{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:31:50Z","timestamp":1781735510602,"version":"3.54.5"},"reference-count":54,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2020,6,18]],"date-time":"2020-06-18T00:00:00Z","timestamp":1592438400000},"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 retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models.<\/jats:p>","DOI":"10.3390\/rs12121966","type":"journal-article","created":{"date-parts":[[2020,6,18]],"date-time":"2020-06-18T12:21:46Z","timestamp":1592482906000},"page":"1966","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":67,"title":["WaterNet: A Convolutional Neural Network for Chlorophyll-a Concentration Retrieval"],"prefix":"10.3390","volume":"12","author":[{"given":"Muhammad Aldila","family":"Syariz","sequence":"first","affiliation":[{"name":"Department of Geomatics, National Cheng Kung University, Tainan City 70101, Taiwan"},{"name":"Department of Civil Engineering, Institut Teknologi Sepuluh Nopember, Surabaya 60111, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8126-8794","authenticated-orcid":false,"given":"Chao-Hung","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Geomatics, National Cheng Kung University, Tainan City 70101, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manh Van","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Department of Geomatics, National Cheng Kung University, Tainan City 70101, Taiwan"},{"name":"Institute of Geography, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Hanoi 100000, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2663-9016","authenticated-orcid":false,"given":"Lalu Muhamad","family":"Jaelani","sequence":"additional","affiliation":[{"name":"Department of Geomatics Engineering, Institut Teknologi Sepuluh Nopember, Surabaya 60111, Indonesia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0489-9979","authenticated-orcid":false,"given":"Ariel C.","family":"Blanco","sequence":"additional","affiliation":[{"name":"Department of Geodetic Engineering, University of the Philippines Diliman, Diliman 1104, Philippines"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/018011d0","article-title":"Poisonous Australian lake","volume":"18","author":"Francis","year":"1878","journal-title":"Nature"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1111\/j.1749-7345.1990.tb00529.x","article-title":"A review of the effects of algal blooms on shellfish and aquaculture","volume":"21","author":"Shumwey","year":"1990","journal-title":"J. World Aquac. Soc."},{"key":"ref_3","first-page":"819","article-title":"The economic effects of harmful algal blooms in the United States: Estimates, assessment issues, and information","volume":"25","author":"Hoagland","year":"2012","journal-title":"Assessment"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Feng, X., Cheng, X., and Wang, C. (2011, January 24\u201326). Remote estimation of chlorophyll-a concentrations in Taihu Lake during cyanobacterial algae bloom outbreak. Proceedings of the 2011 19th International Conference on Geoinformatics, Shanghai, China.","DOI":"10.1109\/GeoInformatics.2011.5980962"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4919","DOI":"10.1109\/JSTARS.2017.2739184","article-title":"Landsat 8\/OLI Two bands ratio algorithm for chlorophyll-a concentration mapping in hypertrophic waters: An application to west lake in Hanoi (Vietnam)","volume":"10","author":"Ha","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kown, Y.S., Baek, S.H., Lim, Y.K., Pyo, J.C., Ligaray, M., Park, Y., and Cho, K.H. (2018). Monitoring coastal chlorophyll-a concentrations in coastal areas using machine learning models. Water, 10.","DOI":"10.3390\/w10081020"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Van Nguyen, M., Lin, C.H., Chu, H.J., Jaelani, L.M., and Syariz, M.A. (2020). Spectral feature selection optimization for water quality estimation. Int. J. Environ. Res. Public Health, 17.","DOI":"10.3390\/ijerph17010272"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/j.rse.2010.09.021","article-title":"Neural network estimation of chlorophyll a from MERIS full resolution data for the coastal waters of Galician rias (NW Spain)","volume":"115","author":"Spyrakos","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1109\/TGRS.2011.2163199","article-title":"Estimation of chlorophyll a concentration using NIR\/Red bands of MERIS and classification procedure in inland turbid water","volume":"50","author":"Li","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_10","first-page":"138","article-title":"A soft-classification-based chlorophyll-a estimation method using MERIS data in the highly turbid and eutrophic Taihu Lake","volume":"74","author":"Zhang","year":"2019","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_11","unstructured":"Cristina, S., Fragoso, B., Icely, J., and Grant, J. (2020, May 14). Aquaspace Project Document. Available online: http:\/\/www.aquaspace-h2020.eu\/wp-content\/uploads\/2018\/09\/AquaSpaceMM-07-RS-27Aug18.pdf."