Software Open Access

Sea-Ice Floe Segmentation

Denton, Alexis Anne

This repository contains a user-friendly, MATLAB Live Script to easily and automatically segment sea ice floes (chunks) in imagery (for example, from satellites or aerial platforms).

The algorithm and code were written by Alexis Denton (Yale University) for and used to segment high-resolution optical satellite images in the accompanying submitted manuscript (preprint, in review) coauthored with Mary-Louise Timmermans (Yale University), Denton and Timmermans (2021)

This algorithm was developed to contribute an easy, automated, and reproducible method to the Arctic science community for the identification of sea ice floes in remote sensing imagery. If you use this algorithm in your work or research or for any other reason, credit the author here (Alexis Denton) and cite the code DOI issued by Zenodo. The DOI badge to the right points to the latest released version of the repository.

The development of this code and the research presented in the manuscript was funded by the Office of Naval Research as a part of their Multi-University Research Initiative (MURI) Mathematics and Data Science for Physical Modeling and Prediction of Sea Ice. To learn more about the work of the Sea Ice MURI, please visit

For further details about the algorithm, please see Denton and Timmermans (2021)

Version 1.0.1 Note: This version is functionally the same as v1.0.0 (same MATLAB code). The only difference is that this release does not include older figure files for display in the README from the pre-release version; it only includes figure files used in the first release README file.

Files (6.0 MB)
Name Size
6.0 MB Download
  • Denton, A. A. and Timmermans, M.-L.: Characterizing the Sea-Ice Floe Size Distribution in the Canada Basin from High-Resolution Optical Satellite Imagery, The Cryosphere Discuss. [preprint],, in review, 2021.

All versions This version
Views 246140
Downloads 3224
Data volume 199.8 MB144.0 MB
Unique views 11689
Unique downloads 3024


Cite as