Skip to main content

Advertisement

SpringerLink
Log in

Probabilistic machine learning for predicting desiccation cracks in clayey soils

  • Original Paper
  • Published:
Bulletin of Engineering Geology and the Environment Aims and scope Submit manuscript

Abstract

With frequent heatwaves and drought-downpour cycles, climate change gives rise to severe desiccation cracks. In this research, a probabilistic machine learning (ML) framework is developed to improve the deterministic models. Therefore, a complete set of data-driven soil and environment parameters, including initial water content (IWC), crack water content (CWC), final water content (FWC), soil layer thickness (SLT), temperature (Temp), and relative humidity (RH), is utilized as inputs to predict the crack surface ratio (CSR). Also, a comprehensive set of MLs, including an ensemble of regression trees (i.e., random forests [RF] and regression trees [RT]), gradient-boosted trees (viz. GBT and XGBT), support-vector machines (SVM), and artificial neural network-particle swarm optimization (ANN-PSO), is developed for predictions. Monte Carlo simulation (MCS) is then employed to insert uncertainties in the given models via shuffling and randomizing samples. Two sensitivity analyses, in particular input exclusion and partial dependence-individual conditional expectation plots, are further established to assess the prediction reliability. Results indicate that the performance ranking of developed MLs can be put as SVM > GBT > XGBT > ANN-PSO > RF > RT. However, according to the probabilistic modeling based on the MCS, GBTs are highly capable for predictions with the lowest errors and uncertainties. The performance order of the models in terms of the higher coefficient of determination and lower standard deviation is GBT > SVM > XGBT > RF > ANN-PSO > RT. The sensitivity analyses also categorized the parameter importance in the order of FWC > CWC > SLT > IWC > Temp > RH. These findings demonstrate the immense capabilities of probabilistic MLs under uncertainties by measuring prediction error variances and hence improving performance precision.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data availability

Data and materials can be obtained from the corresponding author upon reasonable requests.

References

  • Abu-Hejleh AN, Znidarčić D (1995) Desiccation theory for soft cohesive soils. Journal of Geotechnical Engineering 121(6):493–502

    Google Scholar 

  • Amarasiri AL, Kodikara JK, Costa S (2011) Numerical modelling of desiccation cracking. Int J Numer Anal Meth Geomech 35(1):82–96

    Google Scholar 

  • Armaghani DJ, Koopialipoor M, Bahri M, Hasanipanah M, Tahir MM (2020) A SVR-GWO technique to minimize flyrock distance resulting from blasting. Bull Eng Geol Env 79(8):4369–4385

    Google Scholar 

  • Baghbani A, Choudhury T, Costa S, Reiner J (2022) Application of artificial intelligence in geotechnical engineering: a state-of-the-art review. Earth Sci Rev 228:103991

    Google Scholar 

  • Bronswijk JJ, Bernardus. (1988) Modelling of water balance, cracking and subsidence of clay soils. J Hydrol 97(3–4):199–212

    Google Scholar 

  • Chen Y, Xu Y, Jamhiri B, Wang L, Li T (2022) Predicting uniaxial tensile strength of expansive soil with ensemble learning methods. Comput Geotech 150:104904

    Google Scholar 

  • Cheng Q, Tang CS, Zhu C, Li K, Shi B (2020a) Drying-induced soil shrinkage and desiccation cracking monitoring with distributed optical fiber sensing technique. Bull Eng Geol Env 79(8):3959–3970

    Google Scholar 

  • Cheng Q, Tang C-S, Zeng H, Zhu C, An Ni, Shi B (2020b) Effects of microstructure on desiccation cracking of a compacted soil. Eng Geol 265:105418

    Google Scholar 

  • Choudhury T, Costa S (2018) Prediction of parallel clay cracks using neural networks–a feasibility study. In: International Congress and Exhibition “Sustainable civil infrastructures: innovative infrastructure geotechnology”. Springer, Cham, pp 214–224

  • Cordero JA, Prat PC, Ledesma A (2021) Experimental analysis of desiccation cracks on a clayey silt from a large-scale test in natural conditions. Eng Geol 292:106256

    Google Scholar 

  • Costa S, Kodikara J, Thusyanthan NI (2008) Modelling of desiccation crack development in clay soils. In: Proc. 12th International Conference of IACMAG, Goa, India. pp 1099–1107

  • Costa S, Kodikara J (2009) Shrinkage development during soil desiccation. Unsaturated soils, two volume set: experimental studies in unsaturated soils and expansive soils (Vol. 1) & Theoretical and Numerical Advances in Unsaturated Soil Mechanics 2, 433

