Abstract
Thermal conductivity is the unique thermal characteristic of soil that regulates the flow of heat energy. A significant impact on geothermal applications is caused by the heat conductivity of the soil. Generally thermal conductivity of soil depends on quartz content, degree of saturation, porosity, dry density, weather condition, and some topographical factors. In this study, four major factors are considered on which thermal conductivity of soil depends, viz., quartz content (QC), degree of saturation (S), porosity (η), and dry density (γ) of soil. In this study, three machine learning models, namely, adaptive neuro fuzzy inference system (ANFIS), extreme learning machine (ELM), and extreme gradient boosting (XGBoost) are used to predict thermal conductivity of soil more accurately and errorless. A total of 110 datasets have been used, where 70% (77 cases) of the dataset are used in the training phase and the rest 30% (33 cases) are used in the testing phase. Models’ performances are judged using various performance parameters like R2, a-20 index, VAF, WI, NS RMSE, MAE, SI, RSR, and WMAPE. Proposed models are also judged with the help of regression curve, error matrix, rank analysis, radar diagram, and William’s plot. Reliability index (β) and failure probability (Pf) are computed with the help of FOSM (first-order second moment) approach. The overall performance of ANFIS model is superior as compared to the other models, and ELM performs worst. To know the influence of each input parameters on the output, sensitivity analysis is performed.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs12517-023-11831-1/MediaObjects/12517_2023_11831_Fig10_HTML.png)
Similar content being viewed by others
Data availability
The data presented in this study are available on request from the corresponding author.
Abbreviations
- ML:
-
Machine learning
- Qc :
-
Quartz content
- η:
-
Porosity
- ELM:
-
Extreme learning machine
- R2 :
-
Coefficient of determination
- WI:
-
Willmott’s index of agreement
- RMSE:
-
Root mean square error
- SI:
-
Scatter index
- FOSM:
-
First-order second moment method
- Pf :
-
Probability of failure
- TMP:
-
Trend measuring parameters
- TR:
-
Training
- µ:
-
Average value
- Ee :
-
Error for EMP
- SOR:
-
Strength of relation
- ANFIS:
-
Adaptive neuro fuzzy inference system
- S:
-
Degree of saturation
- γ:
-
Dry density
- XGBoost:
-
Extreme gradient boosting
- VAF:
-
Variance account factor
- NS:
-
Nash Sutcliffe efficiency
- MAE:
-
Mean absolute error
- RSR:
-
RMSE-observation standard deviation ratio
- β:
-
Reliability index
- TC:
-
Thermal conductivity
- EMP:
-
Error measuring parameters
- TS:
-
Testing
- σ:
-
Standard deviation
- Et :
-
Error for TMP
- I:
-
Ideal value of EMP and TMP
References
Abu-Hamdeh NH, Reeder RC (2000) Soil thermal conductivity: effects of density, moisture content, salt concentration and organic matter. Soil Sci Soc Am J 64:1285–1290. https://doi.org/10.2136/sssaj2000.6441285x4
Abu-Hamdeh NH, Khdair AI, Reeder RC (2001) A comparison of two methods used to evaluate thermal conductivity for some soils. Int J Heat Mass Transf 44:1073–1078. https://doi.org/10.1016/S0017-9310(00)00144-7
Abu-Hamdeh NH (2003) Thermal properties of soils as affected by density and water content. Biosys Eng 86(1):97–102. https://doi.org/10.1016/S1537-5110(03)00112-0
Adrinek S, Singh RM, Janza M, Zerun M, Ryzynski G (2022) Evaluation of thermal conductivity estimation models with laboratory-measured thermal conductivities of sediments. Environ Earth Sci 81(15). https://doi.org/10.1007/s12665-022-10505-7
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. The 22nd ACM SIGKDD international conference. https://doi.org/10.1145/2939672.2939785
Cosenza P, Guerin R, Tabbagh A (2003) Relationship between thermal conductivity and water content of soils using numerical modelling. Eur J Soil Sci 54:581–587. https://doi.org/10.1046/j.1365-2389.2003.00539.x
Da TX, Chen T, He WK, Elshaikh T, Ma Y, Tong ZF (2022) Applying machine learning methods to estimate the thermal conductivity of bentonite for a high-level radioactive waste repository. Nucl Eng Des 392. https://doi.org/10.1016/j.nucengdes.2022.111765
Dong Y, McCartney JS, Lu N (2015) Critical review of thermal conductivity models for unsaturated soils. Geotech Geol Eng 33:207–221. https://doi.org/10.1007/s10706-015-9843-2
Do DT, Le NQK (2020) Using extreme gradient boosting to identify origin of replication in Saccharomyces cerevisiae via hybrid features. Genomics 112(3):2445–2451. https://doi.org/10.1016/j.ygeno.2020.01.017
Farouki QT (1981) Thermal properties of Soils in Cold Region. Cold Reg Sci Technol 5:67–75. https://doi.org/10.1016/0165-232X(81)90041-0
Huang GB, Zhi QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Huang GB, Wang DH, Lan Y (2011) Extreme learning machine: a survey. Int J Mach Learn Cybern 2:107–122
Hu G, Zhao L, Wu X, Li R, Wu T, **e C, Qiao Y, Shi J, Li W, Cheng G (2016) New Fourier-series-based analytical solution to the conduction-convection equation to calculate soil temperature, determine soil thermal properties, or estimate water flux. Int J Heat Mass Transf 95:815–823. https://doi.org/10.1016/j.ijheatmasstransfer.2015.11.078
Johansen O (1975) Thermal conductivity of soils. Ph.D thesis, Trondheim, Norway. (CRREL Draft Translation 637, 1977). ADA 044002.
