Mars-Bench Atmospheric Dust Classification, HiRISE RDR Tiles (Dusty vs Not Dusty)
- Provider
- Mirali Purohit, Hannah Kerner et al. (Mars-Bench, Arizona State University)
- License
- CC-BY-4.0 (source)
- Size
- 20 files
- Format
- CSV, Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/Mirali33/mb-atmospheric_dust_cls_rdr)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.48550/arXiv.2510.24010
- Category
- Astronomy & Space
- Source
- https://huggingface.co/datasets/Mirali33/mb-atmospheric_dust_cls_rdr
About this dataset
Binary classification of dust-obscured versus clear MRO HiRISE views of Mars, using 100 x 100 pixel tiles from Reduced Data Record (RDR) products, the processed and downsampled HiRISE images used for quick viewing and first analysis. Labels (dusty, not_dusty) come from the Doran (2019) HiRISE atmospheric dust dataset, class-balanced into 9,817 training, 4,969 validation and 5,214 test tiles, with 1-, 2-, 5-, 10-, 15- and 20-shot training subsets. It mirrors mb-atmospheric_dust_cls_edr on raw EDR frames, which makes the pair a test of whether a model is robust to the processing level of orbital imagery. Parquet shards under data/ carry the image and label; annotation.csv and mapping.json give the file list and class names. Load with the Hugging Face datasets library. About 200 MB. Part of Mars-Bench (Purohit et al., NeurIPS 2025 Datasets and Benchmarks track, arXiv:2510.24010), 20 standardized Mars datasets released by the authors under CC BY 4.0; cite Mars-Bench and Doran (2019).
How to load this dataset in Python
import pandas as pd
df = pd.read_csv("hf://datasets/Mirali33/mb-atmospheric_dust_cls_rdr/annotation.csv")
df.head()Data structure
File types in sampled files: CSV, Parquet
Files
Example file: annotation.csv
Analyze this dataset without downloading it
On Scigantic, Mars-Bench Atmospheric Dust Classification, HiRISE RDR Tiles (Dusty vs Not Dusty) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
This page is also available as Markdown and as JSON.
Related Astronomy & Space datasets
- ExoMiner++ TESS 2-Minute Threshold-Crossing Events (TCEs), Sectors 1-67: Vetting Features and Labels for 204,729 Transit Signals
- Multimodal Universe: TESS SPOC Light Curves for 1.1 Million Stars (HATS)
- Multimodal Universe: Galaxy10 DECaLS Galaxy Morphology Images (17,736 Galaxies, HATS)
- Lunar South Pole Synthetic Orthographic Renders for Terrain Relative Navigation (LOLA DEMs, 60-Sun Grid)
- Multimodal Universe DESI x SDSS Cross-Matched Spectra Pairs (13,794 Galaxies)
- DMSP Space Environment Sensor Data: SSJ Precipitating Particles, SSIES-3 Thermal Plasma and SSM Magnetometer, F06 to F19 (CDAWeb on HelioCloud)
- GALEX Galaxy Evolution Explorer Observation Log from MAST: 274,911 Ultraviolet Pointings, 2003-2013
- Sup3rCC