We present MMLSv2, a dataset for landslide segmentation on Martian surfaces. MMLSv2 consists of multimodal imagery with seven bands: RGB, digital elevation model, slope, thermal inertia, and grayscale channels. MMLSv2 comprises 664 images distributed across training, validation, and test splits. In addition, an isolated test set of 276 images from a geographically disjoint region from the base dataset is released to evaluate spatial generalization. Experiments conducted with multiple segmentation models show that the dataset supports stable training and achieves competitive performance, while still posing challenges in fragmented, elongated, and small-scale landslide regions. Evaluation on the isolated test set leads to a noticeable performance drop, indicating increased difficulty and highlighting its value for assessing model robustness and generalization beyond standard in-distribution settings. Dataset will be available at: https://github.com/MAIN-Lab/MMLS_v2
@article{arxiv.2602.08112,
title = {MMLSv2: A Multimodal Dataset for Martian Landslide Detection in Remote Sensing Imagery},
author = {Sidike Paheding and Abel Reyes-Angulo and Leo Thomas Ramos and Angel D. Sappa and Rajaneesh A. and Hiral P. B. and Sajin Kumar K. S. and Thomas Oommen},
journal= {arXiv preprint arXiv:2602.08112},
year = {2026}
}