Skip to main content

Comparison of artificial neural network (ANN) and linear regression modeling with residual errors to predict the unconfined compressive strength and compression index for Erbil City soils, Kurdistan-Iraq

Abstract

The focus of this research is to develop models for predicting the unconfined compressive strength and compression index (Cc) of clay soils according to Atterberg limits, natural water content, dry density, void ratio, and fine content. The soil unconfined compressive strength (UCS) ranged from 24 to 340 kPa and has been quantified with great precision using tested data and data collected from published research studies. The soil compression index ranged from 0.014 to 0.831 which is also correlated by the easily measurable soil properties of Atterberg limits, natural moisture content, density, void ratio, and fine contents (passes no. 200 sieves). A wide experimental test results (a total of 253 tested soils) were combined with more than 350 data collected from different academic research studies, and total data were statistically analyzed and modeled using a linear regression model (LR). According to the correlation determination (R2), mean absolute error (MAE), and the root mean square error (RMSE), the unconfined compressive strength and compression index of soil can be well predicted in terms of liquid limit (LL), plasticity index (PI), moisture content (MC), dry density (γd), void ratio, and percentage passing no. 200 sieve using linear simulation techniques. The performance of the LR models was compared using artificial neural networks (ANN) models with different hidden layers and input layers. Based on the statistical assessments such as R2, RMSE, and MAE the LR models were close to the ANN model to predict the UCS and Cc of the soils. The sensitivity study concludes that the dry density and void ratio are the most influential parameter in determining the unconfined compressive strength and compression index with the training dataset.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Data availability

No data, models, or codes were generated or used during the study.

References

  1. Ahmed C, Mohammed A, Saboonchi A (2020a) ArcGIS mapping, characterisations and modelling the physical and mechanical properties of the Sulaimani City soils, Kurdistan Region, Iraq. Geomech Geoeng:1–14

  2. Ahmed C, Mohammed A, Tahir A (2020b) Geostatistics of strength, modeling and GIS mapping of soil properties for residential purpose for Sulaimani City soils, Kurdistan Region, Iraq. Modeling Earth Systems Environment:1–15

  3. ASTM (D 7263 –2009) n.d.. Standard test methods for laboratory determination of density (unit weight) of soil specimens. West Conshohocken, PA, USA.: American Society for Testing of Materials.

  4. ASTM (D2216−16) (n.d.). standard test method for unconfined compressive strength of cohesive soil. West Conshohocken, PA, USA.: American Society for Testing of Materials.

  5. ASTM (D2435−2011) (n.d.). Standard test methods for one-dimensional consolidation properties of soils using incremental loading. West Conshohocken, PA, USA.: American Society for Testing of Materials.

  6. ASTM (D422-2007) (n.d.). Standard Test Method for Particle-Size Analysis of Soils. West Conshohocken, PA, USA.: American Society for Testing of Materials.

  7. ASTM (D4318 − 2010) (n.d.). Standard test methods for liquid limit, plastic limit, and plasticity index of soils. West Conshohocken, PA, USA.: American Society for Testing of Materials.

  8. Azzouz AS, Krizek RJ, Corotis RB (1976) Regression analysis of soil compressibility. Soils Foundations 16:19–29

    Article  Google Scholar 

  9. Burhan L, Ghafor K, Mohammed A (2020) Enhancing the fresh and hardened properties of the early age concrete modified with powder polymers and characterized using different models. Adv Civil Eng Materials 9(1):227–249

    Article  Google Scholar 

  10. Edil, T. B., Benson, C. H., Li, L., Mickelson, D. M., and Camargo, F. F. (2009). Comparison of basic laboratory test results with more sophisticated laboratory and in-situ tests methods on soils in Southeastern Wisconsin (No. WHRP 09-02).

  11. Ganji P.K (2006), (Obasi et al., 2005), University of Houston.

  12. Ghafor K, Mahmood W, Qadir W, Mohammed A (2020) Effect of particle size distribution of sand on mechanical properties of cement mortar modified with microsilica. ACI Materials J 117(1)

  13. Goktepe AB, Altun S, Altintas G, Tan O (2008) Shear strength estimation of plastic clays with statistical and neural approaches. Build Environ 43:849–860

    Article  Google Scholar 

  14. Hossain MS, Kim WS (2015) Estimation of subgrade resilient modulus for fine-grained soil from unconfined compression test. Transportation Research Record 2473:126–135

