Harmful algal bloom (HAB) is a problematic condition in inland water caused by increased suspended algae or phytoplankton. Blooms rapidly drain nutrients, reduce transparency, and deplete essential resources, causing a swift decrease in biomass. The chlorophyll-a concentration used to quantify the phytoplankton biomass is commonly used as an indicator to evaluate the trophic level of lakes and water quality.
This research aims to develop an estimation model for chlorophyll-a retrieval in eutrophic inland water. The estimation model was generated using the chlorophyll-a observation data from ten reservoirs in Taiwan matched with the spectral reflectance of the Sentinel-2 MSI Level-2A throughout band ratio (N = 409). The algorithm based on band ratio is selected due to its capability of reducing the interference on reflectance. Among all the ratios, the developed algorithms focusing on the relationship within the red-NIR (650 – 800 nm) ratio are more appropriate for chlorophyll-a retrieval in eutrophic environments due to the minimal absorption by CDOM and scattering by mineral particles. The nonlinear relationship between factor parameters and water properties requires an advanced estimation model. Therefore, the machine learning algorithm was developed. The multiple-band ratio was proposed as the input variable in machine learning to obtain the best estimation model.
The collinearity test is utilized to determine the sufficient multiple band ratios with variance inflation factor (VIF<3). Regarding the machine learning model through a qualified scheme in the tunning process, the multiple band ratio presents a robust performance by improving the model accuracy when compared with the single-band ratio input variable. The random forest model using red-NIR three-band (Band ratio, BR 5) shows robust performance in single (R2 = 0.688) and multiple ratios (R2 = 0.873, [BR 5, BR 2]). In this study, the multiple-band ratio concept has been proven to be an effective choice for 18.5% improving the estimation model of chlorophyll-a retrieval. The developed model (multiple band-ratio random forest) was tested in ten study sites to evaluate the stability performance, where the observed and estimated chlorophyll-a result is well-performs in most reservoirs. Furthermore, the Tsengwen reservoir, as the most extensive reservoir in Taiwan, has been preferred for mapping purposes. The result proves the model's capability to map and present the chlorophyll-a distribution.
The proposed model is also developed under the Sentinel-3 OLCI environment corresponding to chlorophyll-a observation data in five reservoirs. The model presents a robust performance for chlorophyll-a retrieval (R2 = 0.822) on OLCI images. The Sentinel-3 OLCI was also an alternate MSI sensor for the rapid examination of chlorophyll-a retrieval since OLCI had a higher revisit time and multiple matchups with MSI. However, the spatial resolution in Sentinel-3 OLCI is coarse. The data integration model was used to refine the spatial resolution. Finally, the model estimates near-daily chlorophyll-a concentration within two months using time-series OLCI images in the Tsengwen reservoir.

Adams, J. et al. (2019) ‘Identifying and treating outliers in finance’, Financial Management, 48(2), pp. 345–384. doi: 10.1111/fima.12269.
Ahmed, U. et al. (2019) ‘Efficient Water Quality Prediction Using Supervised Machine Learning’, Water, 11(1), pp. 1–14.
Alexander, D. L. J., Tropsha, A. andWinkler, D. A. (2015) ‘Beware of R2 : simple, unambiguous assessment of the prediction accuracy of QSAR and QSPR models’, Department of Health & Human Services - USA, 55(7), pp. 1316–1322. doi: 10.1021/acs.jcim.5b00206.Beware.
Alin, A. (2010) ‘Multicollinearity’, Wiley Interdisciplinary Reviews: Computational Statistics, 2(3), pp. 370–374. doi: 10.1002/wics.84.
Amit, Y. andGeman, D. (1997) ‘Shape Quantization and Recognition with Randomized Trees’, Neural Computation, 9(7), pp. 1545–1588. doi: 10.1162/neco.1997.9.7.1545.
Ansper, A. andAlikas, K. (2019) ‘Retrieval of chlorophyll a from Sentinel-2 MSI data for the European Union water framework directive reporting purposes’, Remote Sensing, 11(1). doi: 10.3390/rs11010064.
Baban, S. M. J. (1996) ‘Trophic classification and ecosystem checking of lakes using remotely sensed information’, Hydrological Sciences Journal, 41(6), pp. 939–957. doi: 10.1080/02626669609491560.
Bakker, M. andWicherts, J. M. (2014) ‘Outlier removal, sum scores, and the inflation of the type i error rate in independent samples t tests: The power of alternatives and recommendations’, Psychological Methods, 19(3), pp. 409–427. doi: 10.1037/met0000014.
Barber, R. T. et al. (1983) Coastal and Estuarine Studies of Ocean Color for Interpretation of Satellite.
Berk, A. et al. (2004) ‘MODTRAN5: a reformulated atmospheric band model with auxiliary species and practical multiple scattering options’, Remote Sensing of Clouds and the Atmosphere IX, 5571(November 2004), p. 78. doi: 10.1117/12.564634.
Binding, C. E. et al. (2018) ‘An analysis of satellite-derived chlorophyll and algal bloom indices on Lake Winnipeg’, Journal of Great Lakes Research. Elsevier B.V., 44(3), pp. 436–446. doi: 10.1016/j.jglr.2018.04.001.
Boucher, J. et al. (2018) ‘Assessing the effectiveness of Landsat 8 chlorophyll a retrieval algorithms for regional freshwater monitoring’, Ecological Applications, 28(4), pp. 1044–1054. doi: 10.1002/eap.1708.
Bramich, J., Bolch, C. J. S. andFischer, A. (2021) ‘Improved red-edge chlorophyll-a detection for Sentinel 2’, Ecological Indicators. Elsevier, 120(September 2020), p. 106876. doi: 10.1016/j.ecolind.2020.106876.
Breiman, L. et al. (1984) Classification and Regression Trees, Encyclopedia of Data Warehousing and Mining. doi: 10.4018/9781591405573.ch027.
