Chen0Yadi Min1Haiqiang Jiang2Jing Luo3Mengxin Liu4Enliang Wang5Xingchao Liu6Ke Shi7Xiaoqi Li8State Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaSchool of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaState Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaState Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaNanjing University (Suzhou) High-Tech Institute, Suzhou 215000, ChinaSchool of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaSchool of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaSchool of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaSchool of Water Conservancy and Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaThermal conductivity is a crucial factor for the soil, which is significantly affected by environmental conditions. Based on the variation in the thermal conductivity and the influencing factors of silty clay obtained by the freeze–thaw cycle test, this paper adopted four machine learning models optimized by particle swarm optimization (PSO), including the artificial neural network model (ANN), random forest model (RF), support vector machine model (SVM), and extreme gradient boosting model (XGBoost) to predict the thermal conductivity of the soil. Meanwhile, mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient(R<sup>2</sup>) were used to evaluate the accuracy of the models. The accuracy of the machine learning model and empirical model were also compared. Then, the Monte Carlo simulation was used to analyze the stability of the models. The research results showed that the predicted performance of the machine learning models is significantly better than the empirical models. Among all the machine learning models, the R<sup>2</sup> of the PSO-ANN model is above 0.95, while both RMSE and MAE values are below 0.02 (W·m⁻¹·K⁻¹). In addition, the stability order of the machine learning models is PSO-XGBoost, PSO-ANN, PSO-RF, and PSO-SVM. Therefore, comprehensively considering the accuracy and stability of the four machine learning models, the PSO-ANN model is recommended to predict soil’s thermal conductivity under freeze–thaw action.https://www.mdpi.com/2075-5309/15/5/750freeze–thaw actionmachine learning modelsoil’s thermal conductivityMonte Carlo simulationcold regions
spellingShingle Yuwei Chen
Yadi Min
Haiqiang Jiang
Jing Luo
Mengxin Liu
Enliang Wang
Xingchao Liu
Ke Shi
Xiaoqi Li
Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
Buildings
freeze–thaw action
machine learning model
soil’s thermal conductivity
Monte Carlo simulation
cold regions
title Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
title_full Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
title_fullStr Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
title_full_unstemmed Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
title_short Investigation on Thermal Conductivity of Soil Under Freeze–Thaw Action Based on Machine Learning Models
title_sort investigation on thermal conductivity of soil under freeze thaw action based on machine learning models
topic freeze–thaw action
machine learning model
soil’s thermal conductivity
Monte Carlo simulation
cold regions
url https://www.mdpi.com/2075-5309/15/5/750
work_keys_str_mv AT yuweichen investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT yadimin investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT haiqiangjiang investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT jingluo investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT mengxinliu investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT enliangwang investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT xingchaoliu investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT keshi investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels
AT xiaoqili investigationonthermalconductivityofsoilunderfreezethawactionbasedonmachinelearningmodels