Top

Geotechnical and Geological Engineering

Published in:

13-08-2023 | Original Paper

A Comparative Analysis of Machine Learning Models for Predicting Loess Collapse Potential

Authors: Sahand Motameni, Fateme Rostami, Sara Farzai, Abbas Soroush

Published in: Geotechnical and Geological Engineering | Issue 2/2024

Activate our intelligent search to find suitable subject content or patents.

search-config

AI-assisted search

Off

Abstract

Collapsible soils, particularly loessial soils, present significant geotechnical engineering hazards that should be carefully investigated before any construction can commence. However, it is generally difficult to estimate the collapse potential of soils based on the relative contributions of each of the numerous influencing factors. Therefore, the main objective of this study is to find a reliable method for predicting the collapse potential of loessial soils by using machine learning-based tools. In this regard, details of 766 performed oedometer test were gathered from the published literature containing six variables for each data point including dry unit weight of soil, plasticity index, void ratio, degree of saturation, inundation stress at which the oedometer test was conducted, and the collapse potential. Then, prediction for the degree of collapsibility of loess was performed by employing three well-known supervised machine learning tools, namely Multi-Layer Perceptron Neural Network (MLPNN), Radial Basis Function Network (RBFN), and Naïve Bayesian Classifier (NBC), and outcomes were analyzed based on a comparative view. Simulation results indicate the superiority of MLPNN in estimating the degree of collapsibility of loess against other models in terms of performance error metrics and precision criterion.

previous article Soft Computing Applications for Optimum Rock Fragmentation: An Advanced Overview

next article Modeling the Post-construction Deformation of Spillways over Concrete-Faced Rockfill Dams

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

inform now

Available only for authorised users

Abd El Aal AK, Rouaiguia A (2020) Determination of the geotechnical parameters of soils behavior for safe future urban development, Najran Area, Saudi Arabia: implications for settlements mitigation. Geotech Geol Eng 38(1):695–712. https://doi.org/10.1007/s10706-019-01058-xCrossRef

Al-Harthi AA, Bankher KA (1999) Collapsing loess-like soil in western Saudi Arabia. J Arid Environ 41(4):383–399. https://doi.org/10.1006/jare.1999.0494CrossRef

Assallay AM, Rogers CDF, Smalley IJ (1996) Engineering properties of loess in Libya. J Arid Environ 32(4):373–386. https://doi.org/10.1006/jare.1996.0031CrossRef

ASTM, D5333 (1996) Standard test method for measurement of collapse potential of soils. ASTM International. https://doi.org/10.1520/D5333-92R96.

Basma AA, Kallas N (2004) Modeling soil collapse by artificial neural networks. Geotech Geol Eng 22(3):427–438. https://doi.org/10.1023/B:GEGE.0000025044.72718.dbCrossRef

Bell FG (2013) Engineering properties of soils and rocks. Elsevier

Bell FG, Culshaw MG, Northmore KJ (2003) The metastability of some gull-fill materials from Allington, Kent, UK. Q J Eng GeolHydrogeol 36(3):217–229. https://doi.org/10.1144/1470-9236/02-005CrossRef

Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning. Springer, Berlin

Bolouri Bazzaz J, Marouf MA (2012) Identification and evaluation of mechanical behavior collapsible soil (case study in north eastern of Iran. Sci Q J Iran Assoc Eng Geol 5(1 & 2):27–40

Cabalar AF, Cevik A, Gokceoglu C (2012) Some applications of adaptive neuro-fuzzy inference system (ANFIS) in geotechnical engineering. Comput Geotech 40:14–33CrossRef

Delage, P., Cui, Y.-J., & Antoine, P. (2008). Geotechnical problems related with loess deposits in Northern France. ArXiv Preprint arXiv:0803.1435. https://doi.org/10.48550/arXiv.0803.1435.

