Prediction of UCS values using basic geotechnical soil parameters via regression and Artificial Neural Networks ANN

  • Mudhaffer Alqudah Civil Engineering (CE) Department, The University of Mississippi (UM), University, MS 38677, USA
  • Haitham Saleh Civil Engineering (CE) Department, The University of Mississippi (UM), University, MS 38677, USA
  • Hakan Yasarer Civil Engineering (CE) Department, The University of Mississippi (UM), University, MS 38677, USA
  • Ahmed Al-Ostaz Civil Engineering (CE) Department, The University of Mississippi (UM), University, MS 38677, USA
  • Yacoub Najjar Civil Engineering (CE) Department, The University of Mississippi (UM), University, MS 38677, USA
Article ID: 703
47 Views, 23 PDF Downloads
Keywords: UCS; Artificial Neural Networks (ANN); multi-linear regression (MLR); multi-nonlinear regression (MNLR)

Abstract

Unconfined Compressive Strength (UCS) test is a widely used lab procedure for assessing soil’s undrained shear strength. However, conventional lab testing is time-, cost-, and labor-intensive. This study evaluates predictive models for UCS using basic soil parameters. Soil mixtures were prepared and tested through several laboratory experiments, including Atterberg’s limits, particle size distribution, water content, bulk density using Harvard miniature compaction apparatus, and UCS. A total of 152 soil samples were utilized to train the prediction models. To achieve that, multi-linear regression (MLR), multi-nonlinear regression (MNLR), and backpropagation Artificial Neural Networks (ANN) were employed to relate the dependent variable UCS (predicted) to the independent geotechnical parameters (predictors). Results showed that the best model to predict the UCS values for soil using its soil parameters is the ANN-based model with R2 of 83% and ASE (Averaged Square Error) of 0.0029, followed by the nonlinear regression model with R2 = 49.2% and ASE of 3.63, and finally the MLR model with R2 = 44.5% and ASE of 3.92.

Published
2025-03-03
Section
Original Research Articles

References

Yokoi H. Relationship between soil cohesion and shear strength. Soil Science and Plant Nutrition. 1968; 14(3): 89–93.

Keaton JR. Angle of Internal Friction. In: Bobrowsky P, Marker B (editors). Encyclopedia of Engineering Geology. Springer; 2020; pp. 1–2.

Motaghedi H, Eslami A. Determining soil shear strength parameters from CPT and CPTu data. Scientia Iranica. 2013; 20(5): 1349–1360.

Bai Y, Liu J, Song Z, et al. Unconfined Compressive Properties of Composite Sand Stabilized with Organic Polymers and Natural Fibers. Polymers. 2019; 11(10): 1576. doi: 10.3390/polym11101576

Wu Y, Li Y, Niu B. Assessment of the Mechanical Properties of Sisal Fiber‐Reinforced Silty Clay Using Triaxial Shear Tests. The Scientific World Journal. 2014.

Rabab’ah SR, Sharo AA, Alqudah MM, et al. Effect of using Oil Shale Ash on geotechnical properties of cement-stabilized expansive soil for pavement applications. Case Studies in Construction Materials; 2023; 19: e02508.

Kim M, Okuyucu O, Ordu E, et al. Prediction of undrained shear strength by the GMDH-type neural network using SPT-value and soil physical properties. Materials. 2022; 15(18): 6385.

Farsi S, Esmaeili M, Naseri R. Effect of rock strength on the degradation of ballast equipped with under sleeper pad using discrete element method. International Journal of Science and Research Archive. 2024; 11(1): 2579–2586.

Afolagboye LO, Ajayi DE, Afolabi IO. Machine learning models for predicting unconfined compressive strength: A case study for Precambrian basement complex rocks from Ado-Ekiti, Southwestern Nigeria. Scientific African. 2023; 20: e01715.

Najjar YM, Huang C. Simulating the stress–strain behavior of Georgia kaolin via recurrent neuronet approach. Computers and Geotechnics. 2007; 34(5): 346–361.

Jiang Q, Cao M, Wang Y, et al. Estimation of soil shear strength indicators using soil physical properties of paddy soils in the plastic state. Applied Sciences. 2021; 11(12): 5609.

Cokca E, Erol O, Armangil F. Effects of compaction moisture content on the shear strength of an unsaturated clay. Geotechnical and Geological Engineering. 2004; 22: 285–297.

Wilson SD. Suggested method of test for moisture-density relations of soils using Harvard compaction apparatus. In: Special Procedures for Testing Soil and Rock for Engineering Purposes: Fifth Edition. ASTM International; 1970.

American Society for Testing and Materials. ASTM D2166: Standard Test Method for Unconfined Compressive Strength of Cohesive Soil. ASTM International; 2016.

American Society for Testing and Materials. ASTM D4318–17e1: Standard Test Methods for Liquid Limit, Plastic Limit, and Plasticity Index of Soils. ASTM International; 2018.

Oikonomou N, Mavridou S. The use of waste tyre rubber in civil engineering works. In: Sustainability of construction materials. Woodhead Publishing; 2009. pp. 213–238.

Hastuty IP. Comparison of the use of cement, gypsum, and limestone on the improvement of clay through unconfined compression test. Journal of the Civil Engineering Forum. 2019; 5(2).

Lindeburg MR. Civil Engineering Reference Manual for the PE Exam, 7th ed. Professional Pubns Inc; 1999.

Najjar YM, Ali HE, Basheer IA. On the use of neuronets for simulating the stress-strain behavior of soils. In: Numerical Models in Geomechanics. CRC Press; 1999. pp. 657–662.

Goodfellow I, Bengio Y, Courville A. Deep learning. MIT press; 2016. Volume 196.

Stone M. Cross-validation: A review. Statistics: A Journal of Theoretical and Applied Statistics. 1978; 9(1): 127–139.

Shahin MA, Jaksa MB, Maier HR. State of the Art of Artificial Neural in Geotechnical Engineering. Electronic Journal of Geotechnical Engineering. 2008.