Prediction of Concrete Dam Deformation through the Combination of Machine Learning Models

Dam safety monitoring is of vital importance, due to the high number of fatalities and large economic damage that a failure might imply. This, along with the evolution of artificial intelligence, has led to machine learning techniques being increasingly applied in this field. Many researchers have successfully trained models to predict dam behavior, but errors vary depending on the method used, meaning that the optimal model is not always the same over time. The main goal of this paper is to improve model precision by combining different models. Our research focuses on the comparison of two successful integration strategies in other areas: Stacking and Blending. The methodology was applied to the prediction of radial movements of an arch-gravity dam and was divided into two parts. First, we compared the usual method of estimating model errors and their hyperparameters, i.e., Random Cross Validation and Blocked Cross Validation. This aspect is relevant not only for the importance of robust estimates, but also because it is the source of the data sets used to train meta-learners. The second and main research topic of this paper was the comparison of combination strategies, for which two different types of tests were performed. The results obtained suggest that Blocked CV outperforms the random approach in robustness and that Stacking provides better predictions than Blending. The generalized linear meta-learners trained by the Stacking strategy achieved higher accuracy than the individual models in most cases.

Automated summary

This research aims to improve the accuracy of dam behavior prediction by combining different models. Firstly, two methods of model error estimation were compared, and it was found that Blocked Cross Validation outperforms Random Cross Validation in robustness. Then, two combination strategies were tested, and the results suggest that Stacking provides better predictions than Blending.