Breiman, L. (2001) Random forests, Random Forests. Edited by R. E.Schapire. Kluwer Academic Publishers. doi: 10.1201/9780429469275-8.
Bricaud, A. et al. (1998) ‘Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: Analysis and implications for bio-optical models’, Journal of Geophysical Research: Oceans, 103(C13), pp. 31033–31044. doi: 10.1029/98jc02712.
Bukata, R. P. et al. (1981) ‘Optical water quality model of Lake Ontario 2: Determination of chlorophyll a and suspended mineral concentrations of natural waters from submersible and low altitude optical sensors’, Applied Optics, 20(9), p. 1704. doi: 10.1364/ao.20.001704.
Cairo, C. et al. (2020) ‘Hybrid chlorophyll-a algorithm for assessing trophic states of a tropical brazilian reservoir based on msi/sentinel-2 data’, Remote Sensing, 12(1). doi: 10.3390/RS12010040.
Çako, V., Baci, S. andShena, M. (2013) ‘Water Turbidity as One of the Trophic State Indices in Butrinti Lake’, Journal of Water Resource and Protection, 05(12), pp. 1144–1148. doi: 10.4236/jwarp.2013.512120.
Camann, K., Thomas, A. andEllis, J. (2010) ‘Resampling considerations for registering remotely sensed images’, Conference Proceedings - IEEE SOUTHEASTCON. IEEE, pp. 159–162. doi: 10.1109/SECON.2010.5453899.
Camps-valls, G., Tuia, D. andBruzzone, L. (2013) ‘Advances in hyperspectral image classification’, IEEE Signal Processing Magazine, (January), pp. 45–54.
Cao, Z. et al. (2020) ‘A machine learning approach to estimate chlorophyll-a from Landsat-8 measurements in inland lakes’, Remote Sensing of Environment. Elsevier, 248(July), p. 111974. doi: 10.1016/j.rse.2020.111974.
Carlson, R. E. (1977) ‘A trophic state index for lakes’, Limnology and Oceanography, 22(2), pp. 361–369. doi: 10.4319/lo.1977.22.2.0361.
Castrillo, M. andGarcía, Á. L. (2020) ‘Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods’, Water Research, 172. doi: 10.1016/j.watres.2020.115490.
Cazzaniga, I. et al. (2019) ‘A comparison of Sentinel-3-OLCI and Sentinel-2-MSI-derived Chlorophyll-a maps for two large Italian lakes’, Remote Sensing Letters. Taylor & Francis, 10(10), pp. 978–987. doi: 10.1080/2150704X.2019.1634298.
Chang, C. H. et al. (2009) ‘Monitoring reservoir water quality with Formosat-2 high spatiotemporal imagery’, Journal of Environmental Monitoring, 11(11), pp. 1982–1992. doi: 10.1039/b912897b.
Chen, G. et al. (2017) ‘Multiple Random Forests Modelling for Urban Water Consumption Forecasting’, Water Resources Management. Water Resources Management, 31(15), pp. 4715–4729. doi: 10.1007/s11269-017-1774-7.
Chen, S. et al. (2019) ‘A machine learning approach to estimate surface ocean pCO2 from satellite measurements’, Remote Sensing of Environment. Elsevier, 228(April), pp. 203–226. doi: 10.1016/j.rse.2019.04.019.
Chi, L. andChung, J. (2021) ‘Problematic water quality at island reservoirs: report’, Taiwan News, 2August. Available at: https://www.taipeitimes.com/News/taiwan/archives/2021/08/02/2003761878.
Choi, J. H. et al. (2019) ‘Modelling Chlorophyll-a Concentration using Deep Neural Networks considering Extreme Data Imbalance and Skewness’, International Conference on Advanced Communication Technology, ICACT. Global IT Research Institute (GIRI), 2019-Febru, pp. 631–634. doi: 10.23919/ICACT.2019.8702027.
Chu, H. J. et al. (2021) ‘Multi-reservoir water quality mapping from remote sensing using spatial regression’, Sustainability (Switzerland), 13(11), pp. 1–13. doi: 10.3390/su13116416.
Chusnah, W. N. andChu, H.-J. (2021) ‘Estimating chlorophyll-a concentrations in tropical reservoirs from band-ratio machine learning models’, Remote Sensing Applications: Society and Environment. Elsevier B.V., 25(October 2021), p. 100678. doi: 10.1016/j.rsase.2021.100678.
Ciotti, Á. M., Lewis, M. R. andCullen, J. J. (2002) ‘Assessment of the relationships between dominant cell size in natural phytoplankton communities and the spectral shape of the absorption coefficient’, Limnology and Oceanography, 47(2), pp. 404–417. doi: 10.4319/lo.2002.47.2.0404.
Cousineau, D. andChartier, S. (2010) ‘Outliers detection and treatment: a review.’, International Journal of Psychological Research, 3(1), pp. 58–67. doi: 10.21500/20112084.844.
D’Sa, E. J. (2014) ‘Assessment of chlorophyll variability along the Louisiana coast using multi-satellite data’, GIScience and Remote Sensing. Taylor & Francis, 51(2), pp. 139–157. doi: 10.1080/15481603.2014.895578.
D’Sa, E. J. andMiller, R. L. (2003) ‘Bio-optical properties in waters influenced by the Mississippi River during low flow conditions’, Remote Sensing of Environment, 84(4), pp. 538–549. doi: 10.1016/S0034-4257(02)00163-3.
Dall’Olmo, G. et al. (2005) ‘Assessing the potential of SeaWiFS and MODIS for estimating chlorophyll concentration in turbid productive waters using red and near-infrared bands’, Remote Sensing of Environment, 96(2), pp. 176–187. doi: 10.1016/j.rse.2005.02.007.
Dall’Olmo, G. andGitelson, A. A. (2006) ‘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’, Applied Optics, 45(15), pp. 3577–3592. doi: 10.1364/AO.45.003577.
