Abstract
California Bearing Ratio method is an empirical method of design of flexible pavement developed by California Division of Highways, in 1928 for the design of Roadways, Railways and Airfield. In order to design a pavement by CBR method, the soaked CBR value of soil is evaluated which takes around 4 days or 96 h to complete the test process. The soaked CBR value is used to determine the total thickness of flexible pavement needed to cover the subgrade of the known CBR value. However, the determination of soaked CBR in the laboratory is time-consuming and requires skilled labour and supervision, prompting researchers to explore alternating approaches. Various machine learning methods including artificial neural network (ANN), deep neural networks (DNN) and gene expression programming (GEP) have been previously employed to predict CBR values. However, these methods come with inherent limitations such as sensitivity to hyper-parameters, limited flexibility, lack of interpretability and explainability which raise concerns in critical decision-making applications. In the present study, we have endeavoured to address the shortcomings observed in deep neural networks models and proposed an improved and efficient prediction model for California Bearing Ratio. Three distinct models have been developed using three different methodologies: a fuzzy inference system, an artificial neural network & an adaptive neuro-fuzzy inference system. To conduct the study, large datasets of 2000 Soil samples have been used which were tested under the scheme of Pradhan Mantri Gram Sadak Yojana (PMGSY). Out of the total data, 1501 datasets have been used for training, 499 datasets have been used for testing and for validation of the proposed model, datasets of 15nos soil samples have been used which were entirely separated from the datasets used for training and testing. Upon analysing the prediction results, we found that while ANN demonstrates commendable accuracy in predicting CBR values, the predictability of the manually developed FIS model falls short. Intriguingly, the ANFIS model surpasses both ANN and FIS in terms of predictive accuracy with an a-20 index of 0.83 and R values of 0.92. In Conclusion, our study suggests that the hybrid model of ANN and FIS (ANFIS) emerges as a promising approach for predicting CBR values, offering enhanced accuracy compared to traditional methods and other machine learning models.
Similar content being viewed by others
References
Johnson DG, Bhatia H (1969) The engineering characteristics of the lateritic gravels of Ghana. In: Proceedings of 7th international conference on soil mechanics and foundation engineering
Uyanik KG, Guler N (2013) A study on multiple linear regression analysis. Soc Behav Sci 2013:234–240
Agarwal KB, Ghanekar KD (1970) Prediction of CBR from plasticity characteristics of soil. In: South-east Asian conference on soil engineering
Stephens D (1992) Variation of the California Bearing Ratio in some synthetic Clayey soils. Civil Engineering Siviele Ingenieurswese, pp 379–380
Al-Refeai T, Al-Suhaibani A (1997) Prediction of CBR using dynamic cone penetrometer. J King Saud Univ Eng Sci 9(2):191–203
NCHRP (2001) Guide for mechanistic-empirical design of new and rehabilitated structures. National Cooperative Highway Research Program Transportation Research Board National Research Council, Illinois
Kin MW (2006) California Bearing Ratio Correlation with Soil Index Properties. Master Degree Project Faculty of Civil Engineering University of Technology, Malayasia
Das R, Wason HR, Sharma M (2011) Global regression relations for conversion of surface wave and body wave magnitudes to moment magnitude. Nat Hazards 59(2):801–810
Das R, Wason HR, Sharma M (2013) General Orthogonal Regression relation between body and moment magnitudes. Seismol Res Lett 84(2):219–224
