Applying several machine learning approaches for prediction of unconfined compressive strength of stabilized pond ashes


This paper evaluates the potential of five modeling approaches, namely M5 model tree, random forest, artificial neural networks, support vector machines and Gaussian processes, for the prediction of unconfined compressive strength of stabilized pond ashes with lime and lime sludge. The study not only presents five models for the same set of data but also compares the overall performance of them. Dataset used consists of 255 samples acquired from laboratory experiments. Out of the total, 170 randomly chosen samples were used for training and remaining 85 were used for testing the models. Input dataset consists of eight parameters (uniformity coefficient, coefficient of curvature, maximum dry density, optimum moisture content, lime, lime sludge, curing period and 7-day soaked California bearing ratio), while the output is UCS value at 7, 28, 45, 90 and 180 days of curing. Comparisons of results propose that Gaussian processes modeling strategy works well and the overall performance was substantially nearer to the exact agreement line. As a result of GP model, higher value of CC = 0.997 and lower values of RMSE = 23.016 kPa and MAE = 16.455 were obtained for testing the dataset. Sensitivity analysis suggests that lime, lime sludge, curing period and California bearing ratio are the significant parameters for predicting the unconfined compressive strength of stabilized pond ashes. The results confirmed that GP models are in a position to predict the unconfined compressive strength of stabilized pond ashes with an excessive degree of accuracy; however, GP modeling approach proves that this approach is more economical and less difficult in comparison with tedious laboratory work.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6


  1. 1.

    Akbulut S, Kalkan E, Celik S (2003) Artificial neural networks to estimate the shear strength of compacted soil samples. In: International conference on new developments in soil mechanics and geotechnical engineering, Lefkosa, TRNC

  2. 2.

    Lee SJ, Lee SR, Kim YS (2003) An approach to estimate unsaturated shear strength using artificial neural network and hyperbolic formulation. Comput Geotech 30(6):489–503.

    Article  Google Scholar 

  3. 3.

    Sivrikaya O, Togrol E, Komur M (2004) Determination of unconfined compressive strength by artificial neural network. In: 10th national congress of soil mechanics and foundation engineering, Istanbul, Turkey

  4. 4.

    Majdi A, Rezaei M (2013) Prediction of unconfined compressive strength of rock surrounding a roadway using artificial neural network. Neural Comput Appl 23:381–389.

    Article  Google Scholar 

  5. 5.

    Ceryan N, Okkan U, Kesimal A (2013) Prediction of unconfined compressive strength of carbonate rocks using artificial neural networks. Environ Earth Sci 68:807–819.

    Article  Google Scholar 

  6. 6.

    Sathyapriya S, Arumairaj PD, Ranjini D (2017) Prediction of unconfined compressive strength of a stabilised expansive clay soil using ANN and regression analysis (SPSS). Asian J Res Soc Sci Humanit 7(2):109–123.

    Article  Google Scholar 

  7. 7.

    Zhao HB (2008) Slope reliability analysis using a support vector machine. Comput Geotech 35:459–467.

    Article  Google Scholar 

  8. 8.

    Samui P (2008) Support vector machine applied to settlement of shallow foundations on cohesionless soils. Comput Geotech 35(3):419–427.

    Article  MATH  Google Scholar 

  9. 9.

    Lee CY, Chern SG (2013) Application of a support vector machine for liquefaction assessment. J Mar Sci Technol 21(3):318–324.

    Article  Google Scholar 

  10. 10.

    Sabat AK (2015) Prediction of California bearing ratio of a stabilized expansive soil using artificial neural network and support vector machine. Electron J Geotech Eng 20:981–991

    Google Scholar 

  11. 11.

    Lamorski K, Pachepsky Y, Sławiński C, Walczak RT (2008) Using support vector machines to develop pedotransfer functions for water retention of soils in Poland. Soil Sci Soc Am J 72(5):1243–1247.

    Article  Google Scholar 

  12. 12.

    Pal M, Deswal S (2010) Modelling pile capacity using Gaussian process regression. Comput Geotech 37(7–8):942–947.

    Article  Google Scholar 

  13. 13.

    Hoang ND, Pham AD, Nguyen QL, Pham QN (2016) Estimating compressive strength of high performance concrete with Gaussian process regression model. Adv Civ Eng.

    Article  Google Scholar 

  14. 14.

    Leshem G, Ritov Y (2007) Traffic flow prediction using adaboost algorithm with random forests as a weak learner. In: Proceedings of world academy of science, engineering and technology, vol 21, pp 193–198

  15. 15.