Dall’Olmo, G., Gitelson, A. A. andRundquist, D. C. (2003) ‘Towards a unified approach for remote estimation of chlorophyll-a in both terrestrial vegetation and turbid productive waters’, Geophysical Research Letters, 30(18). doi: 10.1029/2003GL018065.
Dekker, A. . (1993) Detection of optical water quality parameters for eutrophic waters by high resolution remote sensing. doi: 10.1177/030913339301700307.
Dekker, A G andPeters, S. W. M. (1993) ‘The use of the Thematic Mapper for the analysis of eutrophic lakes: a case study in the Netherlands.’, International Journal of Remote Sensing. Taylor & Francis, 14(5), pp. 799–821. doi: 10.1080/01431169308904379.
Dekker, A. G. andPeters, S. W. M. (1993) ‘The use of the thematic mapper for the analysis of eutrophic lakes: A case study in the netherlands’, International Journal of Remote Sensing, 14(5), pp. 799–821. doi: 10.1080/01431169308904379.
Díaz-Uriarte, R. andAlvarez de Andrés, S. (2006) ‘Gene selection and classification of microarray data using random forest’, BMC Bioinformatics, 7, pp. 1–13. doi: 10.1186/1471-2105-7-3.
DIOUF, D. andSeck, D. (2019) ‘Modeling the Chlorophyll-a from Sea Surface Reflectance in West Africa by Deep Learning Methods: A Comparison of Multiple Algorithms’, International Journal of Artificial Intelligence & Applications, 10(6), pp. 33–40. doi: 10.5121/ijaia.2019.10603.
Dodds, W. K. andSmith, V. H. (2016) ‘Nitrogen, phosphorus, and eutrophication in streams’, Inland Waters, 6(2), pp. 155–164. doi: 10.5268/IW-6.2.909.
Doerffer, R., Sorensen, K. andAiken, J. (1999) ‘MERIS potential for coastal zone applications’, International Journal of Remote Sensing, 20(9), pp. 1809–1818. doi: 10.1080/014311699212498.
Dormann, C. F. et al. (2013) ‘Collinearity: A review of methods to deal with it and a simulation study evaluating their performance’, Ecography, 36(1), pp. 27–46. doi: 10.1111/j.1600-0587.2012.07348.x.
Doxani, G. et al. (2018) ‘Atmospheric correction inter-comparison exercise’, Remote Sensing, 10(2), pp. 1–18. doi: 10.3390/rs10020352.
ESA (2015) Sentinel-2 User Handbook. ESA Standa. doi: 10.1021/ie51400a018.
ESA (2017) ‘Sentinel-2 Spectral Response Func-tions (S2-SRF), Version: 3.0.’ Available at: ttps://sentinel.esa.int/documents/247904/685211/S2-SRF_COPE-GSEG-EOPG-TN-15-0007_3.0.xlsx.
EUMETSAT (2018) Sentinel-3 OLCI Marine User Handbook.
Falconer, I. R. (1999) ‘An overview of problems caused by toxic blue-green algae (cyanobacteria) in drinking and recreational water’, Environmental Toxicology, 14(1), pp. 5–12. doi: 10.1002/(SICI)1522-7278(199902)14:1<5::AID-TOX3>3.0.CO;2-0.
Finlayson, C. M. andD’Cruz, R. (2010) ‘Inland Water Systems’, Ecosystems and Human Well-being: Current State and Trends, 1(January), pp. 551–583. Available at: http://www.millenniumassessment.org/en/Condition.html.
Gakii, C. andJepkoech, J. (2019) ‘A Classification Model for Water Quality Analysis Using Decision Tree’, Journal of Chemical Information and Modeling, 7(3), pp. 1–8.
Garver, S. A. andSiegel, D. A. (1994) ‘Variability in near-surface particulate absorption spectra: What can a satellite ocean color imager see?’
Gernez, P., Doxaran, D. andBarillé, L. (2017) ‘Shellfish aquaculture from Space: Potential of Sentinel2 to monitor tide-driven changes in turbidity, chlorophyll concentration and oyster physiological response at the scale of an oyster farm’, Frontiers in Marine Science, 4(MAY), pp. 1–15. doi: 10.3389/fmars.2017.00137.
Gershman, A. et al. (2010) ‘A Decision Tree Based Recommender System.’, Iics, pp. 170–179.
Gilerson, A. A. et al. (2010) ‘Algorithms for remote estimation of chlorophyll-a in coastal and inland waters using red and near infrared bands’, Optics Express, 18(23), p. 24109. doi: 10.1364/oe.18.024109.
Gislason, P. O., Benediktsson, J. A. andSveinsson, J. R. (2006) ‘Random forests for land cover classification’, Pattern Recognition Letters, 27(4), pp. 294–300. doi: 10.1016/j.patrec.2005.08.011.
Gitelson, A. (1992) ‘The peak near 700 nm on radiance spectra of algae and water: Relationships of its magnitude and position with chlorophyll’, International Journal of Remote Sensing, 13(17), pp. 3367–3373. doi: 10.1080/01431169208904125.
Gitelson, A. et al. (1993) ‘Quantitative remote sensing methods for real-time monitoring of inland waters quality’, International Journal of Remote Sensing, 14(7), pp. 1269–1295. doi: 10.1080/01431169308953956.
Gitelson, A. A. et al. (2008) ‘A simple semi-analytical model for remote estimation of chlorophyll-a in turbid waters: Validation’, Remote Sensing of Environment, 112(9), pp. 3582–3593. doi: 10.1016/j.rse.2008.04.015.
Gitelson, A. A. et al. (2009) ‘A bio-optical algorithm for the remote estimation of the chlorophyll-a concentration in case 2 waters’, Environmental Research Letters, 4(4). doi: 10.1088/1748-9326/4/4/045003.
Gitelson, A. A., Gritz, Y. andMerzlyak, M. N. (2003) ‘Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves’, Journal of Plant Physiology, 160(3), pp. 271–282. doi: 10.1078/0176-1617-00887.
