Published January 3, 2022
| Version 1.0.0
Dataset
Open
CRISM ML dataset
Authors/Creators
-
1.
Indiana University – Purdue University Indianapolis
-
2.
California Institute of Technology
-
3.
University of Minnesota
Description
This dataset is required to train the models in the CRISM ML toolbox [1].
In the project, we demonstrate the utility of machine learning in two essential CRISM analysis tasks: nonlinear noise removal and mineral classification. We train a hierarchical Bayesian model for estimating distributions of spectral patterns on pixel-scale training data collected from dozens of well-characterized CRISM images.
The following files are included:
- CRISM_bland_unratioed.mat: unratioed training spectra for bland pixels.
- CRISM_labeled_pixels_ratioed.mat: ratioed training spectra for mineral classes.
- CRISM_labeled_pixel_patterns.pdf: visualization of the training segmentation maps and average spectra.
The training spectra are in Matlab v7.3 (and newer) format. To load them in Python, use the mat73 library, because scipy doesn't support the format.
The bland unratioed spectra have the following variables:
| Name | Size | Description |
|---|---|---|
| pixspec | 337 617 × 350 | Unratioed spectra |
| im_names | 340 | List of CRISM image names, mapping them to numerical IDs |
| pixims | 337 617 | Numerical ID of the image the spectrum is from |
| pixcrds | 337 617 × 2 | (x,y) coordinates of the points in the original image |
The labeled ratioed pixels have the following variables:
| Name | Size | Description |
| pixspec | 592 413 × 350 | Ratioed spectra |
| pixlabs | 592 413 | Mineral labels |
| im_names | 77 | List of CRISM image names, mapping them to numerical IDs |
| pixims | 592 413 | Numerical ID of the image the spectrum is from |
| pixpat | 592 413 | ID of the connected patch in the image the pixel belongs to |
| pixcrds | 592 413 × 2 | (x,y) coordinates of pixels in their respective image |
Citation (cite this paper when using the data):
- Plebani, E., Ehlmann, B. L., Leask, E. K., Fox, V. K., & Dundar, M. M. (2022). A machine learning toolkit for CRISM image analysis. Icarus, 376, 114849.
Files
CRISM_labeled_pixel_patterns.pdf
Files
(2.0 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:7c7c34413c13a76bc66b5047d9223033
|
468.8 MB | Download |
|
md5:7e7b5379778ae1c0e39083e57fa44da4
|
32.0 MB | Preview Download |
|
md5:abba1eefd7ab760cf59ea575e4d06000
|
1.5 GB | Download |
Additional details
Dates
- Accepted
-
2022-01-03
Software
- Repository URL
- https://github.com/Banus/crism_ml
- Programming language
- Python
- Development Status
- Inactive
References
- Plebani, E., Ehlmann, B. L., Leask, E. K., Fox, V. K., & Dundar, M. M. (2022). A machine learning toolkit for CRISM image analysis. Icarus, 376, 114849.