Satellite Retrievals of Karenia brevis Harmful Algal Blooms in the West Florida Shelf Using Neural Networks and Comparisons with Other Techniques

We describe the application of a Neural Network (NN) previously developed by us, to the detection and tracking, of Karenia brevis Harmful Algal Blooms (KB HABs) that plague the coasts of the West Florida Shelf (WFS) using Visible Infrared Imaging Radiometer Suite (VIIRS) satellite observations. Previous approaches for the detection of KB HABs in the WFS primarily used observations from the Moderate Resolution Imaging Spectroradiometer Aqua (MODIS-A) satellite. They depended on the remote sensing reflectance signal at the 678 nm chlorophyll fluorescence band (Rrs678) needed for both the normalized fluorescence height (nFLH) and Red Band Difference algorithms (RBD) currently used. VIIRS which has replaced MODIS-A, unfortunately does not have a 678 nm fluorescence channel so we customized the NN approach to retrieve phytoplankton absorption at 443 nm (aph443) using only Rrs measurements from existing VIIRS channels at 486, 551 and 671 nm. The aph443 values in these retrieved VIIRS images, can in turn be correlated to chlorophyll-a concentrations [Chla] and KB cell counts. To retrieve KB values, the VIIRS NN retrieved aph443 images are filtered by applying limiting constraints, defined by (i) low backscatter at Rrs 551 nm and (ii) a minimum aph443 value known to be associated with KB HABs in the WFS. The resulting filtered residual images, are then used to delineate and quantify the existing KB HABs. Comparisons with KB HABs satellite retrievals obtained using other techniques, including nFLH, as well as with in situ measurements reported over a four year period, confirm the viability of the NN technique, when combined with the filtering constraints devised, for effective detection of KB HABs.

[1]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[2]  R. Arnone,et al.  Deriving inherent optical properties from water color: a multiband quasi-analytical algorithm for optically deep waters. , 2002, Applied optics.

[3]  A. El-habashi,et al.  Neural network algorithms for retrieval of harmful algal blooms in the west Florida shelf from VIIRS satellite observations and comparisons with other techniques, without the need for a fluorescence channel , 2015, SPIE Remote Sensing.

[4]  Richard P. Stumpf,et al.  Remote Sensing of Harmful Algal Blooms , 2007 .

[5]  S. Ramos,et al.  Harmful Algal Blooms of the West Florida Shelf and Campeche Bank: Visualization and Quantification using Remote Sensing Methods , 2013 .

[6]  R. Litaker,et al.  Relationships among water column toxins, cell abundance and chlorophyll concentrations during Karenia brevis blooms , 2008 .

[7]  Roland Doerffer,et al.  Neural network for emulation of an inverse model: operational derivation of Case II water properties from MERIS data , 1999 .

[8]  I. Ioannou,et al.  Neural network approach to retrieve the inherent optical properties of the ocean from observations of MODIS. , 2011, Applied optics.

[9]  K. Mahoney,et al.  Backscattering of light by Karenia brevis and implications for optical detection and monitoring , 2003 .

[10]  S. Thiria,et al.  Artificial neural networks for modeling the transfer function between marine reflectance and phytoplankton pigment concentration , 2000 .

[11]  Fred Moshary,et al.  MODIS and MERIS detection of dinoflagellates blooms using the RBD technique , 2009, Remote Sensing.

[12]  P. J. Werdell,et al.  An improved in-situ bio-optical data set for ocean color algorithm development and satellite data product validation , 2005 .

[13]  Jennifer P. Cannizzaro,et al.  A novel technique for detection of the toxic dinoflagellate, Karenia brevis, in the Gulf of Mexico from remotely sensed ocean color data , 2008 .

[14]  Menghua Wang,et al.  Remote Sensing of Inherent Optical Properties : Fundamentals , 2009 .

[15]  R. P. Stumpfa,et al.  Monitoring Karenia brevis blooms in the Gulf of Mexico using satellite ocean color imagery and other data , 2003 .

[16]  Bryan A. Franz,et al.  Satellite-detected fluorescence reveals global physiology of ocean phytoplankton , 2008 .

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

[18]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[19]  Roland Doerffer,et al.  Improved determination of coastal water constituent concentrations from MERIS data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[20]  H. Claustre,et al.  Variability in the chlorophyll‐specific absorption coefficients of natural phytoplankton: Analysis and parameterization , 1995 .

[21]  Chengfeng Le,et al.  A hybrid approach to estimate chromophoric dissolved organic matter in turbid estuaries from satellite measurements: a case study for Tampa Bay. , 2013, Optics express.

[22]  A. Morel.  Optical properties of pure water and pure sea water , 1974 .

[23]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[24]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[25]  R. Bukata,et al.  Optical Properties and Remote Sensing of Inland and Coastal Waters , 1995 .

[26]  K. Ruddick,et al.  Detecting algae blooms in European waters , 2007 .

[27]  T. Wynne,et al.  An evaluation of remote sensing techniques for enhanced detection of the toxic dinoflagellate, Karenia brevis , 2009 .

[28]  Menghua Wang,et al.  Seawifs Postlaunch Calibration and Validation Analyses , 2013 .

[29]  Lin Qi,et al.  A Harmful Algal Bloom of Karenia brevis in the Northeastern Gulf of Mexico as Revealed by MODIS and VIIRS: A Comparison , 2015, Sensors.

[30]  K. Moffett,et al.  Remote Sens , 2015 .

[31]  D. Anderson.  Harmful Algal Blooms and Ocean Observing Systems: Needs, Present Status and Future Potential , 2008 .

[32]  Bryan A. Franz,et al.  Chlorophyll aalgorithms for oligotrophic oceans: A novel approach based on three‐band reflectance difference , 2012 .

[33]  F. Muller‐Karger,et al.  Red tide detection and tracing using MODIS fluorescence data: A regional example in SW Florida coastal waters , 2005 .

[34]  A. Bricaud,et al.  Modeling the inherent optical properties of the ocean based on the detailed composition of the planktonic community. , 2001, Applied optics.

[35]  I. Ioannou,et al.  Fluorescence component in the reflectance spectra from coastal waters. II. Performance of retrieval algorithms. , 2008, Optics express.

[36]  I. Jenkinson,et al.  Harmful algal blooms , 1993, The Lancet.

[37]  John J. Cullen,et al.  Assessment of the relationships between dominant cell size in natural phytoplankton communities and the spectral shape of the absorption coefficient , 2002 .

[38]  Dmitry B. Goldgof,et al.  Evaluation and optimization of remote sensing techniques for detection of Karenia brevis blooms on the West Florida Shelf , 2015 .

[39]  Filipe Aires,et al.  Neural Network Uncertainty Assessment Using Bayesian Statistics: A Remote Sensing Application , 2004, Neural Computation.

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

[41]  E. Fry,et al.  Absorption spectrum (380-700 nm) of pure water. II. Integrating cavity measurements. , 1997, Applied optics.

[42]  Richard P. Stumpf,et al.  Evaluation of the use of SeaWiFS imagery for detecting Karenia brevis harmful algal blooms in the eastern Gulf of Mexico , 2004 .

[43]  Kaveh Bastani,et al.  Remote estimation of in water constituents in coastal waters using neural networks , 2014, Remote Sensing.

[44]  James W. Brown,et al.  A semianalytic radiance model of ocean color , 1988 .

[45]  Lin Qi,et al.  VIIRS Observations of a Karenia brevis Bloom in the Northeastern Gulf of Mexico in the Absence of a Fluorescence Band , 2015, IEEE Geoscience and Remote Sensing Letters.

[46]  T. Wynne,et al.  Detecting Karenia brevis blooms and algal resuspension in the western Gulf of mexico with satellite ocean color imagery , 2005 .

[47]  A. Gilerson,et al.  Novel optical techniques for detecting and classifying toxic dinoflagellate Karenia brevis blooms using satellite imagery. , 2009, Optics express.

[48]  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 .

[49]  Richard P Stumpf,et al.  Skill assessment for an operational algal bloom forecast system. , 2009, Journal of marine systems : journal of the European Association of Marine Sciences and Techniques.

[50]  S. Maritorena,et al.  Bio-optical properties of oceanic waters: A reappraisal , 2001 .

[51]  Kendall L. Carder,et al.  Detection of Karenia Brevis Blooms on the West Florida Shelf Using in Situ Backscattering and Fluorescence Data , 2009 .

[52]  Kevin Winter,et al.  Remote sensing of cyanobacteria-dominant algal blooms and water quality parameters in Zeekoevlei, a small hypertrophic lake, using MERIS , 2010 .

[53]  Zhongping Lee,et al.  Use of hyperspectral remote sensing reflectance for detection and assessment of the harmful alga, Karenia brevis. , 2006, Applied optics.

[54]  Ricardo M Letelier,et al.  An analysis of chlorophyll fluorescence algorithms for the moderate resolution imaging spectrometer (MODIS) , 1996 .

[55]  Lora E Fleming,et al.  Satellite remote sensing of harmful algal blooms: A new multi-algorithm method for detecting the Florida Red Tide (Karenia brevis). , 2010, Harmful algae.

[56]  I. Ioannou,et al.  Deriving ocean color products using neural networks , 2013 .

[57]  F. Aires,et al.  A new neural network approach including first guess for retrieval of atmospheric water vapor, cloud liquid water path, surface temperature, and emissivities over land from satellite microwave observations , 2001 .

[58]  M. He,et al.  Evaluating the performance of artificial neural network techniques for pigment retrieval from ocean color in Case I waters , 2003 .

[59]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[60]  Dariusz Stramski,et al.  Light scattering properties of marine particles in coastal and open ocean waters as related to the particle mass concentration , 2003 .

[61]  P. Minnett,et al.  Long-term evaluation of three satellite ocean color algorithms for identifying harmful algal blooms (Karenia brevis) along the west coast of Florida: A matchup assessment. , 2011, Remote sensing of environment.

[62]  K. Carder,et al.  A remote‐sensing reflectance model of a red‐tide dinoflagellate off west Florida1 , 1985 .

[63]  Richard P. Stumpf,et al.  Applications of Satellite Ocean Color Sensors for Monitoring and Predicting Harmful Algal Blooms , 2001 .

[64]  A. Morel.  Optical modeling of the upper ocean in relation to its biogenous matter content (case I waters) , 1988 .

[65]  I. Ioannou,et al.  Fluorescence component in the reflectance spectra from coastal waters. Dependence on water composition. , 2007, Optics express.