Erdik T, Pektas AO (2019) Rock slope damage level prediction by using multivariate adaptive regression splines (MARS). Neural Comput Appl 31:2269–2278
Patel RS, Desai M (2010) CBR Predicted by Index Properties for Alluvial Soils of South Gujarat. In: Indian geotechnical conference
Yildrin B, Gunaydin O (2011) Estimation of California bearing ratio by using soft computing systems. Expert Syst Appl 38:6381–6391
Alawi M, Rajab M (2013) Prediction of California bearing ratio of subbase layer using multiple linear regression models. Road Mater Pavement Des 14(1):211–219
Varghese V, Babu S, Bijukumar R, Cyrus S, Abraham B (2013) Artificial neural networks: a solution to the ambiguity in prediction of engineering properties of fine-grained soils. Geotech Geol Eng 31(4):1187–1205
Kumar KSP, Nanduri PMBRK, Kumar PND (2014) Validation of predicted California bearing ratio values from different correlations. Am J Eng Res 3(8):344–352
Ramasubbarao GV, Siva Sankar G (2013) Predicting soaked CBR value of fine grained soils using index and compaction characteristics. Jordan J Civ Eng 7(3):354–360
Talukdar DK (2014) A study of correlation between California bearing ratio (CBR) value with other properties of soil. Int J Emerg Technol Adv Eng 4(1):559–562
Sabat KA (2015) Prediction of california bearing ratio of a stabilized expansive soil using artificial neural network and support vector machine. Electron J Geotech Eng 20(3):981–991
Araoujo W, Ruiz G (2013) Correlation equations of CBR with index properties of soil in the city of Piura. In: Proceeding of 14th LACCEI international multi-conference for engineering, education & technology
Erzin Y, Turkoz D (2016) Use of neural networks for the prediction of the CBR value of some Aegean sands. Neural Comput Appl 27:1415–1426
Rehman ZU, Khalid U, Farooq K, Mujtaba H (2017) Prediction of CBR value from index properties of different soils. Tech J Univ Eng Technol Taxila 22(2):18–26
Ghorbani A, Hadi H (2018) Prediction of UCS and CBR of microsilica-lime stabilized sulfate silty sand using ANN and EPR models; application to the deep soil mixing. Soils Found 58(1):34–49
Farias I, William A, Gaby R (2018) Prediction of California bearing ratio from index properties of soils using parametric and non-parametric models. Geotech Geol Eng 36(6):3485–3498
Suthar M, Aggarwal P (2018) Predicting CBR value of stabilized pond ash with lime and lime sludge using ANN and MR models. Int J Geosynth Ground Eng 4
Katte V, Mfoyet S, Bertille M, Wouatong AS, Bezeng L (2019) Correlation of California bearing ratio (CBR) value with soil properties of road subgrade soil. Geotech Geol Eng 37(1):217–234
Tenpe A, Patel A (2018) Application of genetic expression programming and artificial neural network for prediction of CBR. Road Mater Pavement Des 19(1):1–18
Taskiran T (2010) Prediction of California bearing ratio (CBR) of fine grained soils by AI methods. Adv Eng Softw 41(6):886–892
Fikret KT, Kaya Y (2019) Prediction of the California bearing ratio (CBR) of compacted soils by using GMDH-type neural network. Eur Phys J Plus 134:0–15
Alam KS, Abhijit M, Amit S (2020) Prediction of CBR value of Fine-grained soils of West bengal region by Linear-regression Analysis. In: Proceedings of international conference on energy and sustainable development 2020
Al-Busultan S, Gafel KA, Raid RAA, Sajjad ER (2020) Application of artificial neural networks in predicting subbase CBR values using soil indices data. In: IOP conference series: materials science and engineering
Islam MR, Roy AC (2020) Prediction of california bearing ratio of fine-grained soil stabilized with admixtures using soft computing systems. J Civ Eng Sci Technol 11(1):28–44
Yuanyou X, Yanming X, Ruigeng Z (1997) An engineering geology evaluation method based on an artificial neural network and its application. Eng Geol 47:149–156
Sinha SK, Wang MC (2007) Artificial neural network prediction models for soil compaction and permeability. Geotech Geol Eng 26:47–64