Kardani N, Bardhan A, Samui P, Nazem M, Zhou A, Armaghani DJ (2021) A novel technique based on the improved firefly algorithm coupled with extreme learning machine (ELM-IFF) for predicting the thermal conductivity of soil. Eng Comput 38:3321–3340
Li KQ, Kang Q, Nie JY, Huang XW (2022a) Artificial neural network for predicting the thermal conductivity of soils based on a systematic database. Geothermics. https://doi.org/10.1016/j.geothermics.2022.102416
Li KQ, Liu Y, Kang Q (2022) Estimating the thermal conductivity of soils using six machine learning algorithms. International Communications in Heat and Mass Transfer 136. https://doi.org/10.1016/j.icheatmasstransfer.2022.106139
Liu W, Li R, Wu T, Shi X, Zhao L, Wu X, Hu G, Yao J, **ao Y, Ma J, Jiao Y, Wang S (2023) Simulation of soil thermal conductivity based on difference schemes: an empirical composition of 13 models. Int J Therm Sci. https://doi.org/10.1016/j.ijthermalsci.2023.108301
Malek K, Malek K, Khan MF (2021) Response of soil thermal conductivity to various soil properties. Int Commun Heat Mass Transfer 127:1–8. https://doi.org/10.1016/j.icheatmasstransfer.2021.105516
Mekonnen BK, Yang W, Hsieh TN, Liaw SH, Yang FL (2020) Accurate prediction of glucose concentration and identification of major contributing features from hardly distinguishable near-infrared spectroscopy. Biomed Signal Process Control. https://doi.org/10.1016/j.bspc.2020.101923
Mustafa R, Samui P, Kumari S (2022) Reliability analysis of gravity retaining wall using hybrid ANFIS. Infrastructures 7(9):121. https://doi.org/10.3390/infrastructures7090121
Mustafa R, Samui P, Kumari S, Mohamad ET, Bhatawdekar RM (2023) Probabilistic analysis of gravity retaining wall against bearing failure. Asian J Civil Eng 24(8):3099–3119. https://doi.org/10.1007/s42107-023-00697-z
Niu Y (2020) Walmart sales forecasting using XGBoost algorithm and feature engineering. Inst Elect Electron Eng. https://doi.org/10.1109/ICBASE51474.2020.00103
Nusier OK, Abu-Hamdeh NH (2003) Laboratory techniques to evaluate thermal conductivity for some soils. Heat Mass Transfer 39:119–123. https://doi.org/10.1007/s00231-002-0295-x
Rizvi ZH, Zaidi HH, Akhtar SJ, Sattari AS, Wuttke F (2020) Soft and hard computation methods for estimation of the effective thermal conductivity of sands. Heat Mass Transf 56:1947–1959
Rubin AJ, Ho CL (2021) Soil thermal conductivity estimated using a semi-analytical approach. Geothermics. https://doi.org/10.1016/j.geothermics.2021.102051
Sepaskhah AR, Boersma L (1979) Thermal conductivity of soils as a function of temperature and water content. Soil Sci Soc Am J 43:439–444. https://doi.org/10.2136/sssaj1979.03615995004300030003x
TaeBang H, Yoon S, Jeon H (2020) Application of machine learning methods to predict a thermal conductivity model for compacted bentonite. Annals of Nuclear Energy 142 https://doi.org/10.1016/j.anucene.2020.107395
Tokoro T, Ishikawa T, Shirai S, Nakamura T (2016) Estimation method for thermal conductivity of sandy soil with electrical characteristics. Soils Found 56(5):927–936. https://doi.org/10.1016/j.sandf.2016.08.016
Tong B, Gao Z, Horton R, Li Y, Wang L (2016) An empirical model for estimating soil thermal conductivity from soil water content and porosity. American Meteorological Society 601–613 https://doi.org/10.1175/JHM-D-15-0119.1
Wang C, Cai G, Liu X, Wu M (2022) Prediction of soil thermal conductivity based on intelligent computing model. Heat Mass Transfer 58:1695–1708. https://doi.org/10.1007/s00231-022-03209-y
Zhang R, Wu C, Goh ATC, Bohlke T, Zhang W (2021) Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning. Geosci Front 12(1):365–373. https://doi.org/10.1016/j.gsf.2020.03.003
Author information
Authors and Affiliations
Contributions
RM: Conceptualization, formal analysis, investigation, software, validation, visualization. KK: Writing—original draft. SK: Formal analysis, data curation. GK: Methodology. PS: Writing—review and editing.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Informed consent
Not applicable.
Conflict of interest
The authors declare no competing interests.
Additional information
Responsible Editor: Zeynal Abiddin Erguler
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Mustafa, R., Kumari, K., Kumari, S. et al. Probabilistic analysis of thermal conductivity of soil. Arab J Geosci 17, 22 (2024). https://doi.org/10.1007/s12517-023-11831-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-023-11831-1