Developing a New Machine-Learning Algorithm for Estimating Chlorophyll-a Concentration in Optically Complex Waters: A Case Study for High Northern Latitude Waters by Using Sentinel 3 OLCI

The monitoring of Chlorophyll-a (Chl-a) concentration in high northern latitude waters has been receiving increased focus due to the rapid environmental changes in the sub-Arctic, Arctic. Spaceborne optical instruments allow the continuous monitoring of the occurrence, distribution, and amount of Chl-a. In recent years, the Ocean and Land Color Instruments (OLCI) onboard the Sentinel 3 (S3) A and B satellites were launched, which provide data about various aquatic environments on advantageous spatial, spectral, and temporal resolutions with high SNR. Although S3 OLCI could be favorable to monitor high northern latitude waters, there have been several challenges related to Chl-a concentration retrieval in these waters due to their unique optical properties coupled with challenging environments including high sun zenith angle, presence of sea ice, and frequent cloud covers. In this work, we aim to overcome these difficulties by developing a machine-learning (ML) approach designed to estimate Chl-a concentration from S3 OLCI data in high northern latitude optically complex waters. The ML model is optimized and requires only three S3 OLCI bands, reflecting the physical characteristic of Chl-a as input in the regression process to estimate Chl-a concentration with improved accuracy in terms of the bias (five times improvements.) The ML model was optimized on data from Arctic, coastal, and open waters, and showed promising performance. Finally, we present the performance of the optimized ML approach by computing Chl-a maps and corresponding certainty maps in highly complex sub-Arctic and Arctic waters. We show how these certainty maps can be used as a support to understand possible radiometric calibration issues in the retrieval of Level 2 reflectance over these waters. This can be a useful tool in identifying erroneous Level 2 Remote sensing reflectance due to possible failure of the atmospheric correction algorithm.

[1]  Katalin Blix,et al.  A Generalized Chlorophyll-A Estimation Model for Complexity-Diverse Arctic Waters , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[2]  M. Babin,et al.  Northward Expansion and Intensification of Phytoplankton Growth During the Early Ice‐Free Season in Arctic , 2018, Geophysical Research Letters.

[3]  Torbjørn Eltoft,et al.  Remote Sensing of Water Quality Parameters over Lake Balaton by Using Sentinel-3 OLCI , 2018, Water.

[4]  I. Laurion,et al.  Increasing dominance of terrigenous organic matter in circumpolar freshwaters due to permafrost thaw , 2018 .

[5]  Torbjørn Eltoft,et al.  Machine Learning Automatic Model Selection Algorithm for Oceanic Chlorophyll-a Content Retrieval , 2018, Remote. Sens..

[6]  Katalin Blix,et al.  Evaluation of Feature Ranking and Regression Methods for Oceanic Chlorophyll-a Estimation , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[7]  Nilton Nobuhiro Imai,et al.  Estimation of Chlorophyll-a Concentration from Optimizing a Semi-Analytical Algorithm in Productive Inland Waters , 2018, Remote. Sens..

[8]  E. Boss,et al.  Pan-Arctic optical characteristics of colored dissolved organic matter: Tracing dissolved organic carbon in changing Arctic waters using satellite ocean color data , 2017 .

[9]  K. Stamnes,et al.  Atmospheric correction over coastal waters using multilayer neural networks , 2017 .

[10]  E. Hawkins,et al.  Towards seasonal Arctic shipping route predictions , 2017 .

[11]  Jean-Michel Martinez,et al.  Assessment of Chlorophyll-a Remote Sensing Algorithms in a Productive Tropical Estuarine-Lagoon System , 2017, Remote. Sens..

[12]  R. Doerffer,et al.  The OLCI Neural Network Swarm (ONNS): A Bio-Geo-Optical Algorithm for Open Ocean and Coastal Waters , 2017, Front. Mar. Sci..

[13]  Robert Jenssen,et al.  Gaussian Process Sensitivity Analysis for Oceanic Chlorophyll Estimation , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Carsten Brockmann,et al.  Evolution of the C2RCC Neural Network for Sentinel 2 and 3 for the Retrieval of Ocean Colour Products in Normal and Extreme Optically Complex Waters , 2016 .

[15]  Zhihao Qin,et al.  Estimating crop chlorophyll content with hyperspectral vegetation indices and the hybrid inversion method , 2016 .

[16]  L. Rainville,et al.  Recent Arctic Ocean sea ice loss triggers novel fall phytoplankton blooms , 2014 .

[17]  Jeffrey R. Key,et al.  Arctic sea ice in transformation: A review of recent observed changes and impacts on biology and human activity , 2014 .

[18]  E. Stewart,et al.  Governance of Arctic expedition cruise ships in a time of rapid environmental and economic change , 2014 .

[19]  Philippe Massicotte,et al.  Spatial and temporal evolution of the St. Lawrence River spectral profile: A 25-year case study using Landsat 5 and 7 imagery , 2013 .

[20]  A. Matsuoka,et al.  Apparent optical properties of the Canadian Beaufort Sea – Part 2: The 1% and 1 cm perspective in deriving and validating AOP data products , 2013 .