Shyamal G, Atin R, Subrata C (2019) Kriging metamodeling based Monte Carlo simulation for improved seismic fragility analysis of structures. J Earthq Eng
Shiuly A, Sahu R, Mandal S (2017) Site specific seismic hazard analysis and determination of response spectra of Kolkata for maximum considered earthquake. J Geophys Eng 14(3):466–477
Shiuly A, Roy N (2018) A generalized Vs-N correlation using various regression analysis and genetic algorithm. Acta Geodaetica Geophys 53(3):479–502
SandhyaRani and Nagaraj (2017) Prediction of CBR Value with Soil Index Properties; Case Study on Yadadri Region. Int J Latest Eng Manag Res 2(7):9–12
Reddy CNV, Pavani K (2006) Mechnically stabilsed soils-Regression equation for CBR evaluation. In: Indian geotechnical conference
Lee IM, Lee JH (1996) Prediction of pile bearing capacity using artificial neural network. Comput Geotech 18(3):189–200
Lakshmi SM, Subramanian S, Lalithambikhai MP, Vela AM, Ashni M (2016) Evaluation of soaked and unsoaked CBR values of the soil based on the compaction characteristics. Malays J Civ Eng 28(2):172–182
Gunaydin O, Gokoglu A, Fener M (2010) Prediction of artificial soil’s unconfined compression strength test using statistical analyses and artificial neural networks. Adv Eng Softw 41:1115–1123
Das R, Wason HR, Sharma M (2014) Unbiased Estimation of Moment from Body and Surface Wave Magnitude. Bull Seismol Soc Am 104(4):1802–1811
Chandrakar V, Yadav RK (2016) Study of correlation of CBR value with engineering properties and index properties of coarse grained soil. Int Res J Eng Technol 3(11):772–778
Soumya B, Subrata C (2018) An improved robust multi-objective optimization of structure with random parameters. Adv Struct Eng 21(11):1597–1607
Simpson AR, Priest SD (1993) The application of genetic algorithms to optimisation problems in geotechnics. Comput Geotech 15(1):1–19
Lee SJ, Lee SR, Kim YS (2003) An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation. Computer 30:489–503
Harini H, Nagesh S (2014) Predicting CBR of fine-grained soils by artificial neural network and multiplelinear regression. Int J Civ Eng Technol 5(2):119–126
Alam K, Abhijit M, Amit S (2020) Prediction of CBR value of fine grained soils of Bengal Basin by genetic expression programming, artificial neural network and Krigging method. J Geol Soc India 95(2):190–196
Black WPM (1962) Method of estimating the California Bearing Ratio of Cohesive Soils from Plasticity Data. Geotechnique 12(4):271–282
Panagiotis AG, Maria A, Athanasia SD, Antonia M (2019) Application of artificial neural networks for the prediction of the compressive strength of cement-based mortars. Comput Concr 24(4):329–345
Han-Lin W, Zhen-Yu Y (2020) High performance prediction of soil compaction parameters using multi expression programming. Eng Geol 276:105758
Lai S, Serra M (1997) Concrete strength prediction by means of neural network. Constr Build Mater 11(2):93–98
Kaymaz I (2005) Application of kriging method to structural reliability. Struct Saf 27(2):133–151
Kalyan K, Soumya B, Saibal K, Shiuly A (2019) An efficient robust cost optimization procedure for rice husk ash concrete mix. Comput Concr 23(6):433–444
Johari A, Habibagahi G, Ghahramani A (2006) Prediction of soil–water characteristic curve using genetic programming. J Geotech Geoenviron Eng 132(5):661–665
Javadi AA, Rezania M, Nezhad MM (2006) Evaluation of liquefaction induced lateral displacements using genetic programming. Comput Geotech 33(4):222–233
Gurtug Y, Sridharan A (2002) Prediction of compaction characteristics of fine-grained soils. Géotechnique 52(10):761–763
Black W (1943) A Method of estimating the California Bearing Ratio of Cohesive Soils from Plasticity Data 281–282
Navid K, Abidhan B, Pijush S, Majidreza N, Panagiotis AG, Annan Z (2022) Predicting the thermal conductivity of soils using integrated approach of ANN and PSO with adaptive and time-varying acceleration coefficients. Int J Therm Sci 173:107427