Gitelson, A. A., Schalles, J. F. andHladik, C. M. (2007) ‘Remote chlorophyll-a retrieval in turbid, productive estuaries: Chesapeake Bay case study’, Remote Sensing of Environment, 109(4), pp. 464–472. doi: 10.1016/j.rse.2007.01.016.
Gomez-Chova, L. et al. (2015) ‘Multimodal Classification of Remote Sensing Images: A Review and Future Directions’, Proceedings of the IEEE, 103(9), pp. 1560–1584. doi: 10.1109/JPROC.2015.2449668.
Gorelick, N. et al. (2017) ‘Google Earth Engine: Planetary-scale geospatial analysis for everyone’, Remote Sensing of Environment. The Author(s), 202, pp. 18–27. doi: 10.1016/j.rse.2017.06.031.
Gurlin, D., Gitelson, A. A. andMoses, W. J. (2011) ‘Remote estimation of chl-a concentration in turbid productive waters - Return to a simple two-band NIR-red model?’, Remote Sensing of Environment. Elsevier Inc., 115(12), pp. 3479–3490. doi: 10.1016/j.rse.2011.08.011.
Ha, N. T. T. et al. (2017) ‘Selecting the best band ratio to estimate chlorophyll-a concentration in a tropical freshwater lake using sentinel 2A images from a case study of Lake Ba Be (Northern Vietnam)’, ISPRS International Journal of Geo-Information, 6(9). doi: 10.3390/ijgi6090290.
Han, L. andJordan, K. J. (2005) ‘Estimating and mapping chlorophyll-a concentration in Pensacola Bay, Florida using Landsat ETM + data’, International Journal of Remote Sensing, 26(23), pp. 5245–5254. doi: 10.1080/01431160500219182.
Hmimina, G. et al. (2019) ‘Linking phytoplankton pigment composition and optical properties: A framework for developing remote-sensing metrics for monitoring cyanobacteria’, Water Research. Elsevier Ltd, 148, pp. 504–514. doi: 10.1016/j.watres.2018.09.055.
Ho, W.-T., Ryu, K. andWan, K.-M. (2017) ‘Treatment of Outliers: Firm Heterogeneity in Managerial Incentives and Corporate Innovation Relationship * Wai-Tung Ho * , Keunkwan Ryu † , and Kam-Ming Wan ‡’, pp. 1–52.
Hollister, J. W., Milstead, W. B. andKreakie, B. J. (2016) ‘Modeling lake trophic state: A random forest approach’, Ecosphere, 7(3), pp. 1–38. doi: 10.1002/ecs2.1321.
Hu, C., Feng, L. andGuan, Q. (2021) ‘A Machine Learning Approach to Estimate Surface Chlorophyll a Concentrations in Global Oceans from Satellite Measurements’, IEEE Transactions on Geoscience and Remote Sensing, 59(6), pp. 4590–4607. doi: 10.1109/TGRS.2020.3016473.
Huang, G. et al. (2019) ‘Evaluation of CatBoost method for prediction of reference evapotranspiration in humid regions’, Journal of Hydrology. Elsevier, 574(December 2018), pp. 1029–1041. doi: 10.1016/j.jhydrol.2019.04.085.
Hunter, P. D. et al. (2009) ‘Using remote sensing to aid the assessment of human health risks from blooms of potentially toxic cyanobacteria’, Environmental Science and Technology, 43(7), pp. 2627–2633. doi: 10.1021/es802977u.
Hussein, N. M. andAssaf, M. N. (2020) ‘Multispectral Remote Sensing Utilization for Monitoring Chlorophyll-a Levels in Inland Water Bodies in Jordan’, Scientific World Journal, 2020. doi: 10.1155/2020/5060969.
Inglada, J. et al. (2006) ‘Analysis of artifacts in sub-pixel remote sensing image registration’, Revue Francaise de Photogrammetrie et de Teledetection, 45(184), pp. 29–34.
Jadhav, S. D. andChanne, H. P. (2016) ‘Efficient Recommendation System Using Decision Tree Classifier and Collaborative Filtering’, International Research Journal of Engineering and Technology(IRJET), 3(8), pp. 2113–2118.
Jarrell, M. G. (1991) ‘Review of the Literature: Multivariate Outliers’.
Jiang, P. et al. (2007) ‘MiPred: Classification of real and pseudo microRNA precursors using random forest prediction model with combined features’, Nucleic Acids Research, 35(SUPPL.2), pp. 339–344. doi: 10.1093/nar/gkm368.
K.M. (1975) ‘The algal bowl. lakes and man’, Environmental Pollution (1970), 9(3), p. 240. doi: 10.1016/0013-9327(75)90042-7.
Kallio, K. et al. (2001) ‘Retrieval of water quality from airborne imaging spectrometry of various lake types in different seasons’, Science of the Total Environment, 268(1–3), pp. 59–77. doi: 10.1016/S0048-9697(00)00685-9.
Kallio, K., Koponen, S. andPulliainen, J. (2003) ‘Feasibility of airborne imaging spectrometry for lake monitoring - A case study of spatial chlorophyll a distribution in two meso-eutrophic lakes’, International Journal of Remote Sensing, 24(19), pp. 3771–3790. doi: 10.1080/0143116021000023899.
Kannan, K. S., Manoj, K. andArumugam, S. (2015) ‘Labeling Methods for Identifying Outliers’, International Journal of Statistics and Systems(IJSS), (November).
Kasprzak, P. et al. (2008) ‘Chlorophyll a concentration across a trophic gradient of lakes: An estimator of phytoplankton biomass?’, Limnologica, 38(3–4), pp. 327–338. doi: 10.1016/j.limno.2008.07.002.
DeKeukelaere, L. et al. (2018) ‘Atmospheric correction of Landsat-8/OLI and Sentinel-2/MSI data using iCOR algorithm: validation for coastal and inland waters’, European Journal of Remote Sensing. Taylor & Francis, 51(1), pp. 525–542. doi: 10.1080/22797254.2018.1457937.
