A study of real-world micrograph data quality and machine learning model robustness

Machine-learning (ML) techniques hold the potential of enabling efficient quantitative micrograph analysis, but the robustness of ML models with respect to real-world micrograph quality variations has not been carefully evaluated. We collected thousands of scanning electron microscopy (SEM) microgra...

Full description

Saved in:
Bibliographic Details
Published in:npj computational materials 2021-10, Vol.7 (1), p.1-11, Article 161
Main Authors: Zhong, Xiaoting, Gallagher, Brian, Eves, Keenan, Robertson, Emily, Mundhenk, T. Nathan, Han, T. Yong-Jin
Format: Article
Language:English
Subjects:
639/301/1034
639/301/930
Automation
Characterization and Evaluation of Materials
Chemistry and Materials Science
Compressive strength
Computational Intelligence
Datasets
Deep learning
Laboratories
Learning algorithms
Machine learning
MATERIALS SCIENCE
Mathematical and Computational Engineering
Mathematical and Computational Physics
Mathematical Modeling and Industrial Mathematics
Micrography
Microstructure
Photomicrographs
Pixels
Robustness
Scanning electron microscopy
Theoretical
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine-learning (ML) techniques hold the potential of enabling efficient quantitative micrograph analysis, but the robustness of ML models with respect to real-world micrograph quality variations has not been carefully evaluated. We collected thousands of scanning electron microscopy (SEM) micrographs for molecular solid materials, in which image pixel intensities vary due to both the microstructure content and microscope instrument conditions. We then built ML models to predict the ultimate compressive strength (UCS) of consolidated molecular solids, by encoding micrographs with different image feature descriptors and training a random forest regressor, and by training an end-to-end deep-learning (DL) model. Results show that instrument-induced pixel intensity signals can affect ML model predictions in a consistently negative way. As a remedy, we explored intensity normalization techniques. It is seen that intensity normalization helps to improve micrograph data quality and ML model robustness, but microscope-induced intensity variations can be difficult to eliminate.
ISSN:2057-3960
2057-3960
DOI:10.1038/s41524-021-00616-3