{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T20:55:44Z","timestamp":1775249744816,"version":"3.50.1"},"reference-count":21,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["NR N00014-17-1-2963"],"award-info":[{"award-number":["NR N00014-17-1-2963"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>We performed an out-of-distribution (OOD) analysis of \u223c12,000,000 semi-independent 128 \u00d7 128 pixel2 sea surface temperature (SST) regions, which we define as cutouts, from all nighttime granules in the MODIS R2019 Level-2 public dataset to discover the most complex or extreme phenomena at the ocean\u2019s surface. Our algorithm (ULMO) is a probabilistic autoencoder (PAE), which combines two deep learning modules: (1) an autoencoder, trained on \u223c150,000 random cutouts from 2010, to represent any input cutout with a 512-dimensional latent vector akin to a (non-linear) Empirical Orthogonal Function (EOF) analysis; and (2) a normalizing flow, which maps the autoencoder\u2019s latent space distribution onto an isotropic Gaussian manifold. From the latter, we calculated a log-likelihood (LL) value for each cutout and defined outlier cutouts to be those in the lowest 0.1% of the distribution. These exhibit large gradients and patterns characteristic of a highly dynamic ocean surface, and many are located within larger complexes whose unique dynamics warrant future analysis. Without guidance, ULMO consistently locates the outliers where the major western boundary currents separate from the continental margin. Prompted by these results, we began the process of exploring the fundamental patterns learned by ULMO thereby identifying several compelling examples. Future work may find that algorithms such as ULMO hold significant potential\/promise to learn and derive other, not-yet-identified behaviors in the ocean from the many archives of satellite-derived SST fields. We see no impediment to applying them to other large remote-sensing datasets for ocean science (e.g., SSH and ocean color).<\/jats:p>","DOI":"10.3390\/rs13040744","type":"journal-article","created":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T21:35:42Z","timestamp":1613597742000},"page":"744","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Deep Learning of Sea Surface Temperature Patterns to Identify Ocean Extremes"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7738-6875","authenticated-orcid":false,"given":"J. Xavier","family":"Prochaska","sequence":"first","affiliation":[{"name":"Affiliate of the Department of Ocean Sciences, University of California, Santa Cruz, CA 95064, USA"},{"name":"Department of Astronomy and Astrophysics, University of California, Santa Cruz, CA 95064, USA"},{"name":"Kavli Institute for the Physics and Mathematics of the Universe (Kavli IPMU), 5-1-5 Kashiwanoha, Kashiwa 277-8583, Japan"}]},{"given":"Peter C.","family":"Cornillon","sequence":"additional","affiliation":[{"name":"Graduate School of Oceanography, University of Rhode Island, Narragansett, RI 02882, USA"}]},{"given":"David M.","family":"Reiman","sequence":"additional","affiliation":[{"name":"Department of Physics, University of California, Santa Cruz, CA 95064, USA"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,17]]},"reference":[{"key":"ref_1","unstructured":"Prochaska, J.X., and Reiman, D. (2021, February 16). Available online: https:\/\/github.com\/AI-for-Ocean-Science\/ulmo."},{"key":"ref_2","unstructured":"GHRSST Project Office (2021, February 16). Available online: https:\/\/www.ghrsst.org\/ghrsst-data-services\/products\/."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Abul Hayat, M., Stein, G., Harrington, P., Luki\u0107, Z., and Mustafa, M. (2020). Self-Supervised Representation Learning for Astronomical Images. arXiv.","DOI":"10.3847\/2041-8213\/abf2c7"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Saux Picart, S., Tandeo, P., Autret, E., and Gausset, B. (2018). Exploring Machine Learning to Correct Satellite-Derived Sea Surface Temperatures. Remote Sens., 10.","DOI":"10.3390\/rs10020224"},{"key":"ref_5","first-page":"1","article-title":"Improved machine-learning based open-water\/sea-ice\/cloud discrimination over wintertime Antarctic sea ice using MODIS thermal-infrared imagery","volume":"2020","author":"Paul","year":"2020","journal-title":"Cryosphere Discuss."