Classifying Alloy Surface Preparation Quality with Metadata-Infused Machine Learning for Rapid Alloy Discovery

This repository contains image data that supports the work of an ML-driven framework for automated surface analysis of microscopy images. We create a training dataset by imaging stainless steel samples to benchmark four developed deep neural network architectures. These models, based on a YOLOv8n-cls backend, integrate image features and process metadata using various fusion methods to distinguish between acceptable and unacceptable surface finishes. 

Release Number: LLNL-DATA-2023483
Distribution Type: Unlimited/ CC BY 4.0

This work was performed under the auspices of the US Department of Energy (DOE) by Lawrence Livermore National Laboratory under contract number DE-AC52-07NA27344 and was supported by Laboratory Directed Research and Development (LDRD) funding under project number 25-ERD-039. Work performed by Cornell University was supported under subcontract [SUBCONTRACT NUMBER] with Lawrence Livermore National Laboratory.

We thank the Lawrence Livermore National Laboratory (LLNL) Data Science Summer Institute (DSSI) for their support.