Kirk, J. T. O. (1983) ‘Light and photosynthesis in aquatic ecosystems.’, Light and photosynthesis in aquatic ecosystems., (March), pp. 3–6. doi: 10.2307/2405114.
Kit, T. (2017) ‘Ocean Colour with Sentinel-3 Olci July 2017, North Sea’, Research and User Support-Copernicus, (July), pp. 1–16. Available at: https://rus-copernicus.eu/portal/wp-content/uploads/library/education/training/OCEA04_OceanColour_S3_Tutorial.pdf.
Kown, Y. S. et al. (2018) ‘Monitoring coastal chlorophyll-a concentrations in coastal areas using machine learning models’, Water (Switzerland), 10(8), pp. 1–17. doi: 10.3390/w10081020.
Kravitz, J. et al. (2020) ‘Application of Sentinel 3 OLCI for chl-a retrieval over small inland water targets: Successes and challenges’, Remote Sensing of Environment. Elsevier, 237(December 2019), p. 111562. doi: 10.1016/j.rse.2019.111562.
Kutser, T. et al. (2005) ‘Mapping lake CDOM by satellite remote sensing’, Remote Sensing of Environment, 94(4), pp. 535–540. doi: 10.1016/j.rse.2004.11.009.
Kutser, T. (2009) ‘Passive optical remote sensing of cyanobacteria and other intense phytoplankton blooms in coastal and inland waters’, International Journal of Remote Sensing, 30(17), pp. 4401–4425. doi: 10.1080/01431160802562305.
Kyryliuk, D. andKratzer, S. (2019) ‘Evaluation of Sentinel-3A OLCI Products Derived Using the Case-2 Regional CoastColour Processor over the Baltic Sea’, (October 1978).
Lahouar, A. andBenHadj Slama, J. (2015) ‘Day-ahead load forecast using random forest and expert input selection’, Energy Conversion and Management. Elsevier Ltd, 103, pp. 1040–1051. doi: 10.1016/j.enconman.2015.07.041.
Lai, Y. et al. (2021) ‘Retrieval and evaluation of chlorophyll-a concentration in reservoirs with main water supply function in beijing, china, based on landsat satellite images’, International Journal of Environmental Research and Public Health, 18(9). doi: 10.3390/ijerph18094419.
Le, C. et al. (2009) ‘A four-band semi-analytical model for estimating chlorophyll a in highly turbid lakes: The case of Taihu Lake, China’, Remote Sensing of Environment. Elsevier B.V., 113(6), pp. 1175–1182. doi: 10.1016/j.rse.2009.02.005.
Le, C. et al. (2011) ‘Remote estimation of chlorophyll a in optically complex waters based on optical classification’, Remote Sensing of Environment - REMOTE SENS ENVIRON, 115, pp. 725–737. doi: 10.1016/j.rse.2010.10.014.
Le, C. et al. (2013) ‘Long-term distribution patterns of remotely sensed water quality parameters in Chesapeake Bay’, Estuarine, Coastal and Shelf Science, 128, pp. 93–103. Available at: https://www.sciencedirect.com/science/article/abs/pii/S0272771413002217.
Leys, C. et al. (2019) ‘How to classify, detect, and manage univariate and multivariate outliers, with emphasis on pre-registration’, International Review of Social Psychology, 32(1), pp. 1–10. doi: 10.5334/irsp.289.
Li, S. et al. (2021) ‘Quantification of chlorophyll-a in typical lakes across China using Sentinel-2 MSI imagery with machine learning algorithm’, Science of the Total Environment. Elsevier B.V., 778, p. 146271. doi: 10.1016/j.scitotenv.2021.146271.
Li, Y. et al. (2018) ‘Evaluation of Sentinel-2A Surface Reflectance Derived Using Sen2Cor in North America’, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. IEEE, 11(6), pp. 1997–2021. doi: 10.1109/JSTARS.2018.2835823.
Lindholm, T., Eriksson, J. E. andMeriluoto, J. A. O. (1989) ‘Toxic cyanobacteria and water quality problems-Examples from a eutrophic lake on Åland, South West Finland’, Water Research, 23(4), pp. 481–486. doi: 10.1016/0043-1354(89)90139-5.
Lins, R. C. et al. (2017) ‘Assessment of chlorophyll-a remote sensing algorithms in a productive tropical estuarine-lagoon system’, Remote Sensing, 9(6), pp. 1–19. doi: 10.3390/rs9060516.
Mamun, M. et al. (2020) ‘Prediction of algal chlorophyll-a and water clarity in monsoon-region reservoir using machine learning approaches’, Water (Switzerland), 12(1). doi: 10.3390/w12010030.
Matsushita, B. et al. (2015) ‘A hybrid algorithm for estimating the chlorophyll-a concentration across different trophic states in Asian inland waters’, ISPRS Journal of Photogrammetry and Remote Sensing. International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS), 102, pp. 28–37. doi: 10.1016/j.isprsjprs.2014.12.022.
Matthews, M. W., Bernard, S. andWinter, K. (2010) ‘Remote sensing of cyanobacteria-dominant algal blooms and water quality parameters in Zeekoevlei, a small hypertrophic lake, using MERIS’, Remote Sensing of Environment. Elsevier Inc., 114(9), pp. 2070–2087. doi: 10.1016/j.rse.2010.04.013.
Matus-Hernández, M. Á., Hernández-Saavedra, N. Y. andOctavio Martínez-Rincón, R. (2018) ‘Predictive performance of regression models to estimate Chlorophyll - A concentration based on Landsat imagery’, PLoS ONE, 13(10). doi: 10.1371/journal.pone.0205682.
McClain, C. R., Feldman, G. C. andHooker, S. B. (2004) ‘An overview of the SeaWiFS project and strategies for producing a climate research quality global ocean bio-optical time series’, Deep-Sea Research Part II: Topical Studies in Oceanography, 51(1–3), pp. 5–42. doi: 10.1016/j.dsr2.2003.11.001.