    Article  Google Scholar 

  15. Jain R, Jain PK, Bhadauria SS (2010) Computational approach to predict soil shear strength. Int J Eng Sci Technol 2:3874–3885

    Google Scholar 

  16. Karumanchi SR, Mandal A (2020) Moisture variations and its effect on shrinkage and swelling characteristics of unsaturated soil. Eur J Environ Civ Eng 24(11):1785–1801

    Article  Google Scholar 

  17. Mahmood W, Mohammed A (2020) Hydraulic conductivity, grain size distribution (GSD) and cement injectability limits predicted of sandy soils using vipulanandan models. Geotech Geol Eng 38(2):2139–2158

    Article  Google Scholar 

  18. Mohammadzadeh SD, Kazemi S-F, Mosavi A, Nasseralshariati E, Tah JH (2019a) Prediction of compression index of fine-grained soils using a gene expression programming model. Infrastructures 4:26

    Article  Google Scholar 

  19. Mohammadzadeh S D, Kazemi S-F, Mosavi A, Nasseralshariati E, Tah JH (2019b) Prediction of compression index of fine-grained soils using a gene expression programming model Infrastructures 4:26

  20. Mohammed, A., Burhan, L., Ghafor, K., Sarwar, W., & Mahmood, W. (2020c). Artificial neural network (ANN), M5P-tree, and regression analyses to predict the early age compression strength of concrete modified with DBC-21 and VK-98 polymers. Neural Comput Applic, 1-23.

  21. Mohammed, A., & Mahmood, W. (2018). Vipulanandan failure models to predict the tensile strength, compressive modulus, fracture toughness and ultimate shear strength of calcium rocks. International Journal of Geotechnical Engineering, 1-11.

  22. Mohammed A, Mahmood W (2019) New Vipulanandan p-q model for particle size distribution and groutability limits for sandy soils. J Testing Evaluation 48(5)

  23. Mohammed A, Mahmood W, Ghafor K (2020d) TGA, rheological properties with maximum shear stress and compressive strength of cement-based grout modified with polycarboxylate polymers. Construct Build Mater 235:117534

    Article  Google Scholar 

  24. Mohammed, A., Rafiq, S., Sihag, P., Kurda, R., & Mahmood, W. (2020a). Soft computing techniques: Systematic multiscale models to predict the compressive strength of HVFA concrete based on mix proportions and curing times. J Building Eng, 101851.

  25. Mohammed A, Rafiq S, Sihag P, Kurda R, Mahmood W, Ghafor K, Sarwar W (2020b) ANN, M5P-tree and nonlinear regression approaches with statistical evaluations to predict the compressive strength of cement-based mortar modified with fly ash. J Mater Res Technol 9(6):12416–12427

    Article  Google Scholar 

  26. Mohammed A, Vipulanandan C (2015) Testing and modeling the short-term behavior of lime and fly ash treated sulfate contaminated CL soil. Geotech Geol Eng 33(4):1099–1114

    Article  Google Scholar 

  27. Mohammed AS (2018) Property correlations and statistical variations in the geotechnical properties of (CH) clay soils. Geotech Geol Eng 36(1):267–281

    Article  Google Scholar 

  28. Mohammed AS, Vipulanandan C (2014) Compressive and tensile behavior of polymer treated sulfate contaminated CL soil. Geotech Geol Eng 32(1):71–83

    Article  Google Scholar 

  29. Mousavi SM, Alavi AH, Gandomi AH, Mollahasani A (2011) Nonlinear genetic-based simulation of soil shear strength parameters. J Earth System Science 120:1001–1022

    Article  Google Scholar 

  30. Mozumder RA, Laskar AI (2015) Prediction of unconfined compressive strength of geopolymer stabilized clayey soil using artificial neural network. Comput Geotech 69:291–300

    Article  Google Scholar 

  31. Obasi N, Anyaegbunam A (2005) Correlation of the undrained shear strength and plasticity index of tropical clays. Niger J Technol 24:1–11

    Google Scholar 

  32. Ojuri OO (2013) Predictive shear strength models for tropical lateritic soils. J Eng 2013

  33. O'Neill MW, Yoon G (1995) Engineering properties of overconsolidated Pleistocene soils of Texas Gulf coast. Transportation Research Record 1479:81–88

    Google Scholar 

  34. Ozer M, Isik NS, Orhan M (2008) Statistical and neural network assessment of the compression index of clay-bearing soils. Bull Eng Geol Environ 67:537–545

