{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T02:22:51Z","timestamp":1781749371745,"version":"3.54.5"},"reference-count":47,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T00:00:00Z","timestamp":1621468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>In this study, we used convolutional neural networks (CNNs)\u2014which are well-known deep learning models suitable for image data processing\u2014to estimate the temporal and spatial distribution of chlorophyll-a in a bay. The training data required the construction of a deep learning model acquired from the satellite ocean color and hydrodynamic model. Chlorophyll-a, total suspended sediment (TSS), visibility, and colored dissolved organic matter (CDOM) were extracted from the satellite ocean color data, and water level, currents, temperature, and salinity were generated from the hydrodynamic model. We developed CNN Model I\u2014which estimates the concentration of chlorophyll-a using a 48 \u00d7 27 sized overall image\u2014and CNN Model II\u2014which uses a 7 \u00d7 7 segmented image. Because the CNN Model II conducts estimation using only data around the points of interest, the quantity of training data is more than 300 times larger than that of CNN Model I. Consequently, it was possible to extract and analyze the inherent patterns in the training data, improving the predictive ability of the deep learning model. The average root mean square error (RMSE), calculated by applying CNN Model II, was 0.191, and when the prediction was good, the coefficient of determination (R2) exceeded 0.91. Finally, we performed a sensitivity analysis, which revealed that CDOM is the most influential variable in estimating the spatiotemporal distribution of chlorophyll-a.<\/jats:p>","DOI":"10.3390\/rs13102003","type":"journal-article","created":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T11:45:57Z","timestamp":1621511157000},"page":"2003","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["A Deep Learning Model Using Satellite Ocean Color and Hydrodynamic Model to Estimate Chlorophyll-a Concentration"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-2086","authenticated-orcid":false,"given":"Daeyong","family":"Jin","sequence":"first","affiliation":[{"name":"Environment Data Strategy Center &amp; Environmental Assessment Group, Korea Environment Institute, Sejong 30147, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eojin","family":"Lee","sequence":"additional","affiliation":[{"name":"Environment Data Strategy Center &amp; Environmental Assessment Group, Korea Environment Institute, Sejong 30147, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyonghwan","family":"Kwon","sequence":"additional","affiliation":[{"name":"Ocean Environment Group, Oceanic, Seoul 07207, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6575-8689","authenticated-orcid":false,"given":"Taeyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Environment Data Strategy Center &amp; Environmental Assessment Group, Korea Environment Institute, Sejong 30147, Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1029\/WR023i008p01393","article-title":"Water quality modeling: A review of the analysis of uncertainty","volume":"23","author":"Beck","year":"1987","journal-title":"Water Resour. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1016\/j.ecolmodel.2004.01.016","article-title":"Development of water quality model in the Satilla River Estuary, Georgia","volume":"178","author":"Zheng","year":"2004","journal-title":"Ecol. Model."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.envsoft.2018.03.001","article-title":"Bayesian framework of parameter sensitivity, uncertainty, and identifiability analysis in complex water quality models","volume":"104","author":"Jia","year":"2018","journal-title":"Envrion. Model. Softw."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yan, J., Xu, Z., Yu, Y., Xu, H., and Gao, K. (2019). Application of a hybrid optimized BP network model to estimate water quality parameters of Beihai Lake in Beijing. Appl. Sci., 9.","DOI":"10.3390\/app9091863"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Vargas, M.R., de Lima, B.S.L.P., and Evsukoff, A.G. (2017, January 26\u201328). Deep learning for stock market prediction from financial news articles. Proceedings of the 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), Annecy, France.","DOI":"10.1109\/CIVEMSA.2017.7995302"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dey, N., Ashour, A., and Borra, S. (2018). Deep learning for medical image processing: Overview, challenges and the future. Classification in BioApps, Springer.","DOI":"10.1007\/978-3-319-65981-7"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e2020GL089436","DOI":"10.1029\/2020GL089436","article-title":"Application of deep learning to estimate atmospheric gravity wave parameters in reanalysis data sets","volume":"47","author":"Matsuoka","year":"2020","journal-title":"Geophys. Res. Lett."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"27893","DOI":"10.1364\/OE.398926","article-title":"Mapping the design space of photonic topological states via deep learning","volume":"28","author":"Singh","year":"2020","journal-title":"Opt. Express"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"104502","DOI":"10.1016\/j.envsoft.2019.104502","article-title":"A spatiotemporal deep learning model for sea surface temperature field prediction using time-series satellite data","volume":"120","author":"Xiao","year":"2019","journal-title":"Envrion. Model. Softw."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Guo, Y., Cao, X., Liu, B., and Peng, K. (2020). El Ni\u00f1o index prediction using deep learning with ensemble empirical mode decomposition. Symmetry, 12.","DOI":"10.3390\/sym12060893"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shin, Y., Kim, T., Hong, S., Lee, S., Lee, E., Hong, S., Lee, C., Kim, T., Park, M., and Park, J. (2020). Prediction of chlorophyll-a concentrations in the Nakdong River using machine learning methods. Water, 12.","DOI":"10.3390\/w12061822"},{"key":"ref_12","first-page":"34","article-title":"Red tide algae image classification using deep learning based open source","volume":"7","author":"Park","year":"2018","journal-title":"Smart MediaJ."},{"key":"ref_13","unstructured":"Lumini, A., Nanni, L., and Maguolo, G. (2019). Deep learning for plankton and coral classification. Appl. Comput. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Raphael, A., Dubinsky, Z., Iluz, D., Benichou, J.I.C., and Netanyahu, N.S. (2020). Deep neural network recognition of shallow water corals in the Gulf of Eilat(Aqaba). Sci. Rep.","DOI":"10.3390\/BDEE2021-09415"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"108261","DOI":"10.1016\/j.oceaneng.2020.108261","article-title":"Real-time data-driven missing data imputation for short-time sensor data of marine systems: A comparative study","volume":"218","author":"Lazakis","year":"2020","journal-title":"Ocean Eng."},{"key":"ref_16","unstructured":"ICCG (2021, April 16). Current Ocean-Colour Sensors. Available online: https:\/\/ioccg.org\/resources\/missions-instruments\/current-ocean-colour-sensors\/."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.pocean.2014.12.013","article-title":"Three decades of ocean-color remote-sensing Trichodesmium spp. In the World\u2019s oceans: A review","volume":"131","author":"McKinna","year":"2015","journal-title":"Prog. Oceanogr."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1080\/01431161.2015.1088673","article-title":"Comparison of MERIS, MODIS, SeaWiFS-derived particulate organic carbon, and in situ measurements in the South China Sea","volume":"37","author":"Hu","year":"2016","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.pocean.2018.01.001","article-title":"An overview of approaches and challenges for retrieving marine inherent optical properties from ocean color remote sensing","volume":"160","author":"Werdell","year":"2018","journal-title":"Prog. Oceanogr."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"30140","DOI":"10.1364\/OE.27.030140","article-title":"Comparing level-2 and level-3 satellite ocean color retrieval validation methodologies","volume":"27","author":"Scott","year":"2019","journal-title":"Opt. Express"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"10285","DOI":"10.1109\/TGRS.2019.2933251","article-title":"Novel spectra-derived features for empirical retrieval of water quality parameters: Demonstrations for OLI, MSI, and OLCI sensors","volume":"57","author":"Bovolo","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Crout, R.L., Ladner, S., Lawson, A., Martinolich, P., and Bowers, J. (2018, January 22\u201325). Calibration and validation of multiple ocean color sensors. Proceedings of the OCEANS 2018 MTS\/IEEE Conference, Charleston, SC, USA.","DOI":"10.1109\/OCEANS.2018.8604863"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3835","DOI":"10.1364\/OE.21.003835","article-title":"Ocean color products from the Korean Geostationary Ocean Color Imager (GOCI)","volume":"21","author":"Wang","year":"2013","journal-title":"Opt. Express"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"140","DOI":"10.3389\/fmars.2017.00140","article-title":"The OLCI neural network swarm(ONNS): A Bio-Geo-Optical algorithm for open ocean and costal waters","volume":"4","author":"Hieronymi","year":"2017","journal-title":"Front. Mar. Sci."},{"key":"ref_25","unstructured":"Brockmann, C., Doerffer, R., Peters, M., Stelzer, K., Embacher, S., and Ruescas, A. (2016, January 9\u201313). Evolution of the C2RCC neural network for SENTINEL 1 and 3 for the retrieval of ocean colour products in normal and extreme optically complex waters. Proceedings of the Living Planet Symposium 2016, Prague, Czech Republic."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Xie, F., Tao, Z., Zhou, X., Lv, T., Wang, J., and Li, R. (2021). A prediction model of water in situ data change under the influence of environment variables in remote sensing validation. Remote Sens., 13.","DOI":"10.3390\/rs13010070"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"146823","DOI":"10.1016\/j.scitotenv.2021.146823","article-title":"Metabarcoding analysis of harmful algal bloom species in the Changjiang Estuary, China","volume":"782","author":"Cui","year":"2021","journal-title":"Sci. Total Environ."