Merheim-Kealy, P., Huot, J. P. andDelwart, S. (1999) ‘The MERIS ground segment’, International Journal of Remote Sensing. Taylor & Francis, 20(9), pp. 1703–1712. doi: 10.1080/014311699212425.
Mobley, C. (1994) ‘Light and Water : Radiative Transfer in Natural Waters Light and Water : Radiative Transfer in Natural Waters can be downloaded from the publications page of the Ocean Optics Web Book ’:, Academic Press, (March), p. 592.
Modiegi, M., Rampedi, I. T. andTesfamichael, S. G. (2020) ‘Comparison of multi-source satellite data for quantifying water quality parameters in a mining environment’, Journal of Hydrology. Elsevier, 591(January), p. 125322. doi: 10.1016/j.jhydrol.2020.125322.
Moore, G. F., Aiken, J. andLavender, S. J. (1999) ‘The atmospheric correction of water colour and the quantitative retrieval of suspended particulate matter in Case II waters: Application to MERIS’, International Journal of Remote Sensing, 20(9), pp. 1713–1733. doi: 10.1080/014311699212434.
Morel, A. andPrieur, L. (1977) ‘Analysis of variations in ocean color’, Limnology and Oceanography, 22(4), pp. 709–722. doi: 10.4319/lo.1977.22.4.0709.
Moses, W. J. et al. (2009) ‘Satellite estimation of chlorophyll-a concentration using the red and NIR bands of MERISThe azov sea case study’, IEEE Geoscience and Remote Sensing Letters, 6(4), pp. 845–849. doi: 10.1109/LGRS.2009.2026657.
Moutzouris-Sidiris, I. andTopouzelis, K. (2021) ‘Assessment of Chlorophyll-a concentration from Sentinel-3 satellite images at the Mediterranean Sea using CMEMS open source in situ data’, Open Geosciences, 13(1), pp. 85–97. doi: 10.1515/geo-2020-0204.
Murphy, K. P. (2012) ‘Machine Learning: A Probabilistic Perspective’, Machine Learning, pp. 555–610. doi: 10.1016/b978-0-08-051055-2.50029-8.
Neville, R. A. andGower, J. F. R. (1977) ‘PASSIVE REMOTE SENSING OF PHYTOPLANKTON VIA CHLOROPHYLL alpha FLUORESCENCE.’, J Geophys Res, 82(24), pp. 3487–3493. doi: 10.1029/jc082i024p03487.
Nünez, J. et al. (1999) ‘Multiresolution-based image fusion with additive wavelet decomposition’, IEEE Transactions on Geoscience and Remote Sensing, 37(3 I), pp. 1204–1211. doi: 10.1109/36.763274.
Nurgiantoro et al. (2019) ‘Assessment of atmospheric correction results by iCOR for MSI and OLI data on TSS concentration’, IOP Conference Series: Earth and Environmental Science, 389(1). doi: 10.1088/1755-1315/389/1/012001.
O’Reilly, J. E. et al. (1998) ‘Ocean color chlorophyll algorithms for SeaWiFS’, Journal of Geophysical Research: Oceans, 103(C11), pp. 24937–24953. doi: 10.1029/98JC02160.
O’Reilly, J. E. andWerdell, P. J. (2019) ‘Chlorophyll algorithms for ocean color sensors - OC4, OC5 & OC6’, Remote Sensing of Environment. Elsevier, 229(October 2018), pp. 32–47. doi: 10.1016/j.rse.2019.04.021.
Odermatt, D. et al. (2012) ‘Review of constituent retrieval in optically deep and complex waters from satellite imagery’, Remote Sensing of Environment. Elsevier Inc., 118, pp. 116–126. doi: 10.1016/j.rse.2011.11.013.
Ogashawara, I. et al. (2021) ‘The use of sentinel-2 for chlorophyll-A spatial dynamics assessment: A comparative study on different lakes in northern Germany’, Remote Sensing, 13(8), pp. 1–26. doi: 10.3390/rs13081542.
Paerl, H. W. et al. (2001) ‘Harmful freshwater algal blooms, with an emphasis on cyanobacteria.’, TheScientificWorldJournal, 1, pp. 76–113. doi: 10.1100/tsw.2001.16.
Paerl, H. W. andOtten, T. G. (2013) ‘Harmful Cyanobacterial Blooms: Causes, Consequences, and Controls’, Microbial Ecology, 65(4), pp. 995–1010. doi: 10.1007/s00248-012-0159-y.
Pahlevan, N. et al. (2020) ‘Seamless retrievals of chlorophyll-a from Sentinel-2 (MSI) and Sentinel-3 (OLCI) in inland and coastal waters: A machine-learning approach’, Remote Sensing of Environment. Elsevier, 240(August 2019), p. 111604. doi: 10.1016/j.rse.2019.111604.
Palmer, S. C. J., Kutser, T. andHunter, P. D. (2015) ‘Remote sensing of inland waters: Challenges, progress and future directions’, Remote Sensing of Environment. Elsevier Inc., 157, pp. 1–8. doi: 10.1016/j.rse.2014.09.021.
Patel, H. H. andPrajapati, P. (2018) ‘Study and Analysis of Decision Tree Based Classification Algorithms’, International Journal of Computer Sciences and Engineering, 6(10), pp. 74–78. doi: 10.26438/ijcse/v6i10.7478.
Peterson, K. T. et al. (2019) ‘Machine learning-based ensemble prediction of water-quality variables using feature-level and decision-level fusion with proximal remote sensing’, Photogrammetric Engineering and Remote Sensing, 85(4), pp. 269–280. doi: 10.14358/PERS.85.4.269.
Pilmis, B. et al. (2018) ‘Recent advances in the understanding and management of eutrophication’, F1000Research, 7, pp. 356–363. doi: 10.12688/f1000research.15081.1.