    Article  Google Scholar 

  35. PARK HI, LEE SR (2011) Evaluation of the compression index of soils using an artificial neural network. Comput Geotech 38:472–481

    Article  Google Scholar 

  36. Qadir W, Ghafor K, Mohammed A (2019) characterizing and modeling the mechanical properties of the cement mortar modified with fly ash for various water-to-cement ratios and curing times. Adv Civil Eng. https://doi.org/10.1155/2019/7013908

  37. ROY S, DASS G (2014) Statistical models for the prediction of shear strength parameters at Sirsa, India. Int J Civil Structural Eng 4:483–498

    Google Scholar 

  38. Salih, A., Rafiq, S., Sihag, P., Ghafor, K., Mahmood, W., & Sarwar, W. (2020). Systematic Multiscale Models to Predict the Effect of High-Volume Fly Ash on the Maximum Compression Stress of Cement-Based Mortar at Various Water/Cement Ratios and Curing Times. Measurement, 108819.

  39. Sharma L, Singh T (2018) Regression-based models for the prediction of unconfined compressive strength of artificially structured soil. Engineering Comput 34:175–186

    Article  Google Scholar 

  40. Sivaruban, N. (2008). Construction and maintenance issues related to transportation infrastructure. Master's Thesis, Department of Civil and Environmental Engineering, University of Houston.

  41. Sridharan A, Nagaraj H (2000b) Compressibility behaviour of remoulded, fine-grained soils and correlation with index properties. Can Geotech J 37:712–722

    Article  Google Scholar 

  42. Sridharan A, Nagaraj HB (2000a) Compressibility behavior of remolded, fine-grained soils and correlation with index properties. Can Geotech J 37(3):712–722

    Article  Google Scholar 

  43. Tiwari B, Ajmera B (2011) A new correlation relating the shear strength of reconstituted soil to the proportions of clay minerals and plasticity characteristics. Applied Clay Sci 53(1):48–57

    Article  Google Scholar 

  44. Vipulanandan, C., Ahossin Guezo, Y. J., & Bilgin, Ö. (2007). Geotechnical properties of marine and deltaic soft clays. In Advances in Measurement and Modeling of Soil Behavior (pp. 1-13).

  45. Vipulanandan, C., & Mohammed, A. (2020). Effect of drilling mud bentonite contents on the fluid loss and filter cake formation on a field clay soil formation compared to the API fluid loss method and characterized using Vipulanandan models. J Petrol Sci Eng, 107029.

  46. Vipulanandan C, Mohammed AS (2014) Hyperbolic rheological model with shear stress limit for acrylamide polymer modified bentonite-drilling muds. J Petrol Sci Eng 122:38–47

    Article  Google Scholar 

  47. Vipulanandan C, Mohammed AS (2021) 3-dimension stresses and new failure model to predict behavior of clay soils in various liquid limit ranges. Arab J Geosci 14(3):1–13

    Article  Google Scholar 

  48. Westerberg B, Müller R, Larsson S (2015) Evaluation of undrained shear strength of Swedish fine-grained sulphide soils. Eng Geol 188:77–87

    Article  Google Scholar 

  49. Yılmaz I (2000) Evaluation of shear strength of clayey soils by using their liquidity index. Bull Eng Geol Environ 59(3):227–229

    Article  Google Scholar 

  50. Zaimoglu AS (2015) Optimization of unconfined compressive strength of fine-grained soils modified with polypropylene fibers and additive materials. KSCE J Civil Eng 19:578–582

    Article  Google Scholar 

  51. Zeng J, Asteris PG, Mamou AP, Mohammed AS, Golias EA, Armaghani DJ, Faizi K, Hasanipanah M (2021) The effectiveness of ensemble-neural network techniques to predict peak uplift resistance of buried pipes in reinforced sand. Appl Sci 11(3):908

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Ahmed Salih.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicts of interest.

Additional information

Responsible editor: Zeynal Abiddin Erguler

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mawlood, Y., Salih, A., Hummadi, R. et al. Comparison of artificial neural network (ANN) and linear regression modeling with residual errors to predict the unconfined compressive strength and compression index for Erbil City soils, Kurdistan-Iraq. Arab J Geosci 14, 485 (2021). https://doi.org/10.1007/s12517-021-06712-4

Download citation

Keywords

  • Unconfined compressive strength
  • Compression index
  • Statistical assessment
  • Modelling