2019
DOI: 10.1557/mrc.2019.118
|View full text |Cite
|
Sign up to set email alerts
|

A data ecosystem to support machine learning in materials science

Abstract: words):Facilitating the application of machine learning to materials science problems requires enhancing the data ecosystem to enable discovery and collection of data from many sources, automated dissemination of new data across the ecosystem, and the connecting of data with materialsspecific machine learning models. Here, we present two projects, the Materials Data Facility (MDF) and the Data and Learning Hub for Science (DLHub), that address these needs. We use examples to show how MDF and DLHub capabilities… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
104
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
6
2
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 155 publications
(105 citation statements)
references
References 29 publications
1
104
0
Order By: Relevance
“…These uniform assemblies were slightly larger than the PCMs formed from PEG-PLK and PEG-PVBTMA, attributed to the highly solvated PMPC corona that accounts for the difference between the lengths determined by a hydrodynamic volume and Guinier approximation for each scattering technique, respectively. Scattering data are available through the Materials Data Facility [69,70] at doi:10.18126/n4un-6usf [71].…”
Section: Discussionmentioning
confidence: 99%
“…These uniform assemblies were slightly larger than the PCMs formed from PEG-PLK and PEG-PVBTMA, attributed to the highly solvated PMPC corona that accounts for the difference between the lengths determined by a hydrodynamic volume and Guinier approximation for each scattering technique, respectively. Scattering data are available through the Materials Data Facility [69,70] at doi:10.18126/n4un-6usf [71].…”
Section: Discussionmentioning
confidence: 99%
“…DLHub also provides a model serving framework for executing inference and other tasks over arbitrary data. DLHub has been exploited by several research projects with success, such as [30], [31].…”
Section: Related Work Regarding Machine Learning Platformsmentioning
confidence: 99%
“…The raw and processed data required to reproduce these findings are available to download from https://doi.org/10.18126/TW5W-XTWE [53] via the Materials Data Facility [54,55].…”
Section: Research Datamentioning
confidence: 99%