Plebani, Emanuele and Ehlmann, Bethany L. and Leask, Ellen K. and Fox, Valerie K. and Dundar, M. Murat (2022) A machine learning toolkit for CRISM image analysis. Icarus, 376 . Art. No. 114849. ISSN 0019-1035. doi:10.1016/j.icarus.2021.114849. https://resolver.caltech.edu/CaltechAUTHORS:20220112-214290393
This is the latest version of this item.
![[img]](https://authors.library.caltech.edu/style/images/fileicons/application_pdf.png) |
PDF
- Published Version
Creative Commons Attribution Non-commercial No Derivatives. 9MB |
|
PDF (MMC S1. Technical details of the model)
- Supplemental Material
Creative Commons Attribution Non-commercial No Derivatives. 555kB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20220112-214290393
Abstract
Hyperspectral images collected by remote sensing have played a significant role in the discovery of aqueous alteration minerals, which in turn have important implications for our understanding of the changing habitability on Mars. Traditional spectral analyzes based on summary parameters have been helpful in converting hyperspectral cubes into readily visualizable three channel maps highlighting high-level mineral composition of the Martian terrain. These maps have been used as a starting point in the search for specific mineral phases in images. Although the amount of labor needed to verify the presence of a mineral phase in an image is quite limited for phases that emerge with high abundance, manual processing becomes laborious when the task involves determining the spatial extent of detected phases or identifying small outcrops of secondary phases that appear in only a few pixels within an image. Thanks to extensive use of remote sensing data and rover expeditions, significant domain knowledge has accumulated over the years about mineral composition of several regions of interest on Mars, which allow us to collect reliable labeled data required to train machine learning algorithms. In this study we demonstrate the utility of machine learning in two essential tasks for hyperspectral data analysis: nonlinear noise removal and mineral classification. We develop a simple yet effective hierarchical Bayesian model for estimating distributions of spectral patterns and extensively validate this model for mineral classification on several test images. Our results demonstrate that machine learning can be highly effective in exposing tiny outcrops of specific phases in orbital data that are not uncovered by traditional spectral analysis. We package implemented scripts, documentation illustrating use cases, and pixel-scale training data collected from dozens of well-characterized images into a new toolkit. We hope that this new toolkit will provide advanced and effective processing tools and improve community’s ability to map compositional units in remote sensing data quickly, accurately, and at scale.
| Item Type: | Article | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Related URLs: |
| ||||||||||||
| ORCID: |
| ||||||||||||
| Additional Information: | © 2021 The Author(s). Published by Elsevier Under a Creative Commons license - Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0). Received 29 June 2021, Revised 18 October 2021, Accepted 6 December 2021, Available online 1 January 2022. Thanks to the CRISM science and operations teams for their work to collect and process these datasets. Thanks to Abigail A. Fraeman for her feedback on a subset of detections. B.L.E and M.D. were sponsored by NASA, USA under Grant Number 80NSSC19K1594. M.D. was sponsored by the National Science Foundation (NSF), USA under Grant Number IIS-1252648 (CAREER). Data Availability. Training datasets and training segmentation maps can be downloaded from https://cs.iupui.edu/~mdundar/CRISM.htm. The toolkit with a user friendly Python notebook, source codes, and documentation is hosted at https://github.com/Banus/crism_ml. | ||||||||||||
| Funders: |
| ||||||||||||
| Subject Keywords: | Machine learning; Hyperspectral image; Mars; Hierarchical Bayesian; CRISM | ||||||||||||
| DOI: | 10.1016/j.icarus.2021.114849 | ||||||||||||
| Record Number: | CaltechAUTHORS:20220112-214290393 | ||||||||||||
| Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20220112-214290393 | ||||||||||||
| Official Citation: | Emanuele Plebani, Bethany L. Ehlmann, Ellen K. Leask, Valerie K. Fox, M. Murat Dundar, A machine learning toolkit for CRISM image analysis, Icarus, Volume 376, 2022, 114849, ISSN 0019-1035, https://doi.org/10.1016/j.icarus.2021.114849. | ||||||||||||
| Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||||||||
| ID Code: | 112845 | ||||||||||||
| Collection: | CaltechAUTHORS | ||||||||||||
| Deposited By: | George Porter | ||||||||||||
| Deposited On: | 12 Jan 2022 11:40 | ||||||||||||
| Last Modified: | 13 Jan 2022 00:02 |
Available Versions of this Item
- A machine learning toolkit for CRISM image analysis. (deposited 12 Jan 2022 11:40) [Currently Displayed]
Commentary/Response Threads
- Plebani, Emanuele and Ehlmann, Bethany L. and Leask, Ellen K. and Fox, Valerie K. and Dundar, M. Murat A machine learning toolkit for CRISM image analysis. (deposited 12 Jan 2022 11:40) [Currently Displayed]
Repository Staff Only: item control page