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1007\/BF02804904","article-title":"Effects of hypoxia, and the balance between hypoxia and enrichment, on coastal fishes and fisheries","volume":"26","author":"Breitburg","year":"2002","journal-title":"Estuaries"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"160947","DOI":"10.1109\/ACCESS.2019.2950833","article-title":"Temporal-Spatial Distribution of Chlorophyll-a and Impacts of Environmental Factors in the Bohai Sea and Yellow Sea","volume":"7","author":"Zhao","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","first-page":"5251902","article-title":"Guidance on setup, calibration, and validation of hydrodynamic, wave, and sediment models for shelf seas and estuaries","volume":"2017","author":"Williams","year":"2017","journal-title":"Adv. Civ. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"392","DOI":"10.7837\/kosomes.2020.26.4.392","article-title":"Pollution status of surface sediment in Jinju bay, a spraying shellfish farming area, Korea","volume":"26","author":"Lee","year":"2020","journal-title":"J. Korean Soc. Mar. Env. Saf."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"485","DOI":"10.3389\/fmars.2019.00485","article-title":"Satellite ocean colour: Current status and future perspective","volume":"6","author":"Groom","year":"2019","journal-title":"Front. Mar. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"111366","DOI":"10.1016\/j.rse.2019.111366","article-title":"Half a century of satellite remote sensing of sea-surface temperature","volume":"233","author":"Minnett","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_34","first-page":"129","article-title":"Analysis of temporal and spatial red tide change in the south sea of Korea using the GOCI Images of COMS","volume":"22","author":"Kim","year":"2014","journal-title":"J. Korean Assoc. Geogr. Inf. Stud."},{"key":"ref_35","unstructured":"KIOST (2020, November 30). Korea Ocean Satellite Center. Available online: https:\/\/www.kiost.ac.kr\/eng.do."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"C09004","DOI":"10.1029\/2012JC008046","article-title":"GOCI, the world\u2019s first geostationary ocean color observation satellite, for the monitoring of temporal variability in coastal water turbidity","volume":"117","author":"Choi","year":"2012","journal-title":"J. Geophys. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"137","DOI":"10.11108\/kagis.2012.15.3.137","article-title":"Monitoring of floating green algae using ocean color satellite remote sensing","volume":"15","author":"Lee","year":"2012","journal-title":"J. Korean Assoc. Geogr. Inf. Stud."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3859","DOI":"10.1080\/01431161.2015.1070323","article-title":"Evaluation of the geostationary ocean color imager (GOCI) to monitor the dynamic characteristics of suspension sediment in Taihu Lake","volume":"36","author":"Huang","year":"2015","journal-title":"Int. J. Remote Sens."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3984","DOI":"10.1080\/01431161.2018.1557793","article-title":"Vicarious calibration of GOCI for the SeaDAS ocean color retrieval","volume":"40","author":"Concha","year":"2019","journal-title":"Int. J. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/s12601-012-0024-4","article-title":"Overview of geostationary ocean color imager(GOCI) and GOCI Data Processing System(GDPS)","volume":"47","author":"Ryu","year":"2012","journal-title":"Ocean Sci. J."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1016\/j.coastaleng.2004.07.014","article-title":"Development and validation of a three-dimensional morphological model","volume":"51","author":"Lesser","year":"2004","journal-title":"Coast. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1016\/j.jmarsys.2008.11.014","article-title":"A 2D\/3D hydrodynamic and sediment transport model for the Yangtze estuary, China","volume":"77","author":"Hu","year":"2009","journal-title":"J. Mar. Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1080\/20442041.2019.1580079","article-title":"Comparison of results from two 3D hydrodynamic models with field data: Internal seiches and horizontal currents","volume":"9","author":"Dissanayake","year":"2019","journal-title":"Inland Waters"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1320","DOI":"10.1016\/j.renene.2019.02.094","article-title":"Application of the actuator disc theory of Delft3D-FLOW to model far-field hydrodynamic impacts of tidal turbines","volume":"139","author":"Ramos","year":"2019","journal-title":"Renew. Energy"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xia, M., and Jiang, L. (2016). Application of an unstructured grid-based water quality model to Chaeapeake Bay and its adjacent coastal ocean. J. Mar. Sci. Eng., 4.","DOI":"10.3390\/jmse4030052"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.wse.2014.10.001","article-title":"An integrated measurement and modelling methodoloby for estuarine water quality management","volume":"8","author":"Hartnett","year":"2015","journal-title":"Water Sci. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.rse.2016.07.031","article-title":"Evaluation of chlorophyll retrievals form Geostationary Ocean Imager(GOCI) for the North-East Asian region","volume":"184","author":"Kim","year":"2016","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/10\/2003\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:04:36Z","timestamp":1760162676000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/10\/2003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,20]]},"references-count":47,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,5]]}},"alternative-id":["rs13102003"],"URL":"https:\/\/doi.org\/10.3390\/rs13102003","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,20]]}}}