Open Access

ARTICLE

Leveraging Neural Networks and Explainable AI for Cost-Effective Retaining Wall Design

Gebrail Bekdaş¹, Yaren Aydın¹, Celal Cakiroglu², Umit Işıkdağ^3,*

1 Department of Civil Engineering, Istanbul University-Cerrahpaşa, Istanbul, 34320, Türkiye
2 GameAbove College of Engineering and Technology, Eastern Michigan University, Ypsilanti, MI 48197, USA
3 Department of Architecture, Mimar Sinan Fine Art University, Istanbul, 34427, Türkiye

* Corresponding Author: Umit Işıkdağ. Email:

(This article belongs to the Special Issue: Frontiers in Computational Modeling and Simulation of Concrete)

Computer Modeling in Engineering & Sciences 2025, 143(2), 1763-1787. https://doi.org/10.32604/cmes.2025.063909

Received 28 January 2025; Accepted 26 March 2025; Issue published 30 May 2025

Abstract

Retaining walls are utilized to support the earth and prevent the soil from spreading with natural slope angles where there are differences in the elevation of ground surfaces. As the need for retaining structures increases, the use of retaining walls is increasing. The retaining walls, which increase the stability of levels, are economical and meet existing adverse conditions. A considerable amount of retaining walls is made from steel-reinforced concrete. The construction of reinforced concrete retaining walls can be costly due to its components. For this reason, the optimum cost should be targeted in the design of retaining walls. This study presents an artificial neural network (ANN) model developed to predict the optimum dimensions of a retaining wall using soil properties, material properties, and external loading conditions. The dataset utilized to train the ANN model is generated with the Flower Pollination Algorithm. The target variables in the dataset are the length of the heel (y₁), length of the toe (y₂), thickness of the stem (top) (y₃), thickness of the stem (bottom) (y₄), foundation base thickness (y₅) and cost (y₆) and these are estimated by utilizing an ANN model based on the height of the wall (x₁), material unit weight (x₂), wall friction angle (x₃), surcharge load (x₄), concrete cost per m³ (x₅), steel cost per ton (x₆) and the soil class (x₇). The model is formulated and trained as a multi-output regression model, as all outputs are numeric and continuous. The training and evaluation of the model results in a high prediction performance (R² > 0.99). In addition, the impacts of different input features on the model predictions are revealed using the SHapley Additive exPlanations (SHAP) algorithm. The study demonstrates that when trained with a large dataset, ANN models perform very well by predicting the optimal cost with high performance.

---

Keywords

---