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Moschos, E., Schwander, O., Stegner, A., and Gallinari, P. (2020, January 4\u20138). DEEP-SST-EDDIES: A Deep Learning framework to detect oceanic eddies in Sea Surface Temperature images. Proceedings of the ICASSP 2020\u201445th International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053909"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1038\/s41598-019-57162-8","article-title":"A machine learning based prediction system for the Indian Ocean Dipole","volume":"10","author":"Ratnam","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Pan, X., Jiang, T., Sui, B., Liu, C., and Sun, W. (2020). Monthly and Quarterly Sea Surface Temperature Prediction Based on Gated Recurrent Unit Neural Network. J. Mar. Sci. Eng., 8.","DOI":"10.3390\/jmse8040249"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6387173","DOI":"10.1155\/2020\/6387173","article-title":"A Novel Method for Sea Surface Temperature Prediction Based on Deep Learning","volume":"2020","author":"Yu","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.isprsjprs.2019.04.015","article-title":"Deep learning in remote sensing applications: A meta-analysis and review","volume":"152","author":"Ma","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_11","unstructured":"Nalisnick, E., Matsukawa, A., Teh, Y.W., Gorur, D., and Lakshminarayanan, B. (2018). Do deep generative models know what they don\u2019t know?. arXiv."},{"key":"ref_12","unstructured":"Minnett, P.J., Kilpatrick, K., Szczodrak, G., Izaguirre, M., Luo, B., Jia, C., Proctor, C., Bailey, S.W., Armstrong, E., and Vazquez-Cuervo, J. (2020, January 1\u20134). MODIS Sea-Surface Temperatures: Characteristics of the R2019.0 Reprocessing of the Terra and Aqua Missions. Proceedings of the 21st International GHRSST Science Team On-Line Meeting, Boulder, CO, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1175\/JTECH-D-18-0103.1","article-title":"Alternating Decision Trees for Cloud Masking in MODIS and VIIRS NASA Sea Surface Temperature Products","volume":"36","author":"Kilpatrick","year":"2019","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A.A. (2016, January 2\u20134). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the ICLR 2016 Workshop, San Juan, Puerto Rico.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_15","unstructured":"Bertalmio, M., Bertozzi, A.L., and Sapiro, G. (2001, January 8\u201314). Navier-stokes, fluid dynamics, and image and video inpainting. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2001, Kauai, HI, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1175\/JPO-D-19-0172.1","article-title":"Reconstructing Upper-Ocean Vertical Velocity Field from Sea Surface Height in the Presence of Unbalanced Motion","volume":"50","author":"Qiu","year":"2019","journal-title":"J. Phys. Oceanogr."},{"key":"ref_17","unstructured":"Durkan, C., Bekasov, A., Murray, I., and Papamakarios, G. (2019). Neural spline flows. arXiv."},{"key":"ref_18","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.pocean.2011.01.002","article-title":"Global observations of nonlinear mesoscale eddies","volume":"91","author":"Chelton","year":"2011","journal-title":"Prog. Oceanogr."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Piola, A.R., Palma, E.D., Bianchi, A.A., Castro, B.M., Dottori, M., Guerrero, R.A., Marrari, M., Matano, R.P., M\u00f6ller, O.O., and Saraceno, M. (2018). Physical Oceanography of the SW Atlantic Shelf: A Review. Plankton Ecology of the Southwestern Atlantic, Springer International Publishing.","DOI":"10.1007\/978-3-319-77869-3_2"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.pocean.2018.07.003","article-title":"The Patagonian shelf circulation: Drivers and variability","volume":"167","author":"Combes","year":"2018","journal-title":"Prog. Oceanogr."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/4\/744\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:25:21Z","timestamp":1760160321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/4\/744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,17]]},"references-count":21,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["rs13040744"],"URL":"https:\/\/doi.org\/10.3390\/rs13040744","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,17]]}}}