A spectral space partition guided ensemble method for retrieving chlorophyll-a concentration in inland waters from Sentinel-2A satellite imagery

Abstract This research proposes an ensemble method for synergistically combining multiple empirical algorithms to better estimate chlorophyll-a (Chl-a) concentration. In previous studies, different empirical algorithms have been employed separately and a single algorithm was often identified as the most suitable predictor for Chl-a retrieval. Our ensemble method combines different individual algorithms to form an ensemble predictor that exploits advantages of each individual algorithm to maximize the overall estimation accuracy. We evaluated two ensemble predictors: the optimally weighted ensemble predictor and the spectral space partition guided ensemble predictor. The ensemble method has been successfully applied to a Sentinel-2A multispectral image acquired over Harsha Lake, Ohio in 2016. Based on in situ water reference data and satellite imagery, we constructed two ensemble predictors that consist of three individual empirical algorithms/estimators, including 2BDA (two-band algorithm), 3BDA (three-band algorithm), and NDCI (Normalized Difference Chlorophyll Index). For the optimally weighted ensemble predictor, the weights for individual algorithms are computed by solving an overdetermined linear system with the pseudoinverse technique. For the spectral space partition guided ensemble predictor, the rules for partitioning spectral space into spectral regions were established as a decision-tree using the CART method. The optimal Chl-a estimate for a pixel is obtained by selectively using the empirical algorithm in the ensemble that has the highest expected accuracy in the spectral region where the pixel is located. Our assessments suggest that the spectral space partition guided ensemble method performs significantly better than three individual empirical algorithms and also better than the optimally weighted ensemble method.

[1]  A. Goetz,et al.  Atmospheric correction algorithms for hyperspectral remote sensing data of land and ocean , 2009 .

[2]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[3]  M. Bauer,et al.  Remote Sensing for Regional Lake Water Quality Assessment: Capabilities and Limitations of Current and Upcoming Satellite Systems , 2015 .

[4]  M. Bauer,et al.  A 20-year Landsat water clarity census of Minnesota's 10,000 lakes , 2008 .

[5]  M. Bauer,et al.  Landsat-based Remote Sensing of Lake Water Quality Characteristics, Including Chlorophyll and Colored Dissolved Organic Matter (CDOM) , 2005 .

[6]  R. Vincent,et al.  Phycocyanin detection from LANDSAT TM data for mapping cyanobacterial blooms in Lake Erie , 2004 .

[7]  Ariel Dinar,et al.  Integrated lake and reservoir management: World Bank approach and experience. , 1997 .

[8]  M. Kahru,et al.  Ocean Color Chlorophyll Algorithms for SEAWIFS , 1998 .

[9]  Lino Augusto Sander de Carvalho,et al.  Assessment of Atmospheric Correction Methods for Sentinel-2 MSI Images Applied to Amazon Floodplain Lakes , 2017, Remote. Sens..

[10]  Yong Q. Tian,et al.  Remote estimation of colored dissolved organic matter and chlorophyll-a in Lake Huron using Sentinel-2 measurements , 2017 .

[11]  Tiit Kutser,et al.  Passive optical remote sensing of cyanobacteria and other intense phytoplankton blooms in coastal and inland waters , 2009 .

[12]  Paul V. Zimba,et al.  Remote Sensing Techniques to Assess Water Quality , 2003 .

[13]  Min Chen,et al.  A Weighted Algorithm Based on Normalized Mutual Information for Estimating the Chlorophyll-a Concentration in Inland Waters Using Geostationary Ocean Color Imager (GOCI) Data , 2015, Remote. Sens..

[14]  M. Griffin,et al.  Compensation of Hyperspectral Data for Atmospheric Effects , 2003 .

[15]  J. Downing,et al.  Plumbing the Global Carbon Cycle: Integrating Inland Waters into the Terrestrial Carbon Budget , 2007, Ecosystems.

[16]  R. Bukata.  Retrospection and introspection on remote sensing of inland water quality: “Like Déjà Vu All Over Again” , 2013 .

[17]  Tiit Kutser,et al.  Remote Sensing of Black Lakes and Using 810 nm Reflectance Peak for Retrieving Water Quality Parameters of Optically Complex Waters , 2016, Remote. Sens..

[18]  M. Schaepman,et al.  Review of constituent retrieval in optically deep and complex waters from satellite imagery , 2012 .

[19]  E. Milton,et al.  The use of the empirical line method to calibrate remotely sensed data to reflectance , 1999 .

