Title: Application of machine learning to the stick-slip dynamics of particulate media

Author (Snapshot): Rituparna Basak, New Jersey Institute of Technology

Abstract:

The stick-slip transition of granular systems is related to earthquakes and avalanches, and therefore understanding the conditions leading to slip events is of general importance. Although stick-slip behavior has been studied extensively, what triggers a slip event still remains unclear. We studied machine learning techniques to analysis of topological data such as force network and persistence diagrams (information of forces, Betti numbers and connectivity) evolving from discrete element simulations of granular system to understand the stick-slip behavior. For predicting the next slip event, we are using some Machine learning algorithms such as Logistic Regression and Support vector machine on a large number of data. The results of the behavior of our model will be shown.