Pires, D. A. et al. (2015) ‘Water quality in four reservoirs of the metropolitan region of São Paulo, Brazil’, Acta Limnologica Brasiliensia, 27(4), pp. 370–380. doi: 10.1590/S2179-975X4914.
Poddar, S., Chacko, N. andSwain, D. (2019) ‘Estimation of Chlorophyll-a in Northern Coastal Bay of Bengal Using Landsat-8 OLI and Sentinel-2 MSI Sensors’, Frontiers in Marine Science, 6(October). doi: 10.3389/fmars.2019.00598.
Prieur, L. (1981) ‘An optical classification of coastal and oceanic waters based on the specific spectral absorption curves of phytoplankton pigments, dissolved organic matter, and other particulate’, Limonology And Oceanography, 26(4), pp. 671–689. Available at: http://www.jstor.org/stable/10.2307/2836033.
Prikaziuk, E., Yang, P. andvan derTol, C. (2021) ‘Google earthengine sentinel-3 OLCI level-1 dataset deviates from the original data: Causes and consequences’, Remote Sensing, 13(6), pp. 1–19. doi: 10.3390/rs13061098.
Protection, H. (2004) ‘Occurrence of Cyanobacterial Toxins ( Microcystins ) in Surface Waters of Rural Bangladesh - Pilot Study Water , Sanitation and Health Protection of the Human Environment World Health Organization’, World Health, (May).
Putri, M. S. A. et al. (2020) ‘Influencing factors analysis of Taiwan eutrophicated reservoirs’, Water (Switzerland), 12(5), pp. 1–16. doi: 10.3390/W12051325.
Pyo, J. C. et al. (2019) ‘A convolutional neural network regression for quantifying cyanobacteria using hyperspectral imagery’, Remote Sensing of Environment. Elsevier, 233(August), p. 111350. doi: 10.1016/j.rse.2019.111350.
Quinlan, J. R. (1990) ‘Decision Trees and Decisionmaking’, IEEE Transactions on Systems, Man and Cybernetics, 20(2), pp. 339–346. doi: 10.1109/21.52545.
Reed, A. H., Henry, R. J. andMason, W. B. (1971) ‘Influence of statistical method used on the resulting estimate of normal range.’, Clinical chemistry, 17 4, pp. 275–284.
Ritchie, J. C. et al. (1994) ‘Chlorophyll Measurements in the Presence of Suspended Sediment Using Broad Band Spectral Sensors Aboard Satellites’, Journal of Freshwater Ecology. Taylor & Francis, 9(3), pp. 197–206. doi: 10.1080/02705060.1994.9664887.
Ritchie, J. C., Zimba, P.V andEveritt, J. H. (2003) ‘Remote Sensing Techniques to Assess Water Quality’, Photogrammetric Engineering and Remote Sensing, 69, pp. 695–704.
Ruddick, K., Cauwer, V.De andPark, Y.-J. (2006) ‘Limnology and Oceanography - 2006 - Ruddick - Seaborne measurements of near infrared water‐leaving reflectance The.pdf’. American Society of Limnology and Oceanography, Inc., pp. 1167–1179.
Rumora, L., Miler, M. andMedak, D. (2020) ‘Impact of various atmospheric corrections on sentinel-2 land cover classification accuracy using machine learning classifiers’, ISPRS International Journal of Geo-Information. MDPI AG, 9(4). doi: 10.3390/ijgi9040277.
Sagan, V. et al. (2020) ‘Monitoring inland water quality using remote sensing: potential and limitations of spectral indices, bio-optical simulations, machine learning, and cloud computing’, Earth-Science Reviews. Elsevier, 205(April), p. 103187. doi: 10.1016/j.earscirev.2020.103187.
Salkind, N. J. (2012) Winsorize In : Encyclopedia of Research Design.
Schalles, J. F. et al. (1998) ‘ESTIMATION OF CHLOROPHYLL a FROM TIME SERIES MEASUREMENTS OF HIGH SPECTRAL RESOLUTION REFLECTANCE IN AN EUTROPHIC LAKE 1 sured indicator of algal density and is a key param- systems . The unique light absorption pattern of Numerous studies during the last’, Water, 390(January 1997), pp. 383–390.
Schalles, J. F. (2006) Optical remote sensing techniques to estimate phytoplankton chlorophyll a concentrations in coastal waters with varying suspended matter and cdom concentrations, Remote Sensing and Digital Image Processing. doi: 10.1007/1-4020-3968-9.
Scornet, E., Biau, G. andVert, J. P. (2015) ‘Consistency of random forests’, Annals of Statistics, 43(4), pp. 1716–1741. doi: 10.1214/15-AOS1321.
Shin, Y. et al. (2020) ‘Prediction of chlorophyll-a concentrations in the Nakdong river using machine learning methods’, Water (Switzerland), 12(6), pp. 1–18. doi: 10.3390/w12061822.
Smith, M. E., Robertson Lain, L. andBernard, S. (2018) ‘An optimized Chlorophyll a switching algorithm for MERIS and OLCI in phytoplankton-dominated waters’, Remote Sensing of Environment. Elsevier, 215(January), pp. 217–227. doi: 10.1016/j.rse.2018.06.002.
Spyrakos, E. et al. (2018) ‘Optical types of inland and coastal waters’, Limnology and Oceanography, 63(2), pp. 846–870. doi: 10.1002/lno.10674.
Strayer, D. L. andDudgeon, D. (2010) ‘Freshwater biodiversity conservation: Recent progress and future challenges’, Journal of the North American Benthological Society, 29(1), pp. 344–358. doi: 10.1899/08-171.1.
Strömbeck, N. andPierson, D. C. (2001) ‘The effects of variability in the inherent optical properties on estimations of chlorophyll a by remote sensing in Swedish freshwaters.’, The Science of the total environment. Netherlands, 268(1–3), pp. 123–137. doi: 10.1016/s0048-9697(00)00681-1.