[20]  Anas El-Alem,et al.  An Adaptive Model to Monitor Chlorophyll-a in Inland Waters in Southern Quebec Using Downscaled MODIS Imagery , 2014, Remote. Sens..

[21]  Lars-Anders Hansson,et al.  Environmental issues in lakes and ponds: current state and perspectives , 2002, Environmental Conservation.

[22]  Tiit Kutser,et al.  First Experiences in Mapping Lake Water Quality Parameters with Sentinel-2 MSI Imagery , 2016, Remote. Sens..

[23]  Alexander A Gilerson,et al.  Algorithms for remote estimation of chlorophyll-a in coastal and inland waters using red and near infrared bands. , 2010, Optics express.

[24]  Stephanie C. J. Palmer,et al.  Remote sensing of inland waters: Challenges, progress and future directions , 2015 .

[25]  Lawrence S. Bernstein,et al.  Quick atmospheric correction code: algorithm description and recent upgrades , 2012 .

[26]  Arve Kylling,et al.  The libRadtran software package for radiative transfer calculations (version 2.0.1) , 2015 .

[27]  A. Gitelson,et al.  A simple semi-analytical model for remote estimation of chlorophyll-a in turbid waters: Validation , 2008 .

[28]  Qingquan Li,et al.  Application of Sentinel 2 MSI Images to Retrieve Suspended Particulate Matter Concentrations in Poyang Lake , 2017, Remote. Sens..

[29]  Lorenzo Bruzzone,et al.  Robust multiple estimator systems for the analysis of biophysical parameters from remotely sensed data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[30]  C. Verpoorter,et al.  A global inventory of lakes based on high‐resolution satellite imagery , 2014 .

[31]  Mohamed Sultan,et al.  Mapping Cyanobacterial Blooms in the Great Lakes Using MODIS , 2009 .

[32]  B. Osborne,et al.  Light and Photosynthesis in Aquatic Ecosystems. , 1985 .

[33]  Jennifer P. Cannizzaro,et al.  Estimating chlorophyll a concentrations from remote-sensing reflectance in optically shallow waters , 2006 .

[34]  Bo Yang,et al.  Comparison of Satellite Reflectance Algorithms for Estimating Phycocyanin Values and Cyanobacterial Total Biovolume in a Temperate Reservoir Using Coincident Hyperspectral Aircraft Imagery and Dense Coincident Surface Observations , 2017, Remote. Sens..

[35]  C. Mobley.  Light and Water: Radiative Transfer in Natural Waters , 1994 .

[36]  Susanna T. Y. Tong,et al.  Comparison of satellite reflectance algorithms for estimating chlorophyll-a in a temperate reservoir using coincident hyperspectral aircraft imagery and dense coincident surface observations , 2016 .

[37]  Chuanmin Hu.  A novel ocean color index to detect floating algae in the global oceans , 2009 .

[38]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[39]  Rich Caruana,et al.  Ensemble selection from libraries of models , 2004, ICML.

[40]  T. Johengen,et al.  An algorithm to retrieve chlorophyll, dissolved organic carbon, and suspended minerals from Great Lakes satellite data , 2013 .

[41]  David G. Stork,et al.  Pattern Classification , 1973 .

[42]  Jeffery A Steevens,et al.  Are harmful algal blooms becoming the greatest inland water quality threat to public health and aquatic ecosystems? , 2016, Environmental toxicology and chemistry.

[43]  Patrick M. Crill,et al.  Freshwater Methane Emissions Offset the Continental Carbon Sink , 2011, Science.

[44]  R. Wetzel.  Limnology: Lake and River Ecosystems , 1975 .

[45]  Anatoly A. Gitelson,et al.  The peak near 700 nm on radiance spectra of algae and water: relationships of its magnitude and position with chlorophyll concentration , 1992 .

[46]  S. Phinn,et al.  A review of ocean color remote sensing methods and statistical techniques for the detection, mapping and analysis of phytoplankton blooms in coastal and open oceans , 2014 .

[47]  M. Matthews.  A current review of empirical procedures of remote sensing in inland and near-coastal transitional waters , 2011 .

[48]  Christopher T. Nietch,et al.  Denitrification alternates between a source and sink of nitrous oxide in the hypolimnion of a thermally stratified reservoir , 2014 .

[49]  S. Postel.  Entering an era of water scarcity: the challenges ahead. , 2000 .