    Polishchuk PG, Muratov EN, Artemenko AG, Kolumbin OG, Muratov NN, Kuzmin VE (2009) Application of random forest approach to QSAR prediction of aquatic toxicity. J Chem Inf Model 49(11):2481–2488

    Article  Google Scholar 

  16. 16.

    Herrera M, Torgo L, Izquierdo J, Pérez-García R (2010) Predictive models for forecasting hourly urban water demand. J Hydrol 387(1–2):141–150

    Article  Google Scholar 

  17. 17.

    Bhattacharya B, Solomatine DP (2003) Neural networks and M5 model trees in modelling water level-discharge relationship for an Indian river. In: European symposium on artificial neural networks, Bruges (Belgium), pp 407–412

  18. 18.

    Solomatine DP, Dulal KN (2003) Model trees as an alternative to neural networks in rainfall-runoff modelling. Hydrol Sci J 48(3):399–411

    Article  Google Scholar 

  19. 19.

    Solomatine DP (2003) Mixtures of simple models vs ANNs in hydrological modelling. In: Design and application of hybrid intelligent systems. IOS Press, Amsterdam, The Netherlands, pp 76–85

    Google Scholar 

  20. 20.

    Solomatine DP, Siek MB (2004) Flexible and optimal M5 model trees with applications to flow predictions. In: Proceedings of 6th international conference on hydroinformatics. World Scientific Press, Singapore

  21. 21.

    Solomatine DP, Xue Y (2004) M5 model trees compared to neural networks: application to flood forecasting in the upper reach of the Huai River in China. J Hydrol Eng 9(6):491–501

    Article  Google Scholar 

  22. 22.

    Pal M, Deswal S (2009) M5 model tree based modelling of reference evapotranspiration. Hydrol Process 30(10):1437–1443

    Article  Google Scholar 

  23. 23.

    Quinlan JR (1992) Learning with continuous classes. In: Proceedings of Australian joint conference on artificial intelligence. World Scientific Press, Singapore, pp 343–348

  24. 24.

    Seeger M, Williams CKI, Lawrence ND (2003) Fast forward selection to speed up sparse Gaussian process regression. In: Bishop CM, Frey BJ (eds) Proceedings of the ninth international workshop on artificial intelligence and statistics

  25. 25.

    Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Google Scholar 

  26. 26.

    Breiman L (2001) Random forest. Mach Learn 45(1):5–32

    Article  Google Scholar 

  27. 27.

    Khandelwal M, Singh TN (2009) Prediction of blast-induced ground vibration using artificial neural network. Int J Rock Mech Min 46(7):1214–1222.

    Article  Google Scholar 

  28. 28.

    Singh TN, Kanchan R, Saigal K, Verma AK (2004) Prediction of p-wave velocity and anisotropic properties of rock using artificial neural networks technique. J Sci Ind Res India 63(1):32–38

    Google Scholar 

  29. 29.

    Vapnik VN (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  30. 30.

    Smola AJ (1996) Regression estimation with support vector learning machines. Master’s Thesis, Technische Universitat Munchen, Germany

  31. 31.

    Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, Cambridge

    Google Scholar 

  32. 32.

    ASTM C618-08a (2008) Standard specification for coal fly ash and raw or calcined natural pozzolan for use in concrete. Annual book of ASTM standards. ASTM C618-08a, West Conshohocken

    Google Scholar 

  33. 33.

    IS: 2720 (Part-7)-1980 (Reaffirmed 2002) Method of test for soils: determination of water content-dry density relation using light compaction (second revision)

  34. 34.

    IS: 2720 (Part-16)-1987 (Reaffirmed 2002) Method of test for soils: laboratory determination of CBR (second revision)

  35. 35.

    IS: 4332 (Part-5)-1970 (Reaffirmed 2006) Methods of test for stabilized soils: determination of unconfined compressive strength of stabilized soils

  36. 36.

    Suthar M, Aggarwal P (2018) Bearing ratio and leachate analysis of pond ash stabilized with lime and lime sludge. J Rock Mech Geotech Eng 10(4):769–777.

    Article  Google Scholar 

  37. 37.

    Sahu JT, Patel S, Senapati A (2013) Engineering properties of copper slag–fly ash–dolime mix and its utilization in the base course of flexible pavements. J Mater Civ Eng 25(12):1871–1879

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Manju Suthar.

Ethics declarations

Conflict of interest

The author declares no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Suthar, M. Applying several machine learning approaches for prediction of unconfined compressive strength of stabilized pond ashes. Neural Comput & Applic 32, 9019–9028 (2020).

Download citation


  • Unconfined compressive strength
  • M5 model tree
  • Random forest
  • Artificial neural network
  • Support vector machines
  • Gaussian processes