  • Costa S, Kodikara JK, Shannon B (2013) Salient factors controlling desiccation cracking of clay in laboratory experiments. Géotechnique 63(1):18–29

    Google Scholar 

  • Costa S, Kodikara J, Barbour SL, Fredlund DG (2018) Theoretical analysis of desiccation crack spacing of a thin, long soil layer. Acta Geotech 13(1):39–49

    Google Scholar 

  • Cuadrado A, Najdi A, Ledesma A, Olivella S, Prat PC (2022) THM analysis of a soil drying test in an environmental chamber: the role of boundary conditions. Comput Geotech 141:104495

    Google Scholar 

  • Cui YJ, Tang CS, Tang AM, Ta AN (2014) Investigation of soil desiccation cracking using an environmental chamber. Rivista Italiana Di Geotecnica 24(1):9–20

    Google Scholar 

  • Dao DV, Ly HB, Trinh SH, Le TT, Pham BT (2019) Artificial intelligence approaches for prediction of compressive strength of geopolymer concrete. Materials 12(6):983

    Google Scholar 

  • Feng D, Gong J, Ni X, Ren J (2021) Experimental and numerical analysis of soil cracking characteristics under evaporation. Math Probl Eng 2021

  • Goodman CC, Vahedifard F (2022) Effects of sample thickness and shape on cracking patterns and crack depth in a compacted clay. In Geo-Congress 169–179

  • Han XL, Jiang NJ, Yang YF, Choi J, Singh DN, Beta P, Wang YJ (2022) Deep learning based approach for the instance segmentation of clayey soil desiccation cracks. Comput Geotech 146:104733

  • Hanson JA, Hardin BO, Mahboub K (1994) Fracture Toughness of Compacted Cohesive Soils Using Ring Test. Journal of Geotechnical Engineering 120(5):872–891

    Google Scholar 

  • Hun DA, Yvonnet J, Guilleminot J, Dadda A, Tang AM, Bornert M (2021) Desiccation cracking of heterogeneous clayey soil: experiments, modelling and simulations. Eng Fract Mech 258:108065

    Google Scholar 

  • Jamhiri B, Xu Y, Jalal FE (2022) Cracking propagation in expansive soils under desiccation and stabilization planning using Bayesian inference and Markov decision chains. Environmen Sci Pollut Res 1–23

  • Jamhiri B, Xu Y, Jalal FE, Chen Y (2021) Hybridizing neural network with trend-adjusted exponential smoothing for time-dependent resistance forecast of stabilized fine sands under rapid shearing. Transp Infrastruct Geotechnol 1–20

  • Jamhiri B, Xu Y, Shadabfar M, Jalal FE (2023) Probabilistic estimation of thermal crack propagation in clays with Gaussian processes and random fields. Geomech Energy Environ 100454

  • Julina M, Thyagaraj T (2019) Quantification of desiccation cracks using X-ray tomography for tracing shrinkage path of compacted expansive soil. Acta Geotech 14(1):35–56

    Google Scholar 

  • Kodikara J, Rajeev P, Rhoden NJ (2011) Determination of thermal diffusivity of soil using infrared thermal imaging. Can Geotech J 48(8):1295–1302

    Google Scholar 

  • Kodikara JK, Choi X (2006) A simplified analytical model for desiccation cracking of clay layers in laboratory tests. In Unsaturated Soils 2006:2558–2569

    Google Scholar 

  • Konrad J-M, Ayad R (1997a) Desiccation of a sensitive clay: field experimental observations. Can Geotech J 34(6):929–942

  • Konrad J-M, Ayad R (1997b) A idealized framework for the analysis of cohesive soils undergoing desiccation. Can Geotech J 34(4):477–488

  • Lakshmikantha MR, Prat PC, Ledesma A (2012) Experimental evidence of size effect in soil cracking. Can Geotech J 49(3):264–284

    Google Scholar 

  • Lakshmikantha RM, Prat Catalán P, Ledesma Villalba A (2018) Boundary effects in the desiccation of soil layers with controlled environmental conditions. Geotech Test J 41(4):675–697

    Google Scholar 

  • Li JH, Zhang LM (2010) Geometric parameters and REV of a crack network in soil. Comput Geotech 37(4):466–475

    Google Scholar 

  • Li JH, Lu Z, Guo LB, Zhang LM (2017) Experimental study on soil-water characteristic curve for silty clay with desiccation cracks. Eng Geol 218:70–76

