{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:13:26Z","timestamp":1775106806998,"version":"3.50.1"},"reference-count":51,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2018,3,8]],"date-time":"2018-03-08T00:00:00Z","timestamp":1520467200000},"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>The size of phytoplankton not only influences its physiology, metabolic rates and marine food web, but also serves as an indicator of phytoplankton functional roles in ecological and biogeochemical processes. Therefore, some algorithms have been developed to infer the synoptic distribution of phytoplankton cell size, denoted as phytoplankton size classes (PSCs), in surface ocean waters, by the means of remotely sensed variables. This study, using the NASA bio-Optical Marine Algorithm Data set (NOMAD) high performance liquid chromatography (HPLC) database, and satellite match-ups, aimed to compare the effectiveness of modeling techniques, including partial least square (PLS), artificial neural networks (ANN), support vector machine (SVM) and random forests (RF), and feature selection techniques, including genetic algorithm (GA), successive projection algorithm (SPA) and recursive feature elimination based on support vector machine (SVM-RFE), for inferring PSCs from remote sensing data. Results showed that: (1) SVM-RFE worked better in selecting sensitive features; (2) RF performed better than PLS, ANN and SVM in calibrating PSCs retrieval models; (3) machine learning techniques produced better performance than the chlorophyll-a based three-component method; (4) sea surface temperature, wind stress, and spectral curvature derived from the remote sensing reflectance at 490, 510, and 555 nm were among the most sensitive features to PSCs; and (5) the combination of SVM-RFE feature selection techniques and random forests regression was recommended for inferring PSCs. This study demonstrated the effectiveness of machine learning techniques in selecting sensitive features and calibrating models for PSCs estimations with remote sensing.<\/jats:p>","DOI":"10.3390\/rs10030191","type":"journal-article","created":{"date-parts":[[2018,3,8]],"date-time":"2018-03-08T12:07:33Z","timestamp":1520510853000},"page":"191","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Comparison of Machine Learning Techniques in Inferring Phytoplankton Size Classes"],"prefix":"10.3390","volume":"10","author":[{"given":"Shuibo","family":"Hu","sequence":"first","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"},{"name":"College of Life Sciences and Oceanography, Shenzhen University, Shenzhen 518060, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9018-985X","authenticated-orcid":false,"given":"Huizeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"},{"name":"Department of Geography, Hong Kong Baptist University, Kowloon Tong, Kowloon, Hong Kong, China"}]},{"given":"Wenjing","family":"Zhao","sequence":"additional","affiliation":[{"name":"South China Institute of Environmental Sciences, the Ministry of Environmental Protection of RPC, Guangzhou 510535, China"}]},{"given":"Tiezhu","family":"Shi","sequence":"additional","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"}]},{"given":"Zhongwen","family":"Hu","sequence":"additional","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"}]},{"given":"Qingquan","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2275-6530","authenticated-orcid":false,"given":"Guofeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the National Administration of Surveying, Mapping and GeoInformation &amp; Shenzhen Key Laboratory of Spatial Smart Sensing and Services &amp; Research Institute for Smart Cities &amp; Guangdong Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen 518060, China"},{"name":"College of Life Sciences and Oceanography, Shenzhen University, Shenzhen 518060, China"}]}],"member":"1968","published-online":{"date-parts":[[2018,3,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1126\/science.281.5374.237","article-title":"Primary production of the biosphere: Integrating terrestrial and oceanic components","volume":"281","author":"Field","year":"1998","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/0079-6611(89)90010-4","article-title":"The biological pump: Profiles of plankton production and consumption in the upper ocean","volume":"22","author":"Longhurst","year":"1989","journal-title":"Prog. Oceanogr."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/0967-0637(95)00017-Z","article-title":"Evidence of the potential influence of planktonic community structure on the interannual variability of particulate organic carbon flux","volume":"42","author":"Boyd","year":"1995","journal-title":"Deep Sea Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.4319\/lo.1978.23.6.1256","article-title":"Pelagic ecosystem structure: Heterotrophic compartments of the plankton and their relationship to plankton size fractions","volume":"23","author":"Sieburth","year":"1978","journal-title":"Limnol. Oceanogr."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3366","DOI":"10.1016\/j.rse.2008.01.021","article-title":"Remote sensing of phytoplankton functional types","volume":"112","author":"Nair","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3389\/fmars.2017.00055","article-title":"Obtaining phytoplankton diversity from ocean color: A scientific roadmap for future development","volume":"4","author":"Bracher","year":"2017","journal-title":"Front. Mar. Sci."