|About this Abstract
||MS&T21: Materials Science & Technology
||Accelerating Materials Science with Big Data and Machine Learning
||Predicting Glass Behaviour from Optical Microscopy Images Using Interpretable Machine Learning
||Ankur Agrawal, Mohd Zaki, Ravinder Bhattoo, N. M. Anoop Krishnan
|On-Site Speaker (Planned)
The deformation behavior of glasses can be classified as “normal” and “anomalous” based on the fracture pattern resulting upon indentation. When the indentation response is shear flow controlled, glasses are said to exhibit “normal” behavior. In contrast, when ring-cone cracks appear upon indentation, the glasses are said to be “anomalous”. To predict properties from microscopy images using machine learning models, we should first be able to extract features from the images. In this work, we demonstrate the ability of neural models pretrained on large datasets to extract features from microscopy images and classify the nature of glasses. Further, we also visualize those features using model explanation methods of GradientSHAP, Integrated Gradients and Occlusion. Overall, this study will guide the researchers in harnessing the capabilities of transfer learning and feature visualization for glass science.