6th World Congress on Integrated Computational Materials Engineering (ICME 2022): Artificial Intelligence & Machine Learning II
Program Organizers: William Joost; Kester Clarke, Los Alamos National Laboratory; Danielle Cote, Worcester Polytechnic Institute; Javier Llorca, IMDEA Materials Institute & Technical University of Madrid; Heather Murdoch, U.S. Army Research Laboratory; Satyam Sahay, John Deere; Michael Sangid, Purdue University
Tuesday 3:50 PM
April 26, 2022
Room: Regency Ballroom DE
Location: Hyatt Regency Lake Tahoe
Session Chair: Zachary Trautt, National Institute Of Standards And Technology
3:50 PM
Machine Learning with Real-World Micrographs: A Study of Data Quality and Model Robustness: Xiaoting Zhong1; Keenan Eves1; Brian Gallagher1; Yong-Jin Han1; 1Lawrence Livermore National Laboratory
In this presentation we show how data quality affect machine learning (ML) models. In particular, we evaluate ML models developed to predict mechanical properties of a molecular solid, 1,3,5-triamino-2,4,6-trinitrobenzene (TATB), using SEM micrographs. Different sets of micrographs were collected with various brightness and contrast settings and stationary microstructure content. Several feature descriptors from different feature classes were applied to encode the micrographs. A random forest model was then trained to predict the ultimate compressive stress of consolidated TATB samples. Results show that instrument-induced pixel intensity signals can be encoded into micrograph feature descriptors and affect ML model predictions in a consistently negative way. Image standardization methods, like histogram equalization, were applied to reduce the instrument-induced signals and successfully improved micrograph feature quality. We conclude that either a careful control of micrograph quality or a careful choice of ML pipeline is necessary to create reliable quantitative micrograph analysis using ML approaches.
4:10 PM
Discovery of Novel High-Entropy Ceramics via Machine Learning: Kevin Kaufmann1; William Mellor1; Olivia Dippo1; Kenneth Vecchio1; 1University of California, San Diego
Although high-entropy materials are attracting considerable interest due to a combination of useful properties and promising applications, predicting their formation remains a hindrance for rational discovery of new systems. Experimental approaches are based on intuition and/or expensive trial and error strategies. Most computational methods rely on the availability of sufficient experimental data and computational power. This work proposes a machine learning framework leveraging thermodynamic and compositional attributes of a given material for predicting the entropy-forming ability of disordered metal carbides. The approach’s suitability is demonstrated by comparing values calculated with density functional theory to ML predictions. Finally, the model is employed to predict the entropy-forming ability of new compositions; several of which are validated by additional density functional theory calculations and experimental synthesis. Compositions were specifically selected because they contain all three of the Group VI elements (Cr, Mo, and W), which do not form room temperature-stable rock-salt monocarbides.