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1472","DOI":"10.1016\/j.ecolmodel.2010.02.014","article-title":"A three-component model of phytoplankton size class for the Atlantic Ocean","volume":"221","author":"Brewin","year":"2010","journal-title":"Ecol. Model."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.rse.2010.09.004","article-title":"An intercomparison of bio-optical techniques for detecting dominant phytoplankton size class from satellite remote sensing","volume":"115","author":"Brewin","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"614","DOI":"10.4319\/lo.2008.53.2.0614","article-title":"Relating phytoplankton photophysiological properties to community structure on large scales","volume":"53","author":"Uitz","year":"2008","journal-title":"Limnol. Oceanogr."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Kostadinov, T., Siegel, D., and Maritorena, S. (2009). Retrieval of the particle size distribution from satellite ocean color observations. J. Geophys. Res., 114.","DOI":"10.1029\/2009JC005303"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3153","DOI":"10.1016\/j.rse.2008.03.011","article-title":"An absorption model to determine phytoplankton size classes from satellite ocean colour","volume":"112","author":"Hirata","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"10467","DOI":"10.1364\/OE.22.010467","article-title":"Novel method for quantifying the cell size of marine phytoplankton based on optical measurements","volume":"22","author":"Lin","year":"2014","journal-title":"Opt. Express"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"605","DOI":"10.4319\/lo.2008.53.2.0605","article-title":"Identifying four phytoplankton functional types from space: An ecological approach","volume":"53","author":"Raitsos","year":"2008","journal-title":"Limnol. Oceanogr."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1364\/AO.52.002257","article-title":"Multivariate approach for the retrieval of phytoplankton size structure from measured light absorption spectra in the mediterranean sea (boussole site)","volume":"52","author":"Organelli","year":"2013","journal-title":"Appl. Opt."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2578","DOI":"10.1016\/j.rse.2011.05.014","article-title":"Cluster analysis of hyperspectral optical data for discriminating phytoplankton pigment assemblages in the open ocean","volume":"115","author":"Torrecilla","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1002\/jgrc.20137","article-title":"Estimation of phytoplankton size fractions based on spectral features of remote sensing ocean color data","volume":"118","author":"Li","year":"2013","journal-title":"J. Geophys. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.rse.2005.07.001","article-title":"An improved bio-optical data set for ocean color algorithm development and satellite data product variation","volume":"98","author":"Werdell","year":"2005","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"19939","DOI":"10.1029\/1999JC000308","article-title":"Phytoplankton pigment distribution in relation to upper thermocline circulation in the eastern mediterranean sea during winter","volume":"106","author":"Vidussi","year":"2001","journal-title":"J. Geophys. Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Uitz, J., Claustre, H., Morel, A., and Hooker, S.B. (2006). Vertical distribution of phytoplankton communities in open ocean: An assessment based on surface chlorophyll. J. Geophys. Res., 111.","DOI":"10.1029\/2005JC003207"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Mouw, C., and Yoder, J. (2010). Optical determination of phytoplankton size composition from global seawifs imagery. J. Geophys. Res., 115.","DOI":"10.1029\/2010JC006337"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hu, C., Lee, Z., and Franz, B. (2012). Chlorophyll algorithms for oligotrophic oceans: A novel approach based on three-band reflectance difference. J. Geophys. Res., 117.","DOI":"10.1029\/2011JC007395"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2019","DOI":"10.1364\/AO.52.002019","article-title":"Generalized ocean color inversion model for retrieving marine inherent optical properties","volume":"52","author":"Werdell","year":"2013","journal-title":"Appl. Opt."},{"key":"ref_23","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_24","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","article-title":"Wrappers for feature subset selection","volume":"97","author":"Kohavi","year":"1997","journal-title":"Artif. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/S0169-7439(98)00051-3","article-title":"Genetic algorithms applied to feature selection in PLS regression: How and when to use them","volume":"41","author":"Leardi","year":"1998","journal-title":"Chemom. Intell. Lab."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1366\/13-07294","article-title":"Soil organic carbon content estimation with laboratory-based visible-near-infrared reflectance spectroscopy: Feature selection","volume":"68","author":"Shi","year":"2014","journal-title":"Appl. Spectrosc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/S0169-7439(01)00119-8","article-title":"The successive projections algorithm for variable selection in spectroscopic multicomponent analysis","volume":"57","author":"Saldanha","year":"2001","journal-title":"Chemom. Intell. Lab."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.ecolind.2016.02.033","article-title":"Successive projections algorithm-based three-band vegetation index for foliar phosphorus estimation","volume":"67","author":"Wang","year":"2016","journal-title":"Ecol. Indic."