An official website of the United States government
Experimental results reveal that rocking shallow foundations reduce earthquake-induced force and flexural displacement demands transmitted to structures and can be used as an effective geotechnical seismic isolation mechanism. This paper presents data-driven predictive models for maximum acceleration transmitted to structures founded on rocking shallow foundations during earthquake loading. Results from base-shaking experiments on rocking foundations have been utilized for the development of artificial neural network regression (ANN), k-nearest neighbors regression, support vector regression, random forest regression, adaptive boosting regression, and gradient boosting regression models. Acceleration amplification ratio, defined as the maximum acceleration at the center of gravity of a structure divided by the peak ground acceleration of the earthquake, is considered as the prediction parameter. For five out of six models developed in this study, the overall mean absolute percentage error in predictions in repeated k-fold cross validation tests vary between 0.128 and 0.145, with the ANN model being the most accurate and most consistent. The cross validation mean absolute error in predictions of all six models vary between 0.08 and 0.1, indicating that the maximum acceleration of structures supported by rocking foundations can be predicted within an average error limit of 8% to 10% of the peak ground acceleration of the earthquake.
more »
« less
Data-Driven Modeling of Seismic Energy Dissipation of Rocking Foundations Using Decision Tree-Based Ensemble Machine Learning Algorithms
The objective of this study is to develop data-driven predictive models for seismic energy dissipation of rocking shallow foundations during earthquake loading using decision tree-based ensemble machine learning algorithms and supervised learning technique. Data from a rocking foundation’s database consisting of dynamic base shaking experiments conducted on centrifuges and shaking tables have been used for the development of a base decision tree regression (DTR) model and four ensemble models: bagging, random forest, adaptive boosting, and gradient boosting. Based on k-fold cross-validation tests of models and mean absolute percentage errors in predictions, it is found that the overall average accuracy of all four ensemble models is improved by about 25%–37% when compared to base DTR model. Among the four ensemble models, gradient boosting and adaptive boosting models perform better than the other two models in terms of accuracy and variance in predictions for the problem considered.
more »
« less
- Award ID(s):
- 2138631
- PAR ID:
- 10486042
- Publisher / Repository:
- American Society of Civil Engineers
- Date Published:
- Journal Name:
- Geo-Congress 2023
- ISBN:
- 9780784484692
- Page Range / eLocation ID:
- 298 to 308
- Format(s):
- Medium: X
- Location:
- Los Angeles, California
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The objective of this study is to develop data-driven predictive models for permanent settlement of rocking shallow foundations during seismic loading using multiple machine learning algorithms and supervised learning technique. Data from a rocking foundation database consisting of dynamic base shaking experiments conducted on centrifuges and shaking tables have been used for the development of k-nearest neighbors regression, support vector regression, and random forest regression models. Based on repeated k-fold cross validation tests of models and mean absolute percentage errors in their predictions, it is found that all three models perform better than a baseline multivariate linear regression model in terms of accuracy and variance in predictions. The average mean absolute errors in predictions of all three models are around 0.005 to 0.006, indicating that the rocking induced permanent settlement can be predicted within an average error limit of 0.5% to 0.6% of the width of the footing.more » « less
-
IntroductionThe objective of this study is to develop predictive models for rocking-induced permanent settlement in shallow foundations during earthquake loading using stacking, bagging and boosting ensemble machine learning (ML) and artificial neural network (ANN) models. MethodsThe ML models are developed using supervised learning technique and results obtained from rocking foundation experiments conducted on shaking tables and centrifuges. The overall performance of ML models are evaluated using k-fold cross validation tests and mean absolute percentage error (MAPE) and mean absolute error (MAE) in their predictions. ResultsThe performances of all six nonlinear ML models developed in this study are relatively consistent in terms of prediction accuracy with their average MAPE varying between 0.64 and 0.86 in final k-fold cross validation tests. DiscussionThe overall average MAE in predictions of all nonlinear ML models are smaller than 0.006, implying that the ML models developed in this study have the potential to predict permanent settlement of rocking foundations with reasonable accuracy in practical applications.more » « less
-
null (Ed.)Learning nonlinear functions from input-output data pairs is one of the most fundamental problems in machine learning. Recent work has formulated the problem of learning a general nonlinear multivariate function of discrete inputs, as a tensor completion problem with smooth latent factors. We build upon this idea and utilize two ensemble learning techniques to enhance its prediction accuracy. Ensemble methods can be divided into two main groups, parallel and sequential. Bagging also known as bootstrap aggregation is a parallel ensemble method where multiple base models are trained in parallel on different subsets of the data that have been chosen randomly with replacement from the original training data. The output of these models is usually combined and a single prediction is computed using averaging. One of the most popular bagging techniques is random forests. Boosting is a sequential ensemble method where a sequence of base models are fit sequentially to modified versions of the data. Popular boosting algorithms include AdaBoost and Gradient Boosting. We develop two approaches based on these ensemble learning techniques for learning multivariate functions using the Canonical Polyadic Decomposition. We showcase the effectiveness of the proposed ensemble models on several regression tasks and report significant improvements compared to the single model.more » « less
-
Ensemble models (bagging and gradient-boosting) of relational decision trees have proved to be some of the most effective learning methods in the area of probabilistic logic models (PLMs). While effective, they lose one of the most important benefits of PLMs—interpretability. In this paper we consider the problem of compressing a large set of learned trees into a single explainable model. To this effect, we propose CoTE—Compression of Tree Ensembles—that produces a single small decision list as a compressed representation. CoTE first converts the trees to decision lists and then performs the combination and compression with the aid of the original training set. An experimental evaluation demonstrates the effectiveness of CoTE in several benchmark relational data sets.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1061/9780784484692.031
