Geotechnical Assessment of Selected Lateritic Soils in Southwest Nigeria for Road Construction and Development of Artificial Neural Network Mathematical Based Model for Prediction of the California Bearing Ratio


Authors : Lateef Bankole Adamolekun; Muyideen Alade Saliu; Abiodun Ismail Lawal; Ismail Adeniyi Okewale

Volume/Issue : Volume 9 - 2024, Issue 6 - June

Google Scholar : https://tinyurl.com/2e5uja97

Scribd : https://tinyurl.com/mpn45vck

DOI : https://doi.org/10.38124/ijisrt/IJISRT24JUN753

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Investigation of the geotechnical characteristics of eighteen different lateritic soils within southwest Nigeria was carried out to determine their suitability for road construction. To achieve this goal, the lateritic soils samples were subjected to different laboratory tests, including specific gravity, Atterberg limits, grain size analysis, California bearing ratio, and compaction, in accordance with the ASTM standard procedure. The results of the tests showed that the specific gravity varied between 2.55 and 2.81; the linear shrinkage varied between 6.68% and 10.98%; the liquid limit varied between 37.17% and 56.93%; the plastic limit ranged from 19.47% to 37.14%; the plasticity index ranged from 3.81% to 30.29%; the fine sand content ranged from 37.07% to 62..93%; the fines content ranged from 36.4% to 60.9%; the maximum dry density ranged from 1747 kg/m3 to 2056 kg/m3 ; the optimum moisture content ranges from 10.94% to 20.51%; the un-soaked California bearing ratio ranged from 14.7% to 45.6%; and the soaked California bearing ratio ranged from 10% to 31%. Based on these results, all the studied soils can be used as road subgrade, while none except Loc.5/S1 is suitable for road subbase. However, none of the soils meets up with the requirement for road base course. The suitability of laterite for the construction of road depends largely on the California bearing ratio. However, laboratory tests for determining the California bearing ratio is tedious, time consuming and costly. As a result of this difficulty, there is a need to develop soft computing models to predict laterite California bearing ratio from index properties with cheap and simple tests. Thus, the experimental datasets of the eighteen studied lateritic soils were used to create and train artificial neural network (ANN) models to predict California bearing ratio from liquid limits, plasticity index, linear shrinkage, fine sand content and fines content. The proposed ANN models were compared with the multiple linear regression models proposed in this study and various regression based models suggested in the literature via statistical analyses. Based on the model comparison, the proposed ANN models outperformed the rest of the models; they presented the highest R 2 and the lowest RMSE, MAPE and MAE values. Thus, the ANN models are validated. To enhance the practical application of the proposed ANN models, they were transformed into simple mathematical equations, which gave the same predictions as the direct ANN models. Thus, they can be used for practical purposes.

Keywords : Lateritic Soil, Geotechnical Property, Road Construction, Artificial Neural Network Model, California Bearing Ratio.

References :

