Understanding Ice Crystal Habit Diversity with Self-Supervised Learning
Abstract
Ice-containing clouds strongly impact climate, but they are hard to model due to ice crystal habit (i.e., shape) diversity. We use self-supervised learning (SSL) to learn latent representations of crystals from ice crystal imagery. By pre-training a vision transformer with many cloud particle images, we learn robust representations of crystal morphology, which can be used for various science-driven tasks. Our key contributions include (1) validating that our SSL approach can be used to learn meaningful representations, and (2) presenting a relevant application where we quantify ice crystal diversity with these latent representations. Our results demonstrate the power of SSL-driven representations to improve the characterization of ice crystals and subsequently constrain their role in Earth's climate system.
Cite
@article{arxiv.2509.07688,
title = {Understanding Ice Crystal Habit Diversity with Self-Supervised Learning},
author = {Joseph Ko and Hariprasath Govindarajan and Fredrik Lindsten and Vanessa Przybylo and Kara Sulia and Marcus van Lier-Walqui and Kara Lamb},
journal= {arXiv preprint arXiv:2509.07688},
year = {2025}
}
Comments
Accepted to NeurIPS 2025 Workshop: Tackling Climate Change with Machine Learning