Cornerstones are the Key Stones: Using Interpretable Machine Learning to Probe the Clogging Process in 2D Granular Hoppers

TL;DR

This study uses interpretable machine learning to identify key grains influencing clogging in granular flow, revealing how positioning a single grain can significantly alter flow duration and mass ejected.

Contribution

The paper demonstrates that simple, interpretable ML models can uncover physical insights into clogging mechanisms, specifically highlighting the role of a cornerstone grain in flow arrest.

Findings

Cornerstone grain position influences arch formation and clogging likelihood.

Proper placement of a cornerstone grain can increase ejected mass by over 50%.

Interpretable ML models reveal meaningful physical factors despite modest predictive accuracy.

Abstract

The sudden arrest of flow by formation of a stable arch over an outlet is a unique and characteristic feature of granular materials. Previous work suggests that grains near the outlet randomly sample configurational flow microstates until a clog-causing flow microstate is reached. However, factors that lead to clogging remain elusive. Here we experimentally observe over 50,000 clogging events for a tridisperse mixture of quasi-2D circular grains, and utilize a variety of machine learning (ML) methods to search for predictive signatures of clogging microstates. This approach fares just modestly better than chance. Nevertheless, our analysis using linear Support Vector Machines (SVMs) highlights the position of potential arch cornerstones as a key factor in clogging likelihood. We verify this experimentally by varying the position of a fixed (cornerstone) grain, and show that such a grain dictates the size of feasible flow-ending arches, and thus the time and mass of each flow. Positioning this grain correctly can even increase the ejected mass by over 50%. Our findings demonstrate that interpretable ML algorithms like SVMs can uncover meaningful physics even when their predictive power is below the standards of conventional ML practice.