Mars-Bench DoMars16k: Martian Landform Classification from MRO CTX (15 classes)
- 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-domars16k)
- 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-domars16k
About Mars-Bench DoMars16k: Martian Landform Classification from MRO CTX (15 classes)
Landform classification on Mars from 200 x 200 pixel MRO Context Camera (CTX) tiles, revised from DoMars16k (Wilhelm et al., 2020). Fifteen classes cover aeolian, fluvial, impact and mass-wasting morphology: aeolian straight and curved bedforms, rough, smooth, textured and mixed terrain, cliffs, ridges, mounds, channels, gullies, slope streaks, mass wasting, craters and crater fields. Splits keep the original partition (11,305 training, 3,231 validation, 1,614 test) and add 1- to 20-shot subsets. A standard test for planetary geomorphology classifiers and for transfer from Earth-observation foundation models. Parquet shards under data/ store the image and label; mapping.json maps the three-letter codes (ael, rou, cli, fsg ...) to names, and annotation.csv lists files. Load with datasets.load_dataset("Mirali33/mb-domars16k"). About 230 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 Wilhelm et al. (2020).
How to load this dataset in Python
import pandas as pd
df = pd.read_csv("hf://datasets/Mirali33/mb-domars16k/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 DoMars16k: Martian Landform Classification from MRO CTX (15 classes) 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
- Mars-Bench MarsSeg MER: Terrain Segmentation for Spirit and Opportunity Navcam/Pancam
- K2 Mission Observation Log from MAST: 764,820 Target Observations Across Campaigns C0-C19 with EPIC IDs
- ISS FPMU Floating Potential Measurement Unit: Ionospheric Plasma Density, Electron Temperature and Station Charging, 2006-2020 (CDAWeb on HelioCloud)
- Mars-Bench Dust Devil Detection, MRO CTX (YOLO/COCO/VOC boxes)
- MIT Quick-Look Pipeline (QLP): TESS full-frame-image light curves
- OMNI Solar Wind and IMF Data: 1-Minute, 5-Minute and Hourly Bow-Shock-Shifted Parameters, 1963-present (CDAWeb on HelioCloud)
- MARE Lunar Rover Dataset: Synthetic Multisensor Frames with Depth, Object and Shadow Ground Truth
- Multimodal Universe: PLAsTiCC Simulated LSST Light Curves