Panagiotis AG, Mehdi N (2019) Artificial bee colony-based neural network for the prediction of the fundamental period of infilled frame structures. Neural Comput Appl 31:4837–4847
Asteris GP, Apostolopoulou M, Skentou DA, Moropoulou A (2019) Application of artificial neural networks for the prediction of the compressive strength of cement-based mortars. Comput Concr 24:329–345
Jang J-SR (1991) Fuzzy modelling using generalized neural networks and Kalman filter algorithm. In: Proceedings of the 9th national conference on artificial intelligence, Anheim, CA, USA
Abraham A (2005) Adaption of Fuzzy Inference System Using Neural Learning. In: Fuzzy system engineering: theory and practice, Springer, pp 53–83
Jang JS (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685
Jang JS (1997) Neuro-fuzzy and soft computing. Prentice Hall, Upper Saddle River, pp 335–368
Tahmasebi P, Ardeshir H (2012) A hybrid neural networks-fuzzy logic-genetic algorithm for grade estimation. Comput Geosci 42:18–27
Bardhan A, Candan G, Avijit B, Pijush S, Panagiotis AG (2021) Efficient computational techniques for predicting the California bearing ratio of soil in soaked conditions. Eng Geol 291:1062
Bardhan A, Panagiotis AG (2023) Application of hybrid ANN paradigms built with nature inspired meta-heuristics for modelling soil compaction parameters. Transp Geotech 41:100995
Bardhan A, Abdel AK, Sangeetha P, Pouria H, Anasua G, Gaurav K, Markos TZ, Panagiotis AG (2023) A hybrid approach of ANN and improved PSO for estimating soaked CBR of subgrade soils of heavy-haul railway corridor. Int J Pavement Eng 24(1):2176494
Pangiotis AG, Saeed N, Mehdi N, Liborio C, Mohammad N (2019) Krill herd algorithm-based neural network in structural seismic reliability evaluation. Mech Adv Mater Struct 26(13):1146–1153
Ghani S, Kumari S (2022) Liquefaction behavior of Indo-Gangetic region using novel metaheuristic optimization algorithms coupled with artificial neural network. Nat Hazards 111:2995–3029
Ghani S, Kumari S (2022) Reliability analysis for liquefaction risk assessment for the City of Patna, India using hybrid computational modeling. J Geol Soc India 98:1395–1406
Ghani S, Kumari S, Shamsad A (2022) Prediction of the seismic effect on liquefaction behavior of fine-grained soils using artificial intelligence-based hybridized modeling. Arab J Sci Eng 47:5411–5441
Ghani S, Sunita K, Abidhan B (2021) A novel liquefaction study for fine-grained soil using PCA-based hybrid soft computing models. Sadhana 46(3):113
David E, Geoffrey E, Ronald J (1986) Learning representations by back-propagating errors. Int J Sci 323:533–536
Demuth H, Beale M, Hagan M (1992) Neural Network Toolbox™ 6”
D’Urso P, Gil M (2017) Fuzzy data analysis and classification. Adv Data Anal Classif 11:645–657
Mathworks (1990) Matlab Optimization Toolbox. United States of America
Apostolopoulou M, Armaghani JD, Bakolas A, Douvika GM, Moropoulou A, Asteris GP (2019) Compressive strength of natural hydraulic lime mortars using soft computing techniques. Procedia Struct Integr 17:914–923
Chen H, Asteris GP, Armaghani JD, Gordan B, Pham TB (2019) Assessing dynamic conditions of the retaining wall: developing two hybrid intelligent models. Appl Sci 9:1042
Apostolopoulou M, Asteris GP, Armaghani JD, Douvika GM, Lourenço BP, Cavaleri L, Bakolas A, Moropoulou A (2020) Mapping and holistic design of natural hydraulic lime mortars. Cem Concr Res 136:106167
Funding
No financial help needed to carry the research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no competing interest among the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
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
Kamrul Alam, S., Shiuly, A. Soft Computing-Based Prediction of CBR Values. Indian Geotech J 54, 474–488 (2024). https://doi.org/10.1007/s40098-023-00780-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40098-023-00780-x