[21]  Tyler Volk,et al.  Ocean Carbon Pumps: Analysis of Relative Strengths and Efficiencies in Ocean‐Driven Atmospheric CO2 Changes , 2013 .

[22]  Ove T. Gudmestad,et al.  Evacuation from Petroleum Facilities Operating in the Barents Sea , 2012 .

[23]  Luis Alonso,et al.  Retrieval of Vegetation Biophysical Parameters Using Gaussian Process Techniques , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[24]  Luis Alonso,et al.  Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3 , 2012 .

[25]  Hans Joachim Schellnhuber,et al.  Declining ocean chlorophyll under unabated anthropogenic CO2 emissions , 2011 .

[26]  O. Johannessen,et al.  Critical vulnerabilities of marine and sea ice–based ecosystems in the high Arctic , 2011 .

[27]  James W. Brown,et al.  Advances in Measuring the Apparent Optical Properties (AOPs) of Optically Complex Waters , 2010 .

[28]  Ziauddin Ahmad,et al.  New aerosol models for the retrieval of aerosol optical thickness and normalized water-leaving radiances from the SeaWiFS and MODIS sensors over coastal regions and open oceans. , 2010, Applied optics.

[29]  Farid Melgani,et al.  Gaussian Process Regression for Estimating Chlorophyll Concentration in Subsurface Waters From Remote Sensing Data , 2010, IEEE Geoscience and Remote Sensing Letters.

[30]  Luis Gómez-Chova,et al.  Biophysical Parameter Estimation With a Semisupervised Support Vector Machine , 2009, IEEE Geoscience and Remote Sensing Letters.

[31]  Pierre Larouche,et al.  An empirical ocean color algorithm for estimating the contribution of chromophoric dissolved organic matter to total light absorption in optically complex waters , 2008 .

[32]  André Morel,et al.  Natural variability of bio-optical properties in Case 1 waters: attenuation and reflectance within the visible and near-UV spectral domains, as observed in South Pacific and Mediterranean waters , 2007 .

[33]  H. Claustre,et al.  Spatial variability of phytoplankton pigment distributions in the Subtropical South Pacific Ocean: comparison between in situ and predicted data , 2007 .

[34]  B. Jena,et al.  Validation of integrated potential fishing zone (IPFZ) forecast using satellite based chlorophyll and sea surface temperature along the east coast of India , 2007 .

[35]  R. Doerffer,et al.  The MERIS Case 2 water algorithm , 2007 .

[36]  Gustavo Camps-Valls,et al.  Retrieval of oceanic chlorophyll concentration with relevance vector machines , 2006 .

[37]  P. J. Werdell,et al.  A multi-sensor approach for the on-orbit validation of ocean color satellite data products , 2006 .

[38]  Giuseppe Zibordi,et al.  Comparison of SeaWiFS, MODIS and MERIS radiometric products at a coastal site , 2006 .

[39]  Giulietta S. Fargion,et al.  Application of machine-learning techniques toward the creation of a consistent and calibrated global chlorophyll concentration baseline dataset using remotely sensed ocean color data , 2003, IEEE Trans. Geosci. Remote. Sens..

[40]  Ping Shi,et al.  Retrieval of oceanic chlorophyll concentration using support vector machines , 2003, IEEE Trans. Geosci. Remote. Sens..

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

[42]  Else Nøst Hegseth,et al.  Spatial variability of chlorophyll-a in the Marginal Ice Zone of the Barents Sea, with relations to sea ice and oceanographic conditions , 2002 .

[43]  Marco Diani,et al.  Retrieval of sea water optically active parameters from hyperspectral data by means of generalized radial basis function neural networks , 2001, IEEE Trans. Geosci. Remote. Sens..

[44]  Crystal S. Thomas,et al.  Computer-assisted high-performance liquid chromatography method development with applications to the isolation and analysis of phytoplankton pigments. , 2001, Journal of chromatography. A.

[45]  D. H. Robinson,et al.  Phytoplankton community structure and the drawdown of nutrients and CO2 in the southern ocean , 1999, Science.

[46]  K. Sand‐Jensen,et al.  CO2 increases oceanic primary production , 1997, Nature.

[47]  H. Gordon,et al.  Influence of oceanic whitecaps on atmospheric correction of ocean-color sensors. , 1994, Applied optics.

[48]  H. Gordon,et al.  Self‐shading of in‐water optical instruments , 1992 .

[49]  Надежда Всеволодовна Коваленко,et al.  АНАЛИЗ ЗНАЧЕНИЙ АЛЬБЕДО ЛЕДНИКОВ КИРГИЗИИ ПО КОСМИЧЕСКИМ СНИМКАМ SENTINEL-2 MSI , 2019 .

[50]  K. Stamnes,et al.  Neural network method to correct bidirectional effects in water-leaving radiance. , 2016, Applied optics.

[51]  M. Tennyson,et al.  Circum-arctic resource appraisal: Estimates of undiscovered oil and gas north of the Arctic Circle , 2008 .

[52]  M. Armenteros,et al.  Digital Commons @ University of Digital Commons @ University of South Florida South Florida , 2022 .