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