  1. Adejumo TWE, Tsado RI 2019 Correlation of California bearing ratio with geotechnical properties of selected lateritic soils. Nigeria Institute of Civil Engineers, 17th International Conference and Annual General Meeting, 63 – 73
  2. Akintoriwa OJ, Ojo JS, Olorunfemi MO 2010 Geophysical investigation of pavement failure in a basement complex terrain of southwestern Nigeria. The Pacific Journal of Science and Technology, 11(2): 649 - 663
  3. Akan R, Keskin SN 2019 The effect of data size of ANFIS and MLR models on the prediction of unconfined compression strength of clayey soils. SN Applied Sciences, 1: 843
  4. Amadi AN, Akande WG, Okunlola IA, Jimoh MO, Francis DG 2015 “Assessment of the Geotechnical Properties of Lateritic Soils in Minna, North Central Nigeria for Roads Design and Construction.”American Journal of Mining and Metallurgy, 3(1): 15-20. https://doi.org/10.12691/ ajmm/3-1-3
  5. ASTM 2002 D854-02 - Standard test methods for specific gravity of soil by water Pycnometer. ASTM, International West Conshohocken, United State of America, 4(2): 1 – 7
  6. ASTM 2021 D1883-21 – Standard test methods for California bearing ratio of laboratory-compaction soil. Annual Book of ASTM Standards, West Conshohocken, PA, 19428-2959, United State of America, 4(8): 1 – 16
  7. ASTM 2002 D4943-02 – Standard test methods for shrinkage factors of soils by wax method. ASTM International, West Conshohocken, United States, 4(2): 1 – 5
  8. ASTM 2002 D422-63 – Standard test methods for particle-size analysis of soils. ASTM International, West Conshohocken, 4(8): 1 – 8
  9. ASTM 2021 D698-12 – Standard test methods for laboratory compaction characteristics of soil using standard effort (12,400 ft-Ibs/ft3(600 kN-m/m)). ASTM International, West Conshohocken, Pennsylvania, United States, 4(8): 1 – 13
  10. ASTM 2018 D4318-17e1 – Standard test methods for liquid limit, plastic limit, plasticity index of soils. Annual book of ASTM standards, USA, 4(8): 1 – 20
  11. Ayodele AL, Falade FA 2016 Geotechnical properties of selected sub-base materials for road construction. Civil and Environmental Research, 8(8): 31 – 39
  12. Federal Ministry of Works and Housing, FMWH 1997 Nigeria General Specification for Roads and Bridges. Revised Edition 2, pp. 271
  13. Gudeta AD, Patel AV 2018 Prediction of CBR value from index properties of different soils: Review. International Journal of Creative Research Thoughts, 6 (2): 1190 – 1197
  14. Jegede G 2004 Highway pavement failure induced by poor geotechnical properties along a section of F209 Okitipupa – Igbokoda highway southwestern, Nigeria. Ife Science Journal, 6(1): 41– 44
  15. Jong YH, Lee CI 2004 Influence of geological conditions on the powder factor for tunnel blasting. International Journal of Rock Mechanics and Minings Sciences, 41: 533 – 538
  16. Khatti J, Grover KS 2021 Computation of permeability of soil using artificial intelligence approaches. International Journal of Engineering and Advance Technology, 11(1): 257 – 266
  17. Lawal AI 2020 An artificial neural network-based mathematical model for the prediction of blast-induced ground vibration in granite quarries in Ibadan, Oyo State Nigeria. Scientific African 8: e00413
  18. Lawal AI, Idris MA 2020 An artificial neural network–based mathematical model for the prediction of blast-induced ground vibrations. International Journal of Environmental Studies, 77(2): 318 – 334
  19. Lawal AI, Aladejare AE, Onifade M, Bada S, Idris MA 2021 Predictions of elemental composition of coal and biomass from their proximate analyses using ANFIS, ANN, and MLR. International Journal of Coal Science and Technology, 8(1): 124 – 140
  20. Madedor AO 1983 Pavement design guidelines and practice for diferent geological areas in Nigeria. In: Ola SA (ed) Tropical soils of Nigeria in engineering practices. Balkena Publishers, Rotterdam: 291–298
  21. Momoh LO, Akintoriwa O, Olorunfemi MO 2008 Geophysical Investigation of Highway failure-A Case Study from the Basement Complex Terrain of South western Nigeria. Journal of Applied Science Research, 4(6): 637 – 648
  22. Nwankwoala HO, Amadi AN, Ushie FA, Warmate T 2014 Determination of subsurface geotechnical properties for foundation design and construction in Akenfe community, Bayelsa State, Nigeria. American Journal of Civil Engineering and Architecture, 2 (4): 130 – 135
  23. Odunfa SO, Owolabi AO, Aiyedun PO, Sadiq OM 2018 Geotechnical Assessment of pavement failure along Lagos-Ibadan Expressway. FUOYE Journal of Engineering and Technology, 3(2): 113 – 117
  24. Ogundipe OM 2008 Road pavement failure caused by poor soil properties along Aramoko-Ilesha highway, Nigeria. Journal of Engineering and Applied Sciences, 3(3), 239-241
  25. Ogunribido THT, Fadairo TE 2020 Geotechnical investigation of road pavement failure along Arigidi/Oke-Agbe Akoko, Southwest, Nigeria. International Journal of Physical Research, 8(2): 35 – 39
  26. Onyelowe KC, Okafor FO 2013 Portland cement/quarry dust improvement of Olokoro laterite for road base. World Journal of Engineering Science India, 1(4): 133 – 143
  27. Owoseni JO, Adeyemi GO, Asiwaju-Bello YA, Anifowose AYB 2012 Engineering geological assessment of some lateritic soils in Ibadan, Southwestern, Nigeria using bivariate and regression analyses. Africa Journal of Science and Technology (AJST), Science and Engineering Series, 12(1): 59 – 71
  28. Owoyemi OO, Ajala OF, Afolagboye LO 2022 Subgrade evaluation of Gbogan-Ode Omu highway, Southwestern, Nigeria. Fuoye Journal of Pure and Applied Sciences, 7(2): 1 – 10
  29. Schmidhuber J 2015 “Deep learning in neural networks: An overview”. Neural Network, 61: 85-117. https://doi.org/10.1016/j.neural.2014.09.003
  30. Tenpe A, Kaur S 2015 Artificial neural network modeling for predicting compaction parameters based on index properties of soil. International Journal of Science and Research, 4(7): 1198 – 1201
  31. Tizpa P, Chenari RJ, Karimpour-Fard M, Machado SL 2014 ANN prediction of some geotechnical properties of some soil from their index parameters. Article in Arabian Journal of Geosciences, 8(5): 2911 – 2920
  32. Torgano ST, Ali MS, Yenealen ET, Tumato AT 2020 Correlation between CBR values and index properties of subgrade soils: in case of Bodili town. International Journal of Advance Research and Innovative Ideas in Education, 6(3): 1167 – 1182
  33. Werbos P 1982 Applications of advances in nonlinear sensitivity analyes. System Modeling and Optimization: 762 – 770. Retrieved 23 May 2024
  34. Yang Z, Yang Z 2014 Compressive biomedical physics. Karolinska institute, Stockholm, Sweden: 1. ISBN 978-0-444-53633-4. Retrieved 26 June 2023