Stumpf, R. P. andTyler, M. A. (1988) ‘Satellite detection of bloom and pigment distributions in estuaries’, Remote Sensing of Environment, 24(3), pp. 385–404. doi: 10.1016/0034-4257(88)90014-4.
Su, H. et al. (2019) ‘Estimating subsurface thermohaline structure of the global ocean using surface remote sensing observations’, Remote Sensing, 11(13). doi: 10.3390/rs11131598.
Su, H. et al. (2021) ‘Estimating coastal chlorophyll-a concentration from time-series olci data based on machine learning’, Remote Sensing, 13(4), pp. 1–21. doi: 10.3390/rs13040576.
Svetnik, V. et al. (2003) ‘Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling’, Journal of Chemical Information and Computer Sciences, 43(6), pp. 1947–1958. doi: 10.1021/ci034160g.
Taiwan Water Corporation (2021) Eutrophication. Available at: https://www.water.gov.tw/en/Subject/Detail/1162?nodeId=4680 (Accessed: 12November2021).
Tebbs, E. J., Remedios, J. J. andHarper, D. M. (2013) ‘Remote sensing of chlorophyll-a as a measure of cyanobacterial biomass in Lake Bogoria, a hypertrophic, saline-alkaline, flamingo lake, using Landsat ETM+’, Remote Sensing of Environment. Elsevier Inc., 135, pp. 92–106. doi: 10.1016/j.rse.2013.03.024.
Thanh Noi, P. andKappas, M. (2017) ‘Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery’, Sensors (Basel, Switzerland), 18(1). doi: 10.3390/s18010018.
Thomas, J. W. andWard, K. (2006) ‘Economic profiling of physician specialists: Use of outlier treatment and episode attribution rules’, Inquiry, 43(3), pp. 271–282. doi: 10.5034/inquiryjrnl_43.3.271.
Tilstone, G. H. et al. (2021) ‘Performance of Ocean Colour Chlorophyll a algorithms for Sentinel-3 OLCI, MODIS-Aqua and Suomi-VIIRS in open-ocean waters of the Atlantic’, Remote Sensing of Environment. Elsevier Inc., 260(May), p. 112444. doi: 10.1016/j.rse.2021.112444.
Toming, K. et al. (2016) ‘First experiences in mapping lakewater quality parameters with sentinel-2 MSI imagery’, Remote Sensing, 8(8), pp. 1–14. doi: 10.3390/rs8080640.
U.S. Environmental Protection Agency (2009) ‘National Lakes Assessment: a collaborative survey of the Nation’s lakes.’, US Environmental Protection Agency, (Epa 841-R-09-001), p. 103.
UNEP (2014) ‘Review of existing water quality guidelines for freshwater ecosystems and application of water quality guidelines on basin level to protect ecosystems’, (November), p. 81.
USGS (2018) Turbidity and Water, Water Science School. Available at: https://www.usgs.gov/special-topics/water-science-school/science/turbidity-and-water.
Vanhellemont, Q. andRuddick, K. (2016) ‘Acolite for Sentinel-2: Aquatic applications of MSI imagery’, European Space Agency, (Special Publication) ESA SP, SP-740(May), pp. 9–13.
Wady, S. M. A. et al. (2020) ‘A new IHS and wavelet based pansharpening algorithm for high spatial resolution satellite imagery’, Advances in Space Research. COSPAR, 66(7), pp. 1507–1521. doi: 10.1016/j.asr.2020.06.001.
Wan, K.-M. (2013) ‘Forthcoming in the Critical Finance Review’, pp. 1–71.
Wang, L. et al. (2020) ‘Mapping freshwater chlorophyll-a concentrations at a regional scale integrating multi-sensor satellite observations with google earth engine’, Remote Sensing, 12(20), pp. 1–18. doi: 10.3390/rs12203278.
Wang, Q. andAtkinson, P. M. (2018) ‘Spatio-temporal fusion for daily Sentinel-2 images’, Remote Sensing of Environment. Elsevier, 204(April 2017), pp. 31–42. doi: 10.1016/j.rse.2017.10.046.
Wang, X. et al. (2019) ‘Unsupervised Sub-pixel water body mapping with sentinel-3 OLCI image’, Remote Sensing, 11(3). doi: 10.3390/rs11030327.
William Cartwright et al. (2014) Principle and Application Progress in Location-Based Services.
Willmott, C. J. andMatsuura, K. (2005) ‘Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance’, Climate Research, 30(1), pp. 79–82. doi: 10.3354/cr030079.
Wolters, E. et al. (2021) ‘iCOR Atmospheric Correction on Sentinel-3 / OLCI over Land : Intercomparison with AERONET, RadCalNet, and SYN Level-2’.
Xu, Q. et al. (2014) ‘High-fidelity component substitution pansharpening by the fitting of substitution data’, IEEE Transactions on Geoscience and Remote Sensing, 52(11), pp. 7380–7392. doi: 10.1109/TGRS.2014.2311815.
Yacobi, Y. Z. et al. (2011) ‘NIR-red reflectance-based algorithms for chlorophyll-a estimation in mesotrophic inland and coastal waters: Lake Kinneret case study’, Water Research. Elsevier Ltd, 45(7), pp. 2428–2436. doi: 10.1016/j.watres.2011.02.002.
Yajima, H. andDerot, J. (2018) ‘Application of the Random Forest model for chlorophyll-a forecasts in fresh and brackish water bodies in Japan, using multivariate long-term databases’, Journal of Hydroinformatics, 20(1), pp. 191–205. doi: 10.2166/hydro.2017.010.
Yang, Z. andAnderson, Y. (2016) ‘Estimating Chlorophyll-A Concentration in a Freshwater Lake Using Landsat 8 Imagery’, Journal of Environment and Earth Science, 6(4), pp. 134–142.
Zhao, Y. andZhang, Y. (2008) ‘Comparison of decision tree methods for finding active objects’, Advances in Space Research, 41(12), pp. 1955–1959. doi: 10.1016/j.asr.2007.07.020.