  • Lin ZY, Wang YS, Tang CS, Cheng Q, Zeng H, Liu C, Shi B (2021) Discrete element modelling of desiccation cracking in thin clay layer under different basal boundary conditions. Comput Geotech 130:103931

    Google Scholar 

  • Liu W, Fan H, Xia M (2022) Credit scoring based on tree-enhanced gradient boosting decision trees. Expert Syst Appl 189:116034

  • Lu Y, Liu S, Weng L, Wang L, Li Z, Lei Xu (2016) Fractal analysis of cracking in a clayey soil under freeze–thaw cycles. Eng Geol 208:93–99

    Google Scholar 

  • Ly HB, Nguyen MH, Pham BT (2021) Metaheuristic optimization of Levenberg–Marquardt-based artificial neural network using particle swarm optimization for prediction of foamed concrete compressive strength. Neural Comput Appl 33(24):17331–17351

    Google Scholar 

  • Miao L, Houston SL, Cui Y, Yuan J (2007) Relationship between soil structure and mechanical behavior for an expansive unsaturated clay. Can Geotech J 44(2):126–137

    Google Scholar 

  • Miller GA, Hassanikhah A, Varsei M (2015) Desiccation crack depth and tensile strength in compacted soil. In unsaturated soil mechanics-from theory to practice: proceedings of the 6th Asia Pacific Conference on Unsaturated Soils (Guilin, China, 23–26 October 2015), 79. CRC Press

  • Mohamad ET, Jahed Armaghani D, Momeni E, Abad ANK, S. V. (2015) Prediction of the unconfined compressive strength of soft rocks: a PSO-based ANN approach. Bull Eng Geol Env 74(3):745–757

    Google Scholar 

  • Moosbauer J, Herbinger J, Casalicchio G, Lindauer M, Bischl B (2021) Explaining hyperparameter optimization via partial dependence plots. Adv Neural Inf Process Syst 34

  • Morris PH, Graham J, Williams DJ (1992) Cracking in drying soils. Can Geotech J 29(2):263–277

    Google Scholar 

  • Morris PH, Graham J, Williams DJ (1994) Crack depths in drying clays using fracture mechanics. Geotechnical Special Publication, 43:40–53

    Google Scholar 

  • Nahlawi H, Kodikara JK (2006) Laboratory experiments on desiccation cracking of thin soil layers. Geotech Geol Eng 24(6):1641–1664

    Google Scholar 

  • Péron H, Delenne J-Y, Laloui L, Youssoufi MSE (2009) Discrete element modelling of drying shrinkage and cracking of soils. Comput Geotech 36(1–2):61–69

    Google Scholar 

  • Pham BT, Nguyen MD, Van Dao D, Prakash I, Ly HB, Le TT, Ho LS, Nguyen KT, Ngo TQ, Hoang V, Ngo HT (2019) Development of artificial intelligence models for the prediction of compression coefficient of soil: an application of Monte Carlo sensitivity analysis. Sci Total Environ 679:172–184

  • Picornell MIGUEL, Lytton RL (1989) Field measurement of shrinkage crack depth in expansive soils. Transp Res Rec 1219:121–130

    Google Scholar 

  • Qiu Y, Zhou J, Khandelwal M, Yang H, Yang P, Li C (2021) Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Eng Comput 1–18

  • ShadabFar M, Huang H (2019) Simplified algorithm for reliability sensitivity analysis of structures: a spreadsheet implementation. PLoS One 14(3):e0213199

    Google Scholar 

  • Singh UK, Jamei M, Karbasi M, Malik A, Pandey M (2022) Application of a modern multi-level ensemble approach for the estimation of critical shear stress in cohesive sediment mixture. J Hydrol 127549

  • Song W-K, Cui Y-J (2020) Modelling of water evaporation from cracked clayey soil. Eng Geol 266:105465

    Google Scholar 

  • Syarif I, Prugel-Bennett A, Wills G (2016) SVM parameter optimization using grid search and genetic algorithm to improve classification performance. Telkomnika 14(4):1502

    Google Scholar 

  • Tang CS, Cui YJ, Tang AM, Shi B (2010) Experiment evidence on the temperature dependence of desiccation cracking behavior of clayey soils. Eng Geol 114(3–4):261–266

    Google Scholar 

  • Tang CS, Cui YJ, Shi B, Tang AM, Liu C (2011a) Desiccation and cracking behaviour of clay layer from slurry state under wetting–drying cycles. Geoderma 166(1):111–118

    Google Scholar 

  • Tang CS, Shi B, Liu C, Gao L, Inyang HI (2011b) Experimental investigation of the desiccation cracking behavior of soil layers during drying. J Mater Civ Eng 23(6):873–878

    Google Scholar 

  • Tang CS, Shi B, Liu C, Suo WB, Gao L (2011c) Experimental characterization of shrinkage and desiccation cracking in thin clay layer. Appl Clay Sci 52(1–2):69–77

    Google Scholar 

  • Tang CS, Zhu C, Leng T, Shi B, Cheng Q, Zeng H (2019) Three-dimensional characterization of desiccation cracking behavior of compacted clayey soil using X-ray computed tomography. Eng Geol 255:1–10

    Google Scholar 

  • Tang CS, Zhu C, Cheng Q, Zeng H, Xu JJ, Tian BG, Shi B (2021) Desiccation cracking of soils: a review of investigation approaches, underlying mechanisms, and influencing factors. Earth Sci Rev 103586

  • Tollenaar RN, Van Paassen LA, Jommi C (2017) Observations on the desiccation and cracking of clay layers. Eng Geol 230:23–31

    Google Scholar 

  • Trabelsi H, Jamei M, Zenzri H, Olivella S (2012) Crack patterns in clayey soils: experiments and modelling. Int J Numer Anal Meth Geomech 36(11):1410–1433

    Google Scholar 

  • Vu HQ, Hu Y, Fredlund DG (2007) Analysis of soil suction changes in expansive Regina clay. In 60th Canadian Geotechnical Conference, OttawaGeo 1–8

  • Wan Y, Xue Q, Liu L, Wang S (2018) Relationship between the shrinkage crack characteristics and the water content gradient of compacted clay liner in a landfill final cover. Soils Found 58(6):1435–1445

    Google Scholar 

  • Wang Y, Gao X, Jiang P, Guo X, Wang R, Guan Z, Chen L, Xu C (2022) An extreme gradient boosting technique to estimate TBM penetration rate and prediction platform. Bull Eng Geol Environ 81(1):1–19

  • Xu JJ, Zhang H, Tang CS, Cheng Q, Liu B, Shi B (2022) Automatic soil desiccation crack recognition using deep learning. Geotechnique 72(4):337–349

    Google Scholar 

  • Xu JJ, Tang CS, Cheng Q, Xu QL, Inyang HI, Lin ZY, Shi B (2021) Investigation on desiccation cracking behavior of clayey soils with a perspective of fracture mechanics: a review. J Soils Sediments 1–30

  • Yesiller N, Miller CJ, Inci G, Yaldo K (2000) Desiccation and cracking behavior of three compacted landfill liner soils. Eng Geol 57(1–2):105–121

    Google Scholar 

  • Zeng H, Tang CS, Zhu C, Vahedifard F, Cheng Q, Shi B (2022) Desiccation cracking of soil subjected to different environmental relative humidity conditions. Eng Geol 106536

  • Zhou M, Chen J, Huang H, Zhang D, Zhao S, Shadabfar M (2021) Multi-source data driven method for assessing the rock mass quality of a NATM tunnel face via hybrid ensemble learning models. Int J Rock Mech Min Sci 147:104914

    Google Scholar 

Download references

Acknowledgements

The authors hereby extend their gratitude to the Key Special Project of the Ministry of Science and Technology of the People’s Republic of China for Monitoring, Warning, and Prevention of Major Natural Disasters for their support, with special thanks to Professor Chao Sheng Tang for his valuable comments.

Author information

Authors and Affiliations

  1. Department of Civil Engineering, State Key Laboratory of Ocean Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    Babak Jamhiri & Yongfu Xu

  2. Department of Civil Engineering, Center for Infrastructure Sustainability and Resilience Research, Sharif University of Technology, Tehran, 145888-9694, Iran

    Mahdi Shadabfar

  3. School of Engineering, Deakin University, Waurn Ponds, Geelong, VIC, 3217, Australia

    Susanga Costa

Authors
  1. Babak Jamhiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yongfu Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahdi Shadabfar
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Susanga Costa
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Babak Jamhiri: Conceptualization, methodology, formal analysis, visualization, and original draft. Yongfu Xu: Supervision, review and editing. Mahdi Shadabfar: Methodology, validation, review and editing. Susanga Costa: Reviewing and editing.

Corresponding author

Correspondence to Yongfu Xu.

Ethics declarations

Competing interests

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jamhiri, B., Xu, Y., Shadabfar, M. et al. Probabilistic machine learning for predicting desiccation cracks in clayey soils. Bull Eng Geol Environ 82, 355 (2023). https://doi.org/10.1007/s10064-023-03366-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10064-023-03366-2

Keywords

Search

Navigation