Abstract
Modern machine learning methods, such as tree ensembles, have recently become extremely popular due to their versatility and scalability in handling heterogeneous data and have been successfully applied across a wide range of domains. In this study, two widely applied tree ensemble methods, i.e., random forest (parallel ensemble) and gradient boosting (sequential ensemble), were investigated to predict resilient modulus, using routinely collected soil properties. Laboratory test data on sandy soils from nine borrow pits in Georgia were used for model training and testing. For comparison purposes, the two tree ensemble methods were evaluated against a regression tree model and a multiple linear regression model, demonstrating their superior performance. The results revealed that a single tree model generally suffers from high variance, while providing a similar performance to the traditional multiple linear regression model. By leveraging a collection of trees, both tree ensemble methods, Random Forest and eXtreme Gradient Boosting, significantly reduced variance and improved prediction accuracy, with the eXtreme Gradient Boosting being the best model, with an R2 of 0.95 on the test dataset.
Highlights
Modern machine learning methods, such as tree ensembles, have recently become extremely popular due to their versatility and scalability in handling heterogeneous data and have been successfully applied across a wide range of domains
We explored the utility of Decision Tree, Random Forest (RF), and XGBoost methods in modeling and predicting the subgrade resilient modulus of subgrade materials
The tree-based models developed were further compared with a traditional Multiple Linear Regression (MLR) model fitted using the same training dataset to demonstrate the superiority of the tree ensemble methods
Summary
As many state transportation agencies start adopting or plan to adopt the Mechanistic–. The goal in selecting a design MR is to characterize the subgrade soil according to its physical properties and behavior within the pavement structure. Laboratory testing of the soil at the density, moisture content, and stresses that are experienced during the pavement design life is recommended. State transportation agencies view the laboratory resilient modulus testing as timeconsuming, complicated, or resource intensive [6]. Yau and Von Quintus [7] noted that most state transportation agencies did not routinely test for the MR of subgrade soils. The utility of modern machine learning methods, i.e., tree ensembles, were explored in modeling and predicting MR using routinely collected soil index properties in Georgia.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have