{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T23:23:14Z","timestamp":1780442594342,"version":"3.54.1"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Mesoscale eddies, which are fast-moving rotating water bodies in the ocean with horizontal scales ranging from 10 km to 100 km and above, are considered to be the weather of the oceans. They are of interest to marine biologists, oceanographers, and geodesists for their impact on water mass, heat, and nutrient transport. Typically, gridded sea level anomaly maps processed from multiple radar altimetry missions are used to detect eddies. However, multi-mission sea level anomaly maps obtained by the operational processors have a lower effective spatiotemporal resolution than their grid spacing and temporal resolution, leading to inaccurate eddy detection. In this study, we investigate the use of higher-resolution along-track sea level anomaly data to infer daily two-dimensional segmentation maps of cyclonic, anticyclonic, or non-eddy areas with greater accuracy than using processed sea level anomaly grid map products. To tackle this challenge, we propose a deep neural network that uses spatiotemporal contextual information within the modality of along-track data. This network is capable of producing a two-dimensional segmentation map from data with varying sparsity. We have developed an architecture called Teddy, which uses a Transformer module to encode and process spatiotemporal information, and a sparsity invariant CNN to infer a two-dimensional segmentation map of classified eddies from the ground tracks of varying sparsity on the considered region. Our results show that Teddy creates two-dimensional maps of classified eddies from along-track data with higher accuracy and timeliness when compared to commonly used methods that work with less accurate preprocessed sea level anomaly grid maps. We train and test our method with a carefully curated and independent dataset, which can be made available upon request.<\/jats:p>","DOI":"10.3389\/frai.2024.1298283","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T05:50:51Z","timestamp":1708581051000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Estimating daily semantic segmentation maps of classified ocean eddies using sea level anomaly data from along-track altimetry"],"prefix":"10.3389","volume":"7","author":[{"given":"Eike","family":"Bolmer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adili","family":"Abulaitijiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Kusche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ribana","family":"Roscher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3390\/rs15071860","article-title":"Transformers in remote sensing: a survey","volume":"15","author":"Aleissaee","year":"2023","journal-title":"Remote Sensing"},{"key":"B2","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1109\/IGARSS46834.2022.9884373","article-title":"\u201cOcclusion sensitivity analysis of neural network architectures for eddy detection,\u201d","volume-title":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","author":"Bolmer","year":"2022"},{"key":"B3","doi-asserted-by":"publisher","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":"B4","doi-asserted-by":"publisher","DOI":"10.1029\/2007GL030812","article-title":"Global observations of large oceanic eddies","author":"Chelton","year":"2007","journal-title":"Geophys. Res. Lett"},{"key":"B5","unstructured":"10.48670\/moi-00146.Global Ocean Along Track L 3 Sea Surface Heights Reprocessed 1993 Ongoing Tailored for Data Assimilation.2020"},{"key":"B6","unstructured":"10.48670\/moi-00169.ESA SST CCI and C3S Reprocessed Sea Surface a Temperature Analyses2021"},{"key":"B7","unstructured":"10.48670\/moi-00149.Global Ocean Gridded L 4 Sea Surface Heights and Derived Variables NRT2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1038\/s41561-018-0162-0","article-title":"Gulf stream rings as a source of iron to the north atlantic subtropical gyre","volume":"11","author":"Conway","year":"2018","journal-title":"Nat. Geosci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/s41597-022-01550-9","article-title":"The near-global ocean mesoscale eddy atmospheric-oceanic-biological interaction observational dataset","volume":"9","author":"Dong","year":"2022","journal-title":"Scient. Data"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1109\/LGRS.2011.2155029","article-title":"An automated approach to detect oceanic eddies from satellite remotely sensed sea surface temperature data","volume":"8","author":"Dong","year":"2011","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B11","article-title":"\u201cAn image is worth 16x16 words: transformers for image recognition at scale,\u201d","author":"Dosovitskiy","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B12","first-page":"6887","volume-title":"Ocean Eddy Identification and Tracking Using Neural Networks","author":"Franz","year":"2018"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"B14","doi-asserted-by":"crossref","first-page":"4452","DOI":"10.1109\/CVPR.2016.482","article-title":"\u201cLearning sparse high dimensional filters: image filtering, dense CRFs and bilateral neural networks,\u201d","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Jampani","year":"2016"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/IGARSS.2018.8518411","article-title":"\u201cEddyNet: A deep neural network for pixel-wise classification of oceanic eddies,\u201d","volume-title":"IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium","author":"Lguensat","year":"2018"},{"key":"B16","article-title":"\u201cAn intriguing failing of convolutional neural networks and the CoordConv solution,\u201d","volume-title":"32nd Conference on Neural Information Processing Systems (NeurIPS 2018)","author":"Liu","year":"2018"},{"key":"B17","doi-asserted-by":"crossref","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"\u201cSwin transformer: Hierarchical vision transformer using shifted windows,\u201d","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Liu","year":"2021"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1175\/JTECH-D-14-00019.1","article-title":"A new sea surface height-based code for oceanic mesoscale eddy tracking","volume":"31","author":"Mason","year":"2014","journal-title":"J. Atmosph. Oceanic Techn"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3390\/rs14153807","article-title":"Why do inverse eddy surface temperature anomalies emerge? the case of the mediterranean sea","author":"Moschos","year":"","journal-title":"Remote Sens"},{"key":"B20","doi-asserted-by":"crossref","first-page":"4307","DOI":"10.1109\/ICASSP40776.2020.9053909","article-title":"\u201cDeep-sst-eddies: A deep learning framework to detect oceanic eddies in sea surface temperature images,\u201d","volume-title":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Moschos","year":"2020"},{"key":"B21","first-page":"8008","article-title":"\u201cReal-time validation of operational ocean models via eddy-detecting deep neural networks,\u201d","volume-title":"IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium","author":"Moschos","year":""},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17591-w","article-title":"Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking","author":"Mousavi","year":"2020","journal-title":"Nat. Commun"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.5194\/essd-14-1087-2022","article-title":"Meta3.1exp: a new global mesoscale eddy trajectory atlas derived from altimetry","volume":"14","author":"Pegliasco","year":"2022","journal-title":"Earth Syst. Sci. Data"},{"key":"B24","first-page":"234","article-title":"\u201cU-net: Convolutional networks for biomedical image segmentation,\u201d","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015","author":"Ronneberger","year":"2015"},{"key":"B25","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/j.isprsjprs.2020.06.006","article-title":"Self-attention for raw optical satellite time series classification","volume":"169","author":"Ru\u00dfwurm","year":"2020","journal-title":"ISPRS J Photogramm. Remote Sens"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/rs12162625","article-title":"Neural network training for the detection and classification of oceanic mesoscale eddies","author":"Santana","year":"2020","journal-title":"Remote Sens"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1109\/3DV.2017.00012","article-title":"\u201cSparsity invariant CNNs,\u201d","volume-title":"IEEE International Conference on 3D Vision (3DV)","author":"Uhrig","year":"2017"},{"key":"B28","volume-title":"Attention Is All You Need.","author":"Vaswani","year":"2017"},{"key":"B29","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/0167-2789(91)90088-Q","article-title":"The dynamics of enstrophy transfer in two-dimensional hydrodynamics","volume":"48","author":"Weiss","year":"1991","journal-title":"Physica D: Nonlin. Phenom"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fmars.2022.1023624","article-title":"Submesoscale oceanic eddy detection in sar images using context and edge association network","author":"Xia","year":"2022","journal-title":"Front. Mar. Sci"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3390\/rs14246360","article-title":"Snowmelt flood susceptibility assessment in kunlun mountains based on the swin transformer deep learning method","author":"Yang","year":"2022","journal-title":"Remote Sens"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3243902","article-title":"Oceanic eddy identification using pyramid split attention u-net with remote sensing imagery","volume":"20","author":"Zhao","year":"2023","journal-title":"IEEE Geosci. Remote Sens. Lett"},{"key":"B33","doi-asserted-by":"crossref","first-page":"6363","DOI":"10.1109\/CVPR.2017.674","article-title":"\u201cInterponet, a brain inspired neural network for optical flow dense interpolation,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zweig","year":"2017"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1298283\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T05:51:10Z","timestamp":1708581070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1298283\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":33,"alternative-id":["10.3389\/frai.2024.1298283"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1298283","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"article-number":"1298283"}}