Machine Learning Raman Open Dataset (MLROD)
Last Revision Date: Sep 29, 2022
|
Published Date: Sep 29, 2022
Image credit: Genesis Berlanga
Description
Machine learning specialized Raman spectral dataset of single mineral specimens and binary powder mineral mixtures.
Publication Reference: Genesis Berlanga, Quentin Williams, Nathan Temiquel. (2022) Convolutional Neural Networks as a Tool for Raman Spectral Mineral Classification Under Low Signal, Dusty Mars Conditions. Earth and Space Science.
Data
| File or URL | Description/Data Usage | File Size | Date |
|---|---|---|---|
| https://doi.org/10.48484/PWRB-R137 | Machine Learning Raman Open Dataset (MLROD) A high volume, machine learning specialized, Raman mineral spectra dataset. License: BY-NC Also available at the Open Data Repository: https://odr.io/MLROD | Sep 29, 2022 |
Related Works
| DOI | Description |
|---|---|
| https://doi.org/10.1029/2021EA002125 | Convolutional Neural Networks as a Tool for Raman Spectral Mineral Classification Under Low Signal, Dusty Mars Conditions |
| https://doi.org/10.48484/PWRB-R137 |
Summary
| Lead Investigator(s) |
 Berlanga, Genesis |
|---|---|
| Funding Sources | NSF |
| Mission/Projects | |
| Themes |
Characterizing Environments for Habitability and Biosignatures
|
| Keywords | Neural networks|olivine|muscovite|carbonates|basaltic glass|Machine learning|rocks (general)|gypsum|forsterite|basalt|sulfide|mafic|quartz|minerals (general)|magnesium sulfates|mineral surfaces|computational (general) |
| Disciplines | astrobiology|crystallography|mineralogy|planetary science|geology|spectroscopy|planetary geology |
| Team Members |
Temiquel, Nathan Williams, Quentin |
Fieldwork Location(s)
No Locations Given
How to Cite
When using this dataset, please cite the data package
provided here as well as original publications,
when available.
License terms and conditions apply.
For data available from this server, the U.S. Government does not warrant or assume any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed.