Journal
INTEGRATING MATERIALS AND MANUFACTURING INNOVATION
Volume 9, Issue 3, Pages 221-227Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s40192-020-00179-z
Keywords
Materials informatics; Machine learning; Featurization; Descriptors; Neural networks
Funding
- NSF CAREER Award [DMR 1651668]
- Berlin International Graduate School in Model and Simulation based Research
- German Academic Exchange Service [57438025]
Ask authors/readers for more resources
New featurization schemes for describing materials as composition vectors in order to predict their properties using machine learning are common in the field of Materials Informatics. However, little is known about the comparative efficacy of these methods. This work sets out to make clear which featurization methods should be used across various circumstances. Our findings include, surprisingly, that simple fractional and random-noise representations of elements can be as effective as traditional and new descriptors when using large amounts of data. However, in the absence of large datasets or for data that is not fully representative, we show that the integration of domain knowledge offers advantages in predictive ability. [GRAPHICS] .
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available