About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Alloy Development for Energy Technologies: ICME Gap Analysis
|
Presentation Title |
Unsupervised Techniques for Outlier Identification in Alloy Datasets |
Author(s) |
Madison Wenzlick, Osman Mamun, M.F.N. Taufique, Ram Devanathan, Keerti Kappagantula, Kelly Rose, Jeffrey Hawk |
On-Site Speaker (Planned) |
Madison Wenzlick |
Abstract Scope |
An increasing emphasis is being placed on the importance of data processing and quality for improving the trustworthiness of machine learning (ML) models and their relevance to material science challenges. Assessing outliers in a dataset can inform where data are not well represented, and where in the data space the resulting model may be less confident. Further, the presence of outliers may result in model overfitting. In this work, we apply dimensionality reduction and unsupervised clustering to two alloy datasets and explore the presence of outliers across the multi-dimensional alloy space. Outliers are assessed relative to each cluster as well as to the overall dataset, and the characteristics of the outlier points are explored to validate the outlier label. The resulting changes in the performance of a ML regression model are investigated after removing outliers. The effect of adding new data on the outlier identification process is explored. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, High-Temperature Materials, ICME |