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Toming, K., Kutser, T., Uiboupin, R., Arikas, A., Vahter, K., and Paavel, B. (2017). Mapping water quality parameters with Sentinel-3 ocean and land colour instrument imagery in the Baltic Sea. Remote Sens., 9.","DOI":"10.3390\/rs9101070"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kravitz, J., Matthews, M., Bernard, S., and Griffith, D. (2020). Application of Sentinel 3 OLCI for chl-a retrieval over small inland water targets: Successes and challenges. Remote Sens. Environ., 237.","DOI":"10.1016\/j.rse.2019.111562"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1016\/j.rse.2014.08.001","article-title":"On-orbit radiometric characterization of OLI (Landsat-8) for applications in aquatic remote sensing","volume":"154","author":"Pahlevan","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Bernardo, N., Watanabe, F., Rodrigues, T., and Alc\u00e2ntara, E. (2016). An investigation into the effectiveness of relative and absolute atmospheric correction for retrieval the TSM concentration in inland waters. Model. Earth Syst. Environ., 2.","DOI":"10.1007\/s40808-016-0176-9"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S0034-4257(02)00029-9","article-title":"Radiometric normalization of multitemporal high-resolution satellite images with quality control for land cover change detection","volume":"82","author":"Du","year":"2002","journal-title":"Remote Sens. Environ."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.rse.2018.09.022","article-title":"Multiple optimal depth predictors analysis (MODPA) for river bathymetry: Findings from spectroradiometry, simulations, and satellite imagery","volume":"218","author":"Vitti","year":"2018","journal-title":"Remote Sens. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, D., Ma, R., Xue, K., and Loiselle, S.A. (2019). The assessment of landsat-8 OLI atmospheric correction algorithms for inland waters. Remote Sens., 11.","DOI":"10.3390\/rs11020169"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/S0034-4257(00)00080-8","article-title":"Atmospheric correction of SeaWiFS imagery over turbid coastal waters: A practical method","volume":"74","author":"Hu","year":"2000","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Denaro, L.G., Lin, B.-Y., Syariz, M.A., Jaelani, L.M., and Lin, C.-H. (2018). Pseudoinvariant feature selection for cross-sensor optical satellite images. J. Appl. Remote Sens., 12.","DOI":"10.1117\/1.JRS.12.045002"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1109\/LGRS.2019.2899969","article-title":"Pseudoinvariant feature selection using multitemporal MAD for optical satellite images","volume":"16","author":"Lin","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.isprsjprs.2018.11.007","article-title":"Spectral-consistent relative radiometric normalization for multitemporal Landsat 8 imagery","volume":"147","author":"Syariz","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/S0924-2716(97)00016-6","article-title":"Assessing the radiometric fidelity of high resolution satellite image mosaics","volume":"52","author":"Guindon","year":"1997","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3769","DOI":"10.1109\/JSTARS.2019.2936403","article-title":"Estimation of chlorophyll-a concentrations in a highly turbid eutrophic lake using a classification-based MODIS land-band algorithm","volume":"12","author":"Li","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4430","DOI":"10.1109\/JSTARS.2017.2723079","article-title":"A Hybrid EOF algorithm to improve MODIS cyanobacteria phycocyanin data quality in a highly turbid lake: Bloom and nonbloom condition","volume":"10","author":"Tao","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_26","first-page":"912","article-title":"Determination of chlorophyll content of small water bodies (kettle holes) using hyperspectral airborne data","volume":"13","author":"Igamberdiev","year":"2011","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3577","DOI":"10.1364\/AO.45.003577","article-title":"Effect of bio-optical parameter variability and uncertainties in reflectance measurements on the remote estimation of chlorophyll-a concentration in turbid productive waters: Modeling results","volume":"45","author":"Gitelson","year":"2006","journal-title":"Appl. Opt."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.isprsjprs.2017.09.011","article-title":"Improved atmospheric correction and chlorophyll-a remote sensing models for turbid waters in a dusty environment","volume":"133","author":"Gherboudj","year":"2017","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3582","DOI":"10.1016\/j.rse.2008.04.015","article-title":"A simple semi-analytical model for remote estimation of chlorophyll-a in turbid waters: Validation","volume":"112","author":"Gitelson","year":"2008","journal-title":"Remote Sens. Environ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/LGRS.2009.2026657","article-title":"Satellite estimation of chlorophyll-a concentration using the red and NIR bands of MERIS\u2014The Azov sea case study","volume":"6","author":"Moses","year":"2009","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.rse.2013.09.024","article-title":"Estimation of diffuse attenuation of ultraviolet light in optically shallow Florida Keys waters from MODIS measurements","volume":"140","author":"Barnes","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_32","first-page":"28","article-title":"Application of Landsat 8 imagery to regional-scale assessment of lake water quality","volume":"51","author":"Wochna","year":"2016","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_33","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_34","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, F., and Ding, J. (2017). Evaluation of water quality based on a machine learning algorithm and water quality index for the Ebinur Lake Watershed. Sci. Rep., 1\u201318.","DOI":"10.1038\/s41598-017-12853-y"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"5403","DOI":"10.1029\/1998JC900082","article-title":"Semianalytic moderate-resolution imaging spectrometer algorithm for chlorophyll-a and absorption with bio-optical domains based on nitrate-depletion temperatures","volume":"104","author":"Carder","year":"1999","journal-title":"J. Geophys. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"18607","DOI":"10.1029\/96JC03243","article-title":"Inherent optical property inversion of ocean color spectra and its biogeochemical interpretation 1. Time series from the Sargassio Sea","volume":"102","author":"Garver","year":"1997","journal-title":"J. Geophys. Res."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3168","DOI":"10.1364\/AO.50.003168","article-title":"Neural network approach to retrieve the inherent optical properties of the ocean from observations of MODIS","volume":"50","author":"Ioannou","year":"2011","journal-title":"Appl. Opt."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.gsf.2015.07.003","article-title":"Machine learning in geosciences and remote sensing","volume":"7","author":"Lary","year":"2016","journal-title":"Geosci. Front."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tsagkatakis, G., Aidini, A., Fotiadou, K., Giannopoulos, M., Pentari, A., and Tsakalides, P. (2019). Survey of deep-learning approaches for remote sensing observation enhancement. Sensors, 19.","DOI":"10.3390\/s19183929"},{"key":"ref_40","first-page":"14","article-title":"Chlorophyll-a concentration retrieval using convolutional neural networks in Laugna Lake, Philippines","volume":"XLII","author":"Syariz","year":"2019","journal-title":"Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.rse.2013.02.015","article-title":"Deriving ocean color products using neural networks","volume":"134","author":"Ioannou","year":"2013","journal-title":"Remote Sens. Environ."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1841","DOI":"10.1080\/014311699212515","article-title":"The use of neural networks for the estimation of oceanic constituents based on the MERIS instrument","volume":"20","author":"Buckton","year":"1999","journal-title":"Int. J. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Hafeez, S., Wong, M., Ho, H., Nazeer, M., Nichol, J., Abbas, S., Tang, D., Lee, K., and Pun, L. (2019). Comparison of machine learning algorithms for retrieval of water quality indicators in case-II waters: A case study of Hong Kong. Remote Sens., 11.","DOI":"10.3390\/rs11060617"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"El-habashi, A., El-habashi, A., Ahmed, S., Ondrusek, M., and Lovko, V. (2020). Analyses of satellite ocean color retrievals show advantage of neural network approaches and algorithms that avoid deep blue bands. J. Appl. Remote Sens., 13.","DOI":"10.1117\/1.JRS.13.024509"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"48","DOI":"10.11113\/aej.v4.15432","article-title":"Hydrodynamic investigation of a shallow lake environment (Laguna Lake, Philippines) and associated implications for eutrophic vulnerability","volume":"4","author":"Herrera","year":"2015","journal-title":"ASEAN Eng. J. Part C"},{"key":"ref_46","unstructured":"Lasco, R.D., and Javier, E.Q. (2018). Laguna de Bay: Case Study for Sustainable Fisheries Development, National Academy of Science and Technology."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"31033","DOI":"10.1029\/98JC02712","article-title":"Variations of light absorption by suspended particles with chlorophyll A concentration in oceanic (case 1) waters: Analysis and implications for bio-optical models","volume":"103","author":"Bricaud","year":"1998","journal-title":"J. Geophys. Res."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"7163","DOI":"10.1029\/2000JC000319","article-title":"Bio-optical properties of oceanic waters: A reappraisal","volume":"106","author":"Morel","year":"2001","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"421","DOI":"10.3390\/rs6010421","article-title":"Improved accuracy of chlorophyll-a concentration estimates from MODIS Imagery using a two-band ratio algorithm and geostatistics: As applied to the monitoring of eutrophication processes over Tien Yen Bay (Northern Vietnam)","volume":"6","author":"Ha","year":"2013","journal-title":"Remote Sens."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"8138","DOI":"10.1029\/2018JC014052","article-title":"Remote sensing of chlorophyll-A in case II waters: A novel approach with improved accuracy over widely implemented turbid water indices","volume":"123","author":"Menon","year":"2018","journal-title":"J. Geophys. Res. Ocean."},{"key":"ref_51","unstructured":"GKSS Research Center (2010). OLCI Level 2 Algorithm Theoretical Basis Document Ocean Colour Turbid Water, GKSS."},{"key":"ref_52","unstructured":"Kingma, D.P., and Ba, J. (2015). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.rse.2011.10.016","article-title":"Normalized difference chlorophyll index: A novel model for remote estimation of chlorophyll-a concentration in turbid productive waters","volume":"117","author":"Mishra","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1080\/014311699212470","article-title":"Interpretation of the 685nm peak in water-leaving radiance spectra in terms of fluorescence, absorption and scattering, and its observation by MERIS","volume":"20","author":"Gower","year":"1999","journal-title":"Int. J. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/12\/1966\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:40:36Z","timestamp":1760175636000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/12\/1966"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,18]]},"references-count":54,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["rs12121966"],"URL":"https:\/\/doi.org\/10.3390\/rs12121966","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,18]]}}}