Optimal Dimensioning of Retaining Walls Using Explainable Ensemble Learning Algorithms

Abstract

This paper develops predictive models for optimal dimensions that minimize the construction cost associated with reinforced concrete retaining walls. Random Forest, Extreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM) algorithms were applied to obtain the predictive models. Predictive models were trained using a comprehensive dataset, which was generated using the Harmony Search (HS) algorithm. Each data sample in this database consists of a unique combination of the soil density, friction angle, ultimate bearing pressure, surcharge, the unit cost of concrete, and six different dimensions that describe an optimal retaining wall geometry. The influence of these design features on the optimal dimensioning and their interdependence are explained and visualized using the SHapley Additive exPlanations (SHAP) algorithm. The prediction accuracy of the used ensemble learning methods is evaluated with different metrics of accuracy such as the coefficient of determination, root mean square error, and mean absolute error. Comparing predicted and actual optimal dimensions on a test set showed that an R2 score of 0.99 could be achieved. In terms of computational speed, the LightGBM algorithm was found to be the fastest, with an average execution speed of 6.17 s for the training and testing of the model. On the other hand, the highest accuracy could be achieved by the CatBoost algorithm. The availability of open-source machine learning algorithms and high-quality datasets makes it possible for designers to supplement traditional design procedures with newly developed machine learning techniques. The novel methodology proposed in this paper aims at producing larger datasets, thereby increasing the applicability and accuracy of machine learning algorithms in relation to optimal dimensioning of structures.

Appraisal of Different Artificial Intelligence Techniques for the Prediction of Marble Strength

“…The IR and AI together will make the prediction more reliable and applicable. Moreover, in the future, the given 70 sample data set can be increased using the harmony search optimization algorithm [80].…”

Prediction of Cooling Load of Tropical Buildings with Machine Learning

“…Machine learning methods have gained importance in today's world [44]. Machine learning algorithms are used in many fields today [45][46][47][48][49][50][51][52]. Supervised learning, which is a type of machine learning, refers to the implementation of classification and regression algorithms where a dependent variable is known in advance.…”

Optimization and Predictive Modeling of Reinforced Concrete Circular Columns

“…The results of them and their interpretations using the SHapley Additive exPlanations (SHAP) technique have been presented in the next section. The theoretical background of ensemble learning and SHAP algorithms can be found in [ 3 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ]. In addition to the SHAP analysis also, a four-level factorial analysis has been carried out to further investigate the sensitivity of to the variations in different design variables.…”

“…Structural optimization aims at designing structures with the best possible dimensions that minimize cost without any impact on structural performance. In recent years metaheuristic optimization techniques have been increasingly applied to the optimization of different structures such as cylindrical reinforced concrete walls [ 1 , 2 ], retaining walls [ 3 , 4 , 5 ], plate girders [ 6 ], laminated composite plates [ 7 , 8 , 9 ], concrete-filled steel tubes [ 10 , 11 ], truss systems [ 12 ], timber structures [ 13 ], and liquid mass dampers [ 14 , 15 , 16 ]. These algorithms can be divided into evolutionary, physics-based, swarm-based, and population-based algorithms [ 17 , 18 , 19 ].…”