Citation :

Mohammed Elmorsli, Mouna El Mkhalet, Nouzha Lamdouar, "Comparative Assessment of Machine Learning Models for Predicting Seismic Displacements of Concrete Gravity Dams," International Journal of Civil Engineering, vol. 13, no. 8, pp. 469-486, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I8P128

Abstract

Concrete gravity dams constitute critical hydraulic infrastructures whose seismic response is crucial for maintaining structural stability and safety. The present study investigates the performance of three machine learning algorithms, namely Multilayer Perceptron (MLP), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost), for predicting the maximum seismic displacement of concrete gravity dams within a Single-Degree-Of-Freedom (SDOF)-based seismic reliability framework. A dataset comprising 304 samples was generated through parametric finite element simulations by varying the principal geometric and material properties of the dam system. The predictive performance of the models was evaluated using six-fold cross-validation based on the coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). Among the evaluated algorithms, MLP achieved the highest prediction accuracy, whereas XGBoost demonstrated comparable performance. SHAP and perturbation-based sensitivity analyses consistently identified dam height as the most influential parameter governing the predicted seismic displacement. The proposed framework provides an efficient and interpretable approach for rapid seismic displacement prediction and seismic reliability assessment of concrete gravity dams.

Keywords

Concrete Gravity Dams, Multilayer Perceptron, Seismic Displacements, Support Vector Regressions, Xgboost Models.