Investigation of the geotechnical characteristics of eighteen different lateritic soils within southwest Nigeria was carried out to determine their suitability for road construction. To achieve this goal, the lateritic soils samples were subjected to different laboratory tests, including specific gravity, Atterberg limits, grain size analysis, California bearing ratio, and compaction, in accordance with the ASTM standard procedure. The results of the tests showed that the specific gravity varied between 2.55 and 2.81; the linear shrinkage varied between 6.68% and 10.98%; the liquid limit varied between 37.17% and 56.93%; the plastic limit ranged from 19.47% to 37.14%; the plasticity index ranged from 3.81% to 30.29%; the fine sand content ranged from 37.07% to 62..93%; the fines content ranged from 36.4% to 60.9%; the maximum dry density ranged from 1747 kg/m3 to 2056 kg/m3 ; the optimum moisture content ranges from 10.94% to 20.51%; the un-soaked California bearing ratio ranged from 14.7% to 45.6%; and the soaked California bearing ratio ranged from 10% to 31%. Based on these results, all the studied soils can be used as road subgrade, while none except Loc.5/S1 is suitable for road subbase. However, none of the soils meets up with the requirement for road base course. The suitability of laterite for the construction of road depends largely on the California bearing ratio. However, laboratory tests for determining the California bearing ratio is tedious, time consuming and costly. As a result of this difficulty, there is a need to develop soft computing models to predict laterite California bearing ratio from index properties with cheap and simple tests. Thus, the experimental datasets of the eighteen studied lateritic soils were used to create and train artificial neural network (ANN) models to predict California bearing ratio from liquid limits, plasticity index, linear shrinkage, fine sand content and fines content. The proposed ANN models were compared with the multiple linear regression models proposed in this study and various regression based models suggested in the literature via statistical analyses. Based on the model comparison, the proposed ANN models outperformed the rest of the models; they presented the highest R 2 and the lowest RMSE, MAPE and MAE values. Thus, the ANN models are validated. To enhance the practical application of the proposed ANN models, they were transformed into simple mathematical equations, which gave the same predictions as the direct ANN models. Thus, they can be used for practical purposes.

Keywords : Lateritic Soil, Geotechnical Property, Road Construction, Artificial Neural Network Model, California Bearing Ratio.

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe