{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:12:52Z","timestamp":1760145172633,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T00:00:00Z","timestamp":1719964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NASA","award":["80NSSC18K0837","80NSSC20K1728"],"award-info":[{"award-number":["80NSSC18K0837","80NSSC20K1728"]}]},{"name":"Simons Foundation Pivot Fellowship","award":["80NSSC18K0837","80NSSC20K1728"],"award-info":[{"award-number":["80NSSC18K0837","80NSSC20K1728"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Clouds and other data artefacts frequently limit the retrieval of key variables from remotely sensed Earth observations. We train a natural language processing (NLP)-inspired algorithm with high-fidelity ocean simulations to accurately reconstruct masked or missing data in sea surface temperature (SST) fields\u2014one of 54 essential climate variables identified by the Global Climate Observing System. We demonstrate that the resulting model, referred to as Enki, repeatedly outperforms previously adopted inpainting techniques by up to an order of magnitude in reconstruction error, while displaying exceptional performance even in circumstances where the majority of pixels are masked. Furthermore, experiments on real infrared sensor data with masked percentages of at least 40% show reconstruction errors of less than the known uncertainty of this sensor (root mean square error (RMSE) \u22720.1 K). We attribute Enki\u2019s success to the attentive nature of NLP combined with realistic SST model outputs\u2014an approach that could be extended to other remotely sensed variables. This study demonstrates that systems built upon Enki\u2014or other advanced systems like it\u2014may therefore yield the optimal solution to mitigating masked pixels in in climate-critical ocean datasets sampling a rapidly changing Earth.<\/jats:p>","DOI":"10.3390\/rs16132439","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T08:45:34Z","timestamp":1719996334000},"page":"2439","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Mitigating Masked Pixels in a Climate-Critical Ocean Dataset"],"prefix":"10.3390","volume":"16","author":[{"given":"Angelina","family":"Agabin","sequence":"first","affiliation":[{"name":"Applied Math Department, University of California, Santa Cruz, CA 95064, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7738-6875","authenticated-orcid":false,"given":"J. Xavier","family":"Prochaska","sequence":"additional","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7296-3282","authenticated-orcid":false,"given":"Peter C.","family":"Cornillon","sequence":"additional","affiliation":[{"name":"Graduate School of Oceanography, University of Rhode Island, Narragansett, RI 02882, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9355-9038","authenticated-orcid":false,"given":"Christian E.","family":"Buckingham","sequence":"additional","affiliation":[{"name":"National Oceanography Centre, Southampton SO14 3ZH, UK"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,3]]},"reference":[{"key":"ref_1","unstructured":"NASA (1987). Space-Based Remote Sensing of the Earth: A Report to the Congress."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1126\/science.210.4465.60","article-title":"Nimbus-7 Coastal Zone Color Scanner: System Description and Initial Imagery","volume":"210","author":"Hovis","year":"1980","journal-title":"Science"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4673","DOI":"10.1029\/JC083iC09p04673","article-title":"Large-scale Gulf Stream frontal study using Geos 3 radar altimeter data","volume":"83","author":"Huang","year":"1978","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1126\/science.204.4400.1405","article-title":"Seasat Mission Overview","volume":"204","author":"Born","year":"1979","journal-title":"Science"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5.1","DOI":"10.1175\/AMSMONOGRAPHS-D-18-0010.1","article-title":"50 Years of Satellite Remote Sensing of the Ocean","volume":"59","author":"Fu","year":"2019","journal-title":"Meteorol. Monogr."},{"key":"ref_6","unstructured":"Stewart, R.H. (1985). Methods of Satellite Oceanography, University of California Press. Number 1 in Scripps Studies in Earth and Ocean Sciences."},{"key":"ref_7","unstructured":"Robinson, I.S. (2004). Measuring the Oceans from Space: The Principles and Methods of Satellite Oceanography, Springer-Praxis Pub. Springer-Praxis Books in Geophysical Sciences; OCLC: ocm53926711."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Martin, S. (2014). An Introduction to Ocean Remote Sensing, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/CBO9781139094368"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Prochaska, J.X., Cornillon, P.C., and Reiman, D.M. (2021). Deep Learning of Sea Surface Temperature Patterns to Identify Ocean Extremes. Remote Sens., 13.","DOI":"10.3390\/rs13040744"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5473","DOI":"10.1175\/2007JCLI1824.1","article-title":"Daily High-Resolution-Blended Analyses for Sea Surface Temperature","volume":"20","author":"Reynolds","year":"2007","journal-title":"J. Clim."},{"key":"ref_11","unstructured":"NASA\/JPL (2015). GHRSST Level 4 MUR Global Foundation Sea Surface Temperature Analysis (v4.1)."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"\u0106atipovi\u0107, L., Mati\u0107, F., and Kalini\u0107\u2019, H. (2023). Reconstruction Methods in Oceanographic Satellite Data Observation\u2013A Survey. J. Mar. Sci. Eng., 11.","DOI":"10.3390\/jmse11020340"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1175\/1520-0426(2003)020<1839:ECADFF>2.0.CO;2","article-title":"EOF Calculations and Data Filling from Incomplete Oceanographic D atasets","volume":"20","author":"Beckers","year":"2003","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.ocemod.2004.08.001","article-title":"Reconstruction of incomplete oceanographic data sets using empirical orthogonal functions: Application to the Adriatic Sea surface temperature","volume":"9","author":"Barth","year":"2005","journal-title":"Ocean Model."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alvera-Azc\u00e1rate, A., Barth, A., Beckers, J.M., and Weisberg, R.H. (2007). Multivariate reconstruction of missing data in sea surface temperature, chlorophyll, and wind satellite fields. J. Geophys. Res. Ocean., 112.","DOI":"10.1029\/2006JC003660"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ping, B., Su, F., and Meng, Y. (2016). An Improved DINEOF Algorithm for Filling Missing Values in Spatio-Temporal Sea Surface Temperature Data. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0155928"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1609","DOI":"10.5194\/gmd-13-1609-2020","article-title":"DINCAE 1.0: A convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations","volume":"13","author":"Barth","year":"2020","journal-title":"Geosci. Model Dev."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Larson, A., and Akanda, A.S. (2023). Transforming Observations of Ocean Temperature with a Deep Convolutional Residual Regressive Neural Network. arXiv.","DOI":"10.3390\/hydrology10060116"},{"key":"ref_19","first-page":"1","article-title":"MAESSTRO: Masked Autoencoders for Sea Surface Temperature Reconstructi on under Occlusion","volume":"2023","author":"Goh","year":"2023","journal-title":"EGUsphere"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., and Girshick, R.B. (2022, January 18\u201324). Masked Autoencoders Are Scalable Vision Learners. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5753","DOI":"10.1029\/96JC02775","article-title":"A finite-volume, incompressible Navier-Stokes model for studies of the ocean on parallel computers","volume":"102","author":"Marshall","year":"1997","journal-title":"J. Geophys. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5733","DOI":"10.1029\/96JC02776","article-title":"Hydrostatic, quasi-hydrostatic, and nonhydrostatic ocean modeling","volume":"102","author":"Marshall","year":"1997","journal-title":"J. Geophys. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2845","DOI":"10.1175\/MWR2823.1","article-title":"Implementation of an Atmosphere\u2013Ocean General Circulation Model on the Expanded Spherical Cube","volume":"132","author":"Adcroft","year":"2004","journal-title":"Mon. Weather Rev."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1175\/JPO-D-15-0087.1","article-title":"Mesoscale to submesoscale wavenumber spectra in Drake Passage","volume":"46","author":"Rocha","year":"2016","journal-title":"J. Phys. Oceanogr."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1038\/s41467-018-02983-w","article-title":"Ocean submesoscales as a key component of the global heat budget","volume":"9","author":"Su","year":"2018","journal-title":"Nat. Commun."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"8084","DOI":"10.1029\/2018JC014438","article-title":"Partitioning Ocean Motions Into Balanced Motions and Internal Gravity Waves: A Modeling Study in Anticipation of Future Space Missions","volume":"123","author":"Torres","year":"2018","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"7803","DOI":"10.1002\/2017JC013009","article-title":"Spectral decomposition of internal gravity wave sea surface height in global models","volume":"122","author":"Savage","year":"2017","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Arbic, B.K., Alford, M.H., Ansong, J.K., Buijsman, M.C., Ciotti, R.B., and Farrar, J.T. (2018). A Primer on Global Internal Tide and Internal Gravity Wave Continuum Modeling in HYCOM and MITgcm, FSU. Chapter 13.","DOI":"10.17125\/gov2018.ch13"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1175\/JTECH-D-17-0076.1","article-title":"An Observing System Simulation Experiment for the Calibration and Validation of the Surface Water Ocean Topography Sea Surface Height Measurement Using In Situ Platforms","volume":"35","author":"Wang","year":"2018","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"3071","DOI":"10.5194\/gmd-8-3071-2015","article-title":"ECCO version 4: An integrated framework for non-linear inverse modeling and global ocean state estimation","volume":"8","author":"Forget","year":"2015","journal-title":"Geosci. Model Dev."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Gallmeier, K., Prochaska, J.X., Cornillon, P.C., Menemenlis, D., and Kelm, M. (2023). An evaluation of the LLC4320 global ocean simulation based on the submesoscale structure of modeled sea surface temperature fields. arXiv.","DOI":"10.5194\/gmd-2023-39"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"9757","DOI":"10.1029\/2019GL083074","article-title":"Surface Kinetic Energy Distributions in the Global Oceans from a High-Resolution Numerical Model and Surface Drifter Observations","volume":"46","author":"Yu","year":"2019","journal-title":"Geophys. Res. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e2022JC018551","DOI":"10.1029\/2022JC018551","article-title":"Near-Surface Oceanic Kinetic Energy Distributions from Drifter Observations and Numerical Models","volume":"127","author":"Arbic","year":"2022","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_34","first-page":"110140O","article-title":"Status of second VIIRS reanalysis (RAN2)","volume":"Volume 11014","author":"Hou","year":"2019","journal-title":"Proceedings of the Ocean Sensing and Monitoring XI"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Prochaska, J.X., Guo, E., Cornillon, P.C., and Buckingham, C.E. (2023). The Fundamental Patterns of Sea Surface Temperature. arXiv.","DOI":"10.1109\/TGRS.2023.3300272"},{"key":"ref_36","unstructured":"Agabin, A., and Prochaska, J.X. (2023). Reconstructing Sea Surface Temperature Images: A Masked Autoencoder Approach for Cloud Masking and Reconstruction. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wu, F., Cornillon, P., Boussidi, B., and Guan, L. (2017). Determining the Pixel-to-Pixel Uncertainty in Satellite-Derived SST Fields. Remote Sens., 9.","DOI":"10.20944\/preprints201707.0066.v1"},{"key":"ref_38","unstructured":"Tseng, G., Zvonkov, I., Purohit, M., Rolnick, D., and Kerner, H. (2023). Lightweight, Pre-trained Transformers for Remote Sensing Timeseries. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Reed, C.J., Gupta, R., Li, S., Brockman, S., Funk, C., Clipp, B., Keutzer, K., Candido, S., Uyttendaele, M., and Darrell, T. (2023). Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning. arXiv.","DOI":"10.1109\/ICCV51070.2023.00378"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/13\/2439\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:09:34Z","timestamp":1760108974000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/13\/2439"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,3]]},"references-count":39,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["rs16132439"],"URL":"https:\/\/doi.org\/10.3390\/rs16132439","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2024,7,3]]}}}