Understanding Ice Crystal Habit Diversity with Self-Supervised Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ko, Joseph, Govindarajan, Hariprasath, Lindsten, Fredrik, Przybylo, Vanessa, Sulia, Kara, van Lier-Walqui, Marcus, Lamb, Kara
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915594440278016
author Ko, Joseph
Govindarajan, Hariprasath
Lindsten, Fredrik
Przybylo, Vanessa
Sulia, Kara
van Lier-Walqui, Marcus
Lamb, Kara
author_facet Ko, Joseph
Govindarajan, Hariprasath
Lindsten, Fredrik
Przybylo, Vanessa
Sulia, Kara
van Lier-Walqui, Marcus
Lamb, Kara
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07688
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Understanding Ice Crystal Habit Diversity with Self-Supervised Learning
Ko, Joseph
Govindarajan, Hariprasath
Lindsten, Fredrik
Przybylo, Vanessa
Sulia, Kara
van Lier-Walqui, Marcus
Lamb, Kara
Atmospheric and Oceanic Physics
Computer Vision and Pattern Recognition
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.
title Understanding Ice Crystal Habit Diversity with Self-Supervised Learning
topic Atmospheric and Oceanic Physics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.07688