# Machine Learning with COSIMA data **URL:** \ **Category:** Ocean\ **Tags:** cosima, machine-learning\ **Created:** [30 April 2025 01:37 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449 "2025-04-30T01:37:13Z")\ **Posts on this page:** 9\ **Page:** 1
**Author:** ![PSpence](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/pspence/32/298_2.png) [@PSpence](https://forum.access-hive.org.au/u/PSpence)\ **Post date:** [30 April 2025 01:37 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/1 "2025-04-30T01:37:13Z")
Hi Folks, I am looking for examples where AI/ML was applied to COSIMA data. A quick “machine” word search on paper titles that cite Kiss et al. 2020 comes up empty. If you know of any working examples please let me know 🙂 Thank you, Paul ---
**Author:** ![adele-morrison](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/adele-morrison/32/90_2.png) [@adele-morrison](https://forum.access-hive.org.au/u/adele-morrison)\ **Post date:** [30 April 2025 01:52 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/2 "2025-04-30T01:52:19Z")
@taimoorsohail @pearseb @nmalan all have work that fits this category. ---
**Author:** ![PSpence](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/pspence/32/298_2.png) [@PSpence](https://forum.access-hive.org.au/u/PSpence)\ **Post date:** [30 April 2025 02:24 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/3 "2025-04-30T02:24:22Z")
Taimoors paper is here [https://www.authorea.com/doi/full/10.22541/au.173264116.62054531](https://www.authorea.com/doi/full/10.22541/au.173264116.62054531) Pearse’s paper is here: [EGUsphere - Optimisation of the World Ocean Model of Biogeochemistry and Trophic-dynamics (WOMBAT) using surrogate machine learning methods](https://egusphere.copernicus.org/preprints/2025/egusphere-2024-4026/) ---
**Author:** ![lidefi87](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/lidefi87/32/91_2.png) [@lidefi87](https://forum.access-hive.org.au/u/lidefi87)\ **Post date:** [30 April 2025 22:32 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/4 "2025-04-30T22:32:36Z")
Hi Paul, I used ACCESS-OM2-01 to estimate the distribution of crabeater seals. I used two machine learning algorithms: boosted regression trees and Random Forests together with two regression based methods. This is under review at the moment. Not the usual application but may be of interest. ---
**Author:** ![navidcy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/navidcy/32/101_2.png) [@navidcy](https://forum.access-hive.org.au/u/navidcy)\ **Post date:** [5 May 2025 04:52 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/5 "2025-05-05T04:52:46Z")
I believe @taimoorsohail, @janzika and collaborators of theirs have more than one relevant papers on this. @PSpence, I’m intrigued tho: why you want to collate such a list? You didn’t provide us any context. ---
**Author:** ![navidcy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/navidcy/32/101_2.png) [@navidcy](https://forum.access-hive.org.au/u/navidcy)\ **Post date:** [5 May 2025 05:07 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/6 "2025-05-05T05:07:49Z")
**ACCESS-OM2** 1. Sohail, T. & Zika, J. D. Unsupervised classification identifies warm, fresh and dense regimes of the Antarctic margins. Journal of Physical Oceanography(2024), 54, 1229–1242. doi:[10.1175/JPO-D-23-0153.1](https://doi.org/10.1175/JPO-D-23-0153.1) 2. Sohail, T., Zika, J. D., & Ehmen, T. How accurate are salinity measurements around Antarctica? A machine learning based approach. Submitted to Machine Learning: Earth (2025). [Preprint](https://doi.org/10.22541/au.173264116.62054531/v1) **ACCESS-CM2** (which has an ACCESS-OM2 ocean?) 1. Piedagnel, E., Sohail, T., & Zika, J. D. Mapping ocean salinity data using Gaussian Mixture Modelling. Submitted to Artificial Intelligence for the Earth Systems (2025). [Preprint](https://doi.org/10.22541/au.173016184.43617162/v1) ---
**Author:** ![navidcy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/navidcy/32/101_2.png) [@navidcy](https://forum.access-hive.org.au/u/navidcy)\ **Post date:** [5 May 2025 05:09 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/7 "2025-05-05T05:09:58Z")
@janzika also! ---
**Author:** ![navidcy](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/navidcy/32/101_2.png) [@navidcy](https://forum.access-hive.org.au/u/navidcy)\ **Post date:** [5 May 2025 05:12 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/8 "2025-05-05T05:12:13Z")
there is no pre-decided notion of what is considered “usual applications” for this 🙂 ---
**Author:** ![taimoorsohail](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.access-hive.org.au/taimoorsohail/32/201_2.png) [@taimoorsohail](https://forum.access-hive.org.au/u/taimoorsohail)\ **Post date:** [7 May 2025 05:55 UTC](https://forum.access-hive.org.au/t/machine-learning-with-cosima-data/4449/9 "2025-05-07T05:55:31Z")
Thanks @navidcy! It’s a bit unclear what constitutes ML or AI. There are the typical neural networks, random forest, etc, but there’s also unsupervised clustering methods which could be considered more stats/data science. Anyway, depending on the actual interpretation, there’s an additional paper myself and co-authors wrote which uses an image compression algorithm to subset the ACCESS-CM2 ocean: Sohail, T., Holmes, R. M., Zika, J. D. Watermass co-ordinates isolate the historical ocean warming signal. Journal of Climate (2023), 36, 3063–3081, doi:[10.1175/JCLI-D-22-0363.1](https://doi.org/10.1175/JCLI-D-22-0363.1)