References

1. Giacomo Sevieri, and Anna De Falco, “Dynamic Structural Health Monitoring for Concrete Gravity Dams based on the Bayesian Inference,” Journal of Civil Structural Health Monitoring, vol. 10, no. 2, pp. 235-250, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Shuyang Yu et al., “Seepage, Deformation, and Stability Analysis of Sandy and Clay Slopes with Different Permeability Anisotropy Characteristics Affected by Reservoir Water Level Fluctuations,” Water, vol. 12, no. 1, pp. 1-20, 2020.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Sihan Song et al., “Automatic Concrete Dam Deformation Prediction Model Based on TPE-STL-LSTM,” Water, vol. 15, no. 11, pp. 1-48, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Jiedeerbieke Madiniyeti et al., “Concrete Dam Deformation Prediction Model Research Based on SSA–LSTM,” Applied Sciences, vol. 13, no. 13, pp. 1-15, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Neander Berto Mendes, and Lineu José Pedroso, “Structural Verification of a Gravity Dam under Seismic Action using Machine Learning,” Computers & Structures, vol. 321, 2026.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Chuan Lin et al., “Variation Trend Prediction of Dam Displacement in the Short-Term Using a Hybrid Model Based on Clustering Methods,” Applied Sciences, vol. 13, no. 19, pp. 1-24, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Wenyuan Wu et al., “A Novel Artificial Intelligence Prediction Process of Concrete Dam Deformation Based on a Stacking Model Fusion Method,” Water, vol. 16, no. 13, pp. 1-26, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Thanh T. Nguyen et al., “Influence of Settlement on Base Resistance of Long Piles in Soft Soil—Field and Machine Learning Assessments,” Geotechnics, vol. 4, no. 2, pp. 447-469, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Yan Su et al., “Dam Deformation Monitoring Model Based on Deep Learning and Split Conformal Quantile Prediction,” Applied Sciences, vol. 15, no. 4, pp. 1-18, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Yaren Aydın et al., “Explainable Ensemble Learning and Multilayer Perceptron Modeling for Compressive Strength Prediction of Ultra-High-Performance Concrete,” Biomimetics, vol. 9, no. 5, pp. 1-15, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Ezgi Gurgenc, Osman Altay, and Elif Varol Altay, “AOSMA-MLP: A Novel Method for Hybrid Metaheuristics Artificial Neural Networks and a New Approach for Prediction of Geothermal Reservoir Temperature,” Applied Sciences, vol. 14, no. 8, pp. 1-19, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Husam Ahmad Al Hamada, and Mohammad Shehab, “Integrated Multi-Layer Perceptron Neural Network and Novel Feature Extraction for Handwritten Arabic Recognition,” International Journal of Data and Network Science, vol. 8, no. 3, pp. 1501-1516, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Wendi Jia, and Quanlong Chen, “Aircraft Structural Stress Prediction Based on Multilayer Perceptron Neural Network,” Applied Sciences, vol. 14, no. 21, pp. 1-21, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Mintae Kim et al., “Deep Learning Approach on Prediction of Soil Consolidation Characteristics,” Buildings, vol. 14, no. 2, pp. 1-18, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Andrés Mauricio Guzmán Sejas et al., “Developing Statistical and Multilayer Perceptron Neural Network Models for a Concrete Dam Dynamic Behaviour Interpretation,” Infrastructures, vol. 10, no. 11, pp. 1-17, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Younes Alouan et al., “Multi-Layer Perceptron Neural Networks for Concrete Strength Prediction: Balancing Performance and Optimizing Mix Designs,” Engineering Proceedings, vol. 112, no. 1, pp. 1-11, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
17. You-Jeng Chang, Ying-Lei Lin, and Ping-Feng Pai, “Support Vector Machines with Hyperparameter Optimization Frameworks for Classifying Mobile Phone Prices in Multi-Class,” Electronics, vol. 14, no. 11, pp. 1-21, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Jonatha Sousa Pimentel, Raydonal Ospina, and Anderson Ara, “A Novel Fusion Support Vector Machine Integrating Weak and Sphere Models for Classification Challenges with Massive Data,” Decision Analytics Journal, vol. 11, pp. 1-14, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Rosita Guido et al., “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Information, vol. 15, no. 4, pp. 1-36, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Ehsan Harirchian et al., “Application of Support Vector Machine Modeling for the Rapid Seismic Hazard Safety Evaluation of Existing Buildings,” Energies, vol. 13, no. 13, pp. 1-15, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Wei Shao et al., “The Application of Machine Learning Techniques in Geotechnical Engineering: A Review and Comparison,” Mathematics, vol. 11, no. 18, pp. 1-16, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Saurabh Kumar Anuragi, “Application of Support Vector Machine in Geotechnical Engineering: A Review,” Global Journal of Engineering and Technology Advances, vol. 21, no. 3, pp. 103-113, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
23. Xin Yang, Yan Xiang, Guangze Shen, and Meng Sun, “A Combination Model for Displacement Interval Prediction of Concrete Dams Based on Residual Estimation,” Sustainability, vol. 14, no. 23, pp. 1-17, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Asif Ahmed et al., “Hybrid BO-XGBoost and BO-RF Models for the Strength Prediction of Self-Compacting Mortars with Parametric Analysis,” Materials, vol. 16, no. 12, pp. 1-27, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Billal Sari-Ahmed et al., “Strength Prediction of Fiber-Reinforced Clay Soils Stabilized with Lime Using XGBoost Machine Learning,” Civil and Environmental Engineering Reports, vol. 34, no. 2, pp. 157-176, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Duygu Demirtürk, Ömer Mintemur, and Abdussamet Arslan, “Optimizing LightGBM and XGBoost Algorithms for Estimating Compressive Strength in High-Performance Concrete,” Arabian Journal for Science and Engineering, vol. 51, no. 4, pp. 4401-4423, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Juli Sergine Tavares Teixeira Saldanha et al., “A Comparison of WaveNet and XGBoost for Traditional Direct Wave Propagation and Seismic Inversion using Horizontal Layer Models,” Research, Society and Development, vol. 13, no. 5, pp. 1-17, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Nazmus Sakib Ahmed, “Machine Learning Models for Pavement Structural Condition Prediction: A Comparative Study of Random Forest (RF) and eXtreme Gradient Boosting (XGBoost),” Open Journal of Civil Engineering, vol. 14, no. 4, pp. 570-586, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Yingui Qiu et al., “Developing Hybrid XGBoost Model to Predict the Strength of Polypropylene and Straw Fibers Reinforced Cemented Paste Backfill and Interpretability Insights,” CMES - Computer Modeling in Engineering and Sciences, vol. 144, no. 2, pp. 1607-1629, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Suraj Kumar Parhi, and Sanjaya Kumar Patro, “Prediction of Compressive Strength of Geopolymer Concrete using a Hybrid Ensemble of Grey Wolf Optimized Machine Learning Estimators,” Journal of Building Engineering, vol. 71, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
31. Odey Alshboul et al., “Extreme Gradient Boosting-Based Machine Learning Approach for Green Building Cost Prediction,” Sustainability, vol. 14, no. 11, pp. 1-20, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Qiubing Ren et al., “A Multiple-Point Monitoring Model for Concrete Dam Displacements based on Correlated Multiple-Output Support Vector Regression,” Structural Health Monitoring, vol. 21, no. 6, pp. 2768-2785, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Chongshi Gu et al., “Multi-Output Displacement Health Monitoring Model for Concrete Gravity Dam in Severely Cold Region based on Clustering of Measured dam Temperature Field,” Structural Health Monitoring, vol. 22, no. 5, pp. 3416-3436, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
34. Bo Xu et al., “A Deep Learning Prediction and Interpretation Method for Concrete Dam Displacement Considering the Lag Effect and the Impact of Cracks,” Engineering Research Express, vol. 7, no. 2, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
35. Muhammad Fikri Alam et al., “Optimizing Multi-Layer Perceptron Performance in Sentiment Classification through Neural Network Feature Extraction,” BACA: Journal of Documentation and Information, vol. 46, no. 1, pp. 1-14, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
36. Xiang Yu et al., “A Continual-Learning-based Multilayer Perceptron for Improved Reconstruction of Three-dimensional Nitrate Concentrations,” Earth System Science Data, vol. 17, no. 6, pp. 2735-2759, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
37. Bandar Alshawi, “Comparison of SVM Kernels in Credit Card Fraud Detection using GANs,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 15, no. 1, pp. 330-337, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
38. Carlos Aníbal Suárez et al., “Improving SVM Performance through Data Reduction and Misclassification Analysis with Linear Programming,” Complex & Intelligent Systems, vol. 11, no. 8, pp. 1-9, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
39. Andrew Oosthuizen, Marelie H. Davel, and Albert Helberg, “Multi-Layer Perceptron for Channel State Information Estimation: Design Considerations,” Southern Africa Telecommunication Networks and Applications Conference (SATNAC) 2022, South Africa, pp. 94-99, 2022.
    [Google Scholar] [Publisher Link]
40. Yildiran Yilmaz et al., “Predicting Mechanical Properties in Geopolymer Mortars, Including Novel Precursor Combinations, through XGBoost Method,” Arabian Journal for Science and Engineering, vol. 50, no. 3, pp. 2009-2033, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]