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3374","DOI":"10.1109\/TGRS.2006.880628","article-title":"Toward an optimal SVM classification system for hyperspectral remote sensing images","volume":"44","author":"Bazi","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wold, S., Martens, H., and Wold, H. (1983). The Multivariate Calibration Problem in Chemistry Solved by the PLS Method. Matrix Pencils, Springer.","DOI":"10.1007\/BFb0062108"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0169-7439(93)85002-X","article-title":"Simpls: An alternative approach to partial least squares regression","volume":"18","year":"1993","journal-title":"Chemom. Intell. Lab."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.ecolind.2014.12.028","article-title":"A comparative assessment of support vector regression, artificial neural networks, and random forests for predicting and mapping soil organic carbon stocks across an afromontane landscape","volume":"52","author":"Were","year":"2015","journal-title":"Ecol. Indic."},{"key":"ref_35","unstructured":"Drucker, H., Burges, C.J., Kaufman, L., Smola, A.J., and Vapnik, V. (1997). Support vector regression machines. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Pelckmans, K., Suykens, J.A., Van Gestel, T., De Brabanter, J., Lukas, L., Hamers, B., De Moor, B., and Vandewalle, J. (2002). Ls-Svmlab: A MATLAB\/C Toolbox for Least Squares Support Vector Machines, KULeuven-ESAT.","DOI":"10.1142\/5089"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_38","unstructured":"Breiman, L., Cutler, A., Liaw, A., and Wiener, M. (2018, March 05). Package\u2019randomforest. Available online: http:\/\/stat.www.berkeley.edu\/~breiman\/RandomForests."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Akaike, H. (1998). Information theory and an extension of the maximum likelihood principle. Selected Papers of Hirotugu Akaike, Springer.","DOI":"10.1007\/978-1-4612-1694-0_15"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.isprsjprs.2013.08.009","article-title":"An approach for developing landsat-5 TM-based retrieval models of suspended particulate matter concentration with the assistance of modis","volume":"85","author":"Wu","year":"2013","journal-title":"ISPRS J. Photogramm."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.isprsjprs.2016.01.011","article-title":"Random forest in remote sensing: A review of applications and future directions","volume":"114","author":"Belgiu","year":"2016","journal-title":"ISPRS J. Photogramm."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liu, H., Shi, T., Chen, Y., Wang, J., Fei, T., and Wu, G. (2017). Improving spectral estimation of soil organic carbon content through semi-supervised regression. Remote Sens., 9.","DOI":"10.3390\/rs9010029"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.1016\/j.rse.2008.02.011","article-title":"Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery","volume":"112","author":"Chan","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.landurbplan.2012.06.009","article-title":"Variable selection for hedonic model using machine learning approaches: A case study in Onondaga County, NY","volume":"107","author":"Yoo","year":"2012","journal-title":"Landsc. Urban Plan."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Xu, S., Lu, B., Baldea, M., Edgar, T.F., and Nixon, M. (2017). An improved variable selection method for support vector regression in nir spectral modeling. J. Process Control.","DOI":"10.1016\/j.jprocont.2017.06.001"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1016\/j.dsr.2005.06.015","article-title":"Remote sensing of phytoplankton groups in case 1 waters from global seawifs imagery","volume":"52","author":"Alvain","year":"2005","journal-title":"Deep Sea Res."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"4377","DOI":"10.1364\/AO.39.004377","article-title":"Band-ratio or spectral-curvature algorithms for satellite remote sensing?","volume":"39","author":"Lee","year":"2000","journal-title":"Appl. Opt."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.rse.2013.02.013","article-title":"Deriving phytoplankton size classes from satellite data: Validation along a trophic gradient in the eastern atlantic ocean","volume":"134","author":"Brotas","year":"2013","journal-title":"Remote Sens. Environ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"759","DOI":"10.5194\/os-11-759-2015","article-title":"Spatio-temporal variability of micro-, nano-and pico-phytoplankton in the Mediterranean Sea from satellite ocean colour data of SeaWiFS","volume":"11","author":"Sammartino","year":"2015","journal-title":"Ocean Sci."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3389\/fmars.2017.00126","article-title":"Regional empirical algorithms for an improved identification of Phytoplankton Functional Types and Size Classes in the Mediterranean Sea using satellite data","volume":"4","author":"Sammartino","year":"2017","journal-title":"Front. Mar. Sci."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.dsr.2013.11.007","article-title":"Comparison of two methods to derive the size-structure of natural populations of phytoplankton","volume":"85","author":"Brewin","year":"2014","journal-title":"Deep Sea Res."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/3\/191\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:57:59Z","timestamp":1760194679000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/3\/191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,8]]},"references-count":51,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,3]]}},"alternative-id":["rs10030191"],"URL":"https:\/\/doi.org\/10.3390\/rs10030191","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,8]]}}}