Predicting the Bearing Capacity of a Shallow Foundation Using Artificial Neural Networks with MATLAB: The Case of the Daraal Peulh Site (Senegal)

Hamed FALL^1, , Déthié SARR¹, Lamine BAR¹ and Abdou Aziz WELLE²

¹Département de Géotechnique, Laboratoire L2M, UFR Sciences de l’Ingénieur, Université Iba Der Thiam de Thiès, Senegal

²Département de Génie Civil, Laboratoire L2M, UFR Sciences de l’Ingénieur, Université Iba Der Thiam de Thiès, Senegal

Cite this paper:
Hamed FALL, Déthié SARR, Lamine BAR and Abdou Aziz WELLE. Predicting the Bearing Capacity of a Shallow Foundation Using Artificial Neural Networks with MATLAB: The Case of the Daraal Peulh Site (Senegal). American Journal of Civil Engineering and Architecture. 2026; 14(4):176-188. doi: 10.12691/ajcea-14-4-5

Abstract

Accurately determining the bearing capacity of shallow foundations is essential in geotechnical engineering. This article proposes an approach using artificial neural networks (ANNs) to estimate the bearing capacity of a continuous footing based on the geotechnical characteristics of the Daraal Peulh site (Senegal). A database of 250 samples was compiled by varying cohesion, the angle of internal friction, the footing width, and the embedment depth. The target values were generated by an equiprobable random mixture of the Terzaghi and Meyerhof formulas. A multilayer perceptron with a hidden layer of 12 neurons, trained using the Levenberg-Marquardt algorithm, yielded a mean squared error (MSE) of 45.97 on the training set and 68.73 on the test set, with correlation coefficients of 0.9932 and 0.9871, respectively. Validation on eight independent samples (four from Terzaghi, four from Meyerhof) yielded relative errors ranging from 3.5% to 38%, with a median error of approximately 13%. This study demonstrates that, despite the inherent variability resulting from the combination of the two theories, the RNA is a rapid and sufficiently reliable estimation tool for the soils of Daraal Peulh, within the limits of the parameter ranges studied.

Keywords:
bearing capacity shallow foundation artificial neural networks MATLAB external validation Meyerhof Daraal Peulh site

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]	Terzaghi, K. (1943). Theoretical Soil Mechanics. John Wiley & Sons.
[2]	George Geoffrey Meyerhof. (1963). Some Recent Research on the Bearing Capacity of Foundations. Canadian Geotechnical Journal. 1(1): 16–26.
[3]	Haykin, S. (2009). Neural Networks and Learning Machines (3rd ed.). Pearson Education.
[4]	Shahin, M.A., Jaksa, M.B., & Maier, H.R. (2009). Recent advances and future challenges for artificial neural systems in geotechnical engineering applications. Advances in Artificial Neural Systems, 2009, 1-9.
[5]	Goh, A.T.C. (1995). Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 9(3), 143–151.
[6]	Moayedi, Hossein & Jahed Armaghani, Danial. (2018). Optimizing an ANN model with ICA for estimating the bearing capacity of driven piles in cohesionless soil. Engineering with Computers, 34. 10.1007/s00366-017-0545-7.
[7]	Moayedi, Hossein, Mosallanezhad, Mansour, A. Rashid, Ahmad Safuan, Wan Jusoh, Wan, and Mu'azu, Mohammed. (2020). A systematic review and meta-analysis of artificial neural network applications in geotechnical engineering: theory and applications. Neural Computing and Applications. 32. 10.1007/s00521-019-04109-9.
[8]	Acharyya, Rana & Dey, Arindam. (2019). Assessment of bearing capacity for strip footings located near a sloping surface using an ANN model. Neural Computing and Applications. 31. 8087–8100. 10.1007/s00521-018-3661-4.
[9]	AFNOR. (1994). NF P94-071-1: Soils: Investigation and Testing—Box Shear Test—Part 1: Direct Shear. French Standardization Association.
[10]	McCulloch, W.S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The Bulletin of Mathematical Biophysics, 5(4), 115–133.
[11]	Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386–408.
[12]	Rumelhart, D.E., Hinton, G.E., & Williams, R.J. (1986). Learning representations by back-propagating errors. *Nature*, 323(6088), 533–536.
[13]	Hagan, M.T., & Menhaj, M.B. (1994). Training feedforward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), 989–993.
[14]	LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
[15]	Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
[16]	Bui, X.N., Muazu, M.A., & Nguyen, H. (2020). Optimizing the Levenberg–Marquardt backpropagation technique for predicting the safety factor of slopes following two-dimensional OptumG2 analysis. Engineering with Computers, 36(3), 941–952.
[17]	MathWorks. (2023). MATLAB Neural Network Toolbox User’s Guide. The MathWorks Inc.
[18]	Chwała, M., & Puła, W. (2020). Evaluation of shallow foundation bearing capacity in the case of a two-layered soil and spatial variability in soil strength parameters. PLoS ONE 15(4): e0231992.
[19]	Pantelidis, L., Meddah, A. The Effect of Loading Inclination and Eccentricity on the Bearing Capacity of Shallow Foundations: A Review. Arch Computat Methods Eng 31, 4189–4208 (2024).
[20]	Skempton, A.W. (1951). The bearing capacity of clays. Proc. Building Research Congress ICE 0 180–189, 1951.
[21]	Terzaghi, K., Peck, R.B., & Mesri, G. (1996). Soil Mechanics in Engineering Practice. Wiley.
[22]	Phoon, K.K., & Kulhawy, F.H. (1999). Characterization of geotechnical variability. Canadian Geotechnical Journal, 36(4), 612–624.
[23]	Duncan, J.M. (2000). Factors of safety and reliability in geotechnical engineering. Journal of Geotechnical and Geoenvironmental Engineering, 126(4), 307–316.
[24]	Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Morgan Kaufmann.
[25]	Patro, S. Gopal & Sahu, Dr. Kishore Kumar. (2015). Normalization: A Preprocessing Stage. IARJSET. 20–22. 10.17148/IARJSET.2015.2305.
[26]	Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2(5), 359–366.
[27]	Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems, 2(4), 303–314.
[28]	Hagan, M.T., Demuth, H.B., & Beale, M.H. (1996). Neural Network Design. PWS Publishing.
[29]	Ripley, B.D. (1996). Pattern Recognition and Neural Networks. Cambridge University Press.
[30]	Prechelt, L. (1998). Early Stopping—But When?. In: Orr, G.B., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol. 1524. Springer, Berlin, Heidelberg.
[31]	Chai, T., & Draxler, R.R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? Geoscientific Model Development, 7(3), 1247–1250.
[32]	Willmott, C.J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79–82.
[33]	Legates, D.R., & McCabe, G.J. (1999). Evaluating the use of “goodness-of-fit” measures in hydrologic and hydroclimatic model validation. Water Resources Research, 35(1), 233–241.
[34]	Nash, J.E., & Sutcliffe, J.V. (1970). River flow forecasting through conceptual models, Part I—A discussion of principles. Journal of Hydrology, 10(3), 282–290.
[35]	Ron Kohavi. 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th International Joint Conference on Artificial Intelligence—Volume 2 (IJCAI'95). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1137–1143.
[36]	Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society: Series B, 36(2), 111–133.
[37]	Montgomery, D.C., Peck, E.A., & Vining, G.G. (2012). Introduction to Linear Regression Analysis (5th ed.). John Wiley & Sons.
[38]	Bishop, C.M. (2006). Pattern Recognition and Machine Learning. Springer.