Derbyshire E (2001) Geological hazards in loess terrain, with particular reference to the loess regions of China. Earth Sci Rev 54(1–3):231–260. https://doi.org/10.1016/S0012-8252(01)00050-2ADSCrossRef

Du K-L, Swamy MN (2013) Neural networks and statistical learning. Springer, Berlin

Dušan B, Zoran B, Čebašek V, Šušić N (2014) Characterization of collapsing loess by seismic dilatometer. Eng Geol 181:180–189CrossRef

Follmer LR (1996) Loess studies in central United States: evolution of concepts. Eng Geol 45(1–4):287–304. https://doi.org/10.1016/j.enggeo.2014.07.011CrossRef

Fredlund DG, Gan JK (1995) The collapse mechanism of a soil subjected to one-dimensional loading and wetting. Genesis and properties of collapsible soils. Springer, Dordrecht, pp 173–205CrossRef

Garakani AA, Haeri SM, Khosravi A, Habibagahi G (2015) Hydro-mechanical behavior of undisturbed collapsible loessial soils under different stress state conditions. Eng Geol 195:28–41. https://doi.org/10.1016/j.enggeo.2015.05.026CrossRef

Giménez RG, de la Villa RV, Martín JG (2012) Characterization of loess in central Spain: a microstructural study. Environ Earth Sci 65(7):2125–2137. https://doi.org/10.1007/s12665-011-1193-7ADSCrossRef

Habibagahi G (2004) Prediction of collapse potential for compacted soils using artificial neural networks. Sci Iran 11(1):1–20

Haeri SM, Zamani A, Garakani AA (2012) Collapse potential and permeability of undisturbed and remolded loessial soil samples. Unsaturated soils: Research and applications. Springer, Berlin, pp 301–308CrossRef

Hafezi Moghaddas N, Nikudel M, Bahrami K (2011) Evaluation of collapsibility of loess deposits of Gharnaveh catchment in north of Kalale, Golestan province. Sci Q J Iran Assoc Eng Geol 4(1 & 2):39–46

Haykin S (2010) Neural networks and learning machines, 3/E. Pearson Education India.

Houston SL, Houston WN, Spadola DJ (1988) Prediction of field collapse of soils due to wetting. J Geotech Eng 114(1):40–58. https://doi.org/10.1061/(ASCE)0733-9410(1988)114:1(40)CrossRef

Iranpour B (2016) The influence of nanomaterials on collapsible soil treatment. Eng Geol 205:40–53. https://doi.org/10.1016/j.enggeo.2016.02.015CrossRef

Jefferson I, Smalley I, Northmore K (2003) Consequence of a modest loess fall over southern and midland England. Mercian Geol 15(4):199–208

Jefferson I, Rogers C, Evstatiev D, Karastanev D (2005) Treatment of metastable loess soils Lessons from Eastern Europe. Elsevier geo-engineering book series. Elsevier, London, pp 723–762

Juang CH, Elton DJ (1997) Predicting collapse potential of soils with neural networks. Trans Res Rec J Trans Res Board 1582(1):22–28. https://doi.org/10.3141/1582-04CrossRef

Karimi A, Khademi H, Kehl M, Jalalian A (2009) Distribution, lithology and provenance of peridesert loess deposits in northeastern Iran. Geoderma 148(3–4):241–250. https://doi.org/10.1016/j.geoderma.2008.10.008ADSCrossRef

Khodabandeh MA, Nokande S, Besharatinezhad A, Sadeghi B, Hosseini SM (2020) The effect of acidic and alkaline chemical solutions on the behavior of collapsible soils. Period Polytech Civ Eng 64(3):939–950. https://doi.org/10.3311/PPci.15643CrossRef

Kim D, Kang S-S (2013) Engineering properties of compacted loesses as construction materials. KSCE J Civ Eng 17(2):335–341. https://doi.org/10.1007/s12205-013-0872-1CrossRef

Langroudi AA, Jefferson I (2013) Collapsibility in calcareous clayey loess: A factor of stress-hydraulic history. Int J Geomate Geotech Constr Mater Environ 5(1):620–626

Li Y, Shi W, Aydin A, Beroya-Eitner MA, Gao G (2020) Loess genesis and worldwide distribution. Earth Sci Rev 201:102947. https://doi.org/10.1016/j.earscirev.2019.102947CrossRef

Liu Z, Liu F, Ma F, Wang M, Bai X, Zheng Y, Yin H, Zhang G (2016) Collapsibility, composition, and microstructure of loess in China. Can Geotech J 53(4):673–686. https://doi.org/10.1139/cgj-2015-0285CrossRef

Ma F, Yang J, Bai X (2017) Water sensitivity and microstructure of compacted loess. Trans Geotech 11:41–56. https://doi.org/10.1016/j.trgeo.2017.03.003CrossRef

Mansour ZM, Chik Z, Taha MR (2008) On the procedures of soil collapse potential evaluation. J Appl Sci 8(23):4434–4439. https://doi.org/10.3923/jas.2008.4434.4439CrossRef

Meier, C., Boley, C., & Zou, Y. (2009). Practical relevance of collapse behavior and microstructure of loess soils in Afghanistan. In: Proceedings of the 17th International Conference on Soil Mechanics and Geotechnical Engineering (Volumes 1, 2, 3 and 4), 738–741. https://doi.org/10.3233/978-1-60750-031-5-738.

Munoz-Castelblanco J, Delage P, Pereira J-M, Cui Y-J (2011) Some aspects of the compression and collapse behavior of an unsaturated natural loess. Géotechnique Letters 1(2):17–22. https://doi.org/10.1680/geolett.11.00003CrossRef

Murty MN, Devi VS (2011) Pattern recognition: An algorithmic approach. Springer, BerlinCrossRef

Nouaouria MS, Guenfoud M, Lafifi B (2008) Engineering properties of loess in Algeria. Eng Geol 99(1–2):85–90. https://doi.org/10.1016/j.enggeo.2008.01.013CrossRef

Owens RL (1990) Collapsible soil hazard map for the southern Wasatch Front [PhD Thesis]. Brigham Young University. Department of Civil Engineering.

Pan L, Zhu J-G, Zhang Y-F (2021) Evaluation of structural strength and parameters of collapsible loess. Int J Geomech 21(6):04021066. https://doi.org/10.1061/(ASCE)GM.1943-5622.0001978CrossRef

Phien-Wej N, Pientong T, Balasubramaniam AS (1992) Collapse and strength characteristics of loess in Thailand. Eng Geol 32(1–2):59–72. https://doi.org/10.1016/0013-7952(92)90018-TCrossRef

Powers, D. M. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. ArXiv Preprint arXiv:2010.16061. https://doi.org/10.48550/arXiv.2010.16061.

Pye K (1984) Loess. Prog Phys Geogr 8(2):176–217CrossRef

Qian Z, Lu X, Yang W, Cui Q (2014) Behaviour of micropiles in collapsible loess under tension or compression load. Geomech Eng. https://doi.org/10.12989/GAE.2014.7.5.477CrossRef

Rabbi A, Cameron DA, Rahman MM (2014) Role of matric suction on wetting-induced collapse settlement of silty sand. Unsat Soil Res Appl. https://doi.org/10.1201/b17034-17CrossRef

Rezaei M, Ajalloeian R, Ghafoori M (2012) Geotechnical properties of problematic soils emphasis on collapsible cases. Int J Geosci 3(1):105–110. https://doi.org/10.4236/ijg.2012.31012CrossRef

Rouaiguia A, Dahim MA (2021) Geotechnical properties of najran soil, Kingdom of Saudi Arabia. Yanbu J Eng Sci 5(1):64–76CrossRef

Sakr M, Mashhour M, Hanna A (2008) Egyptian collapsible soils and their improvement. In: GeoCongress 2008 Geosustainability and Geohazard Mitigation (pp. 654–661). https://doi.org/10.1061/40971(310)81.

Salehi T, Shokrian M, Modirrousta A, Khodabandeh M, Heidari M (2015) Estimation of the collapse potential of loess soils in Golestan Province using neural networks and neuro-fuzzy systems. Arab J Geosci 8(11):9557–9567. https://doi.org/10.1007/s12517-015-1894-4CrossRef

Shafiei A, Dusseault MB, Heidari M (2008) Engineering properties of loess from NE Iran. GeoEdmonton 8:61

Smalley I (1995) Making the material: The formation of silt sized primary mineral particles for loess deposits. Quatern Sci Rev 14(7–8):645–651. https://doi.org/10.1016/0277-3791(95)00046-1ADSCrossRef

Uysal F (2020) Prediction of collapse potential of soils using gene expression programming and parametric study. Arab J Geosci 13(19):1–13. https://doi.org/10.1007/s12517-020-06050-xCrossRef

Wang L, Li X-A, Li L-C, Hong B, Yao W, Lei H, Zhang C (2020) Characterization of the collapsible mechanisms of Malan loess on the Chinese Loess Plateau and their effects on eroded loess landforms. Hum Ecol Risk Assess Int J 26(9):2541–2566. https://doi.org/10.1080/10807039.2020.1721265CrossRef

Xie W, Li P, Zhang M, Cheng T, Wang Y (2018) Collapse behavior and microstructural evolution of loess soils from the Loess Plateau of China. J Mt Sci 15(8):1642–1657. https://doi.org/10.1007/s11629-018-5006-2CrossRef

Xing Y, Gao D, Jin S, Zhang A, Guo M (2019) Study on mechanical behaviors of unsaturated loess in terms of moistening level. KSCE J Civ Eng 23(3):1055–1063. https://doi.org/10.1007/s12205-019-0848-xCrossRef

Yang Y (1989) Study of the mechanism of loess collapse. Sci Chin Ser B Chem Life Sci Earth Sci 32(5):604–617

Yates K, Fenton CH, Bell DH (2018) A review of the geotechnical characteristics of loess and loess-derived soils from Canterbury, South Island, New Zealand. Eng Geol 236:11–21. https://doi.org/10.1016/j.enggeo.2017.08.001CrossRef

Zárate MA (2003) Loess of southern south America. Quatern Sci Rev 22(18–19):1987–2006. https://doi.org/10.1016/S0277-3791(03)00165-3ADSCrossRef

Zhang S (2011) Assessment of loess collapsibility with GRNN. In: Ma Ming (ed) Communication Systems and Information Technology. Springer, Berlin, pp 745–752CrossRef

Zhang W (2020) MARS use in prediction of collapse potential for compacted soils. In: Zhang Wengang (ed) MARS applications in geotechnical engineering systems. Springer, Singapore, pp 27–46CrossRef

Zhang Y, Hu Z, Chen H, Xue T (2018a) Experimental investigation of the behavior of collapsible loess treated with the acid-addition pre-soaking method. KSCE J Civ Eng 22(11):4373–4384. https://doi.org/10.1007/s12205-017-0170-4CrossRef

Zhang Y, Hu Z, Xue Z (2018b) A new method of assessing the collapse sensitivity of loess. Bull Eng Geol Env 77(4):1287–1298. https://doi.org/10.1007/s10064-018-1372-9CrossRef

Zhang W, Sun Y, Chen W, Song Y, Zhang J (2019) Collapsibility, composition, and microfabric of the coastal zone loess around the Bohai Sea China. Eng Geol 257:105142. https://doi.org/10.1016/j.enggeo.2019.05.019CrossRef

Zhangjian XU, Zaiguan LIN, Zhang M (2007) Loess in China and loess landslides. Chin J Rock Mech Eng 26(7):1297–1312

Title: A Comparative Analysis of Machine Learning Models for Predicting Loess Collapse Potential
Authors: Sahand Motameni
Fateme Rostami
Sara Farzai
Abbas Soroush
Publication date: 13-08-2023
Publisher: Springer International Publishing
Published in: Geotechnical and Geological Engineering / Issue 2/2024
Print ISSN: 0960-3182
Electronic ISSN: 1573-1529
DOI: https://doi.org/10.1007/s10706-023-02593-4

Springer Professional

Abstract

Please log in to get access to your license.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Other articles of this Issue 2/2024

Site Characterization of Urban Centers from Himalayan Region Using Active and Passive Seismic Methods

The characteristics of the two-component grout on the stress-state in segmental lining

A Quantitative Rockfall Risk Analysis System for Highway Rock Slopes

Permeability Behavior of Tropical Sapric Peat Under Isotropic Compression

In-situ Creep Behavior of Expansive Soils Based on Pressuremeter Test

Numerical Simulation Study on Shear Properties of Rock Joint Under CNS Boundary Conditions