Remote sensing of chlorophyll-a concentration for drinking water source using genetic algorithms (GA)-partial least square (PLS) modeling

Abstract Accurate estimation of phytoplankton chlorophyll-a (Chl- a ) concentration in turbid waters through remote sensing is a challenge due to the optical complexity of water constituents. Reflectance spectra and concurrent water quality parameters of 225 samples across the Shitoukoumen Reservoir, the drinking water resource for Changchun City, were used to retrieve Chl -a concentration with high total suspended matter (TSM) during 2006–2008. A combination of genetic algorithms and partial least square (GA-PLS) model was established for Chl -a retrieval through GA to select sensitive spectral variables and PLS for regression. To compare GA-PLS performances, the widely accepted three-band algorithm was implemented for Chl -a concentration estimation. Both GA-PLS and the three-band algorithm have stable performance for the aggregated dataset (R 2  = 0.85 and 0.81; RPD = 3.95 and 3.61; relative RMSE = 31.7% and 34.2%), with the GA-PLS model performing marginally better. The temporal transferability of the models was validated with the dataset collected in 2006 and 2007 respectively as independent dataset, showing that GA-PLS outperformed the three-band algorithm. Our result also indicated that relative error [(Chl-a predicted  − Chl-a measured ) / Chl-a measured ] showed good linear relation to TSM: Chl- a ratio (R 2  = 0.84), which implied that TSM concentration exerted significant impact on the accuracy of Chl- a estimation in this case study. As the results were derived from a large number of samples representing a wide range of spatiotemporal variations of pigment under TSM (3.7–472.8 mg/L) concentration influence, the GA-PLS model has great potential for Chl -a estimation for inland waters with similar backgrounds. Nevertheless, the three-band algorithm also has its own merit considering its simplicity for implementation.

[1]  André Morel,et al.  Bio-Optical Models* , 2001 .

[2]  Tami C. Bond,et al.  Spectral absorption properties of atmospheric aerosols , 2007 .

[3]  Alan Weidemann,et al.  Phytoplankton spectral absorption as influenced by community size structure and pigment composition , 2003 .

[4]  J. Pulliainen,et al.  Retrieval of water quality from airborne imaging spectrometry of various lake types in different seasons. , 2001, The Science of the total environment.

[5]  H. Paerl,et al.  Climate change: a catalyst for global expansion of harmful cyanobacterial blooms. , 2009, Environmental microbiology reports.

[6]  A. Gitelson,et al.  Estimation of chlorophyll-a concentration in estuarine waters: case study of the Pearl River estuary, South China Sea , 2011 .

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

[8]  Bruce R. Forsberg,et al.  Relationships among nitrogen and total phosphorus, algal biomass and zooplankton density in the central Amazonia lakes , 2007, Hydrobiologia.

[9]  L. Prieur,et al.  Analysis of variations in ocean color1 , 1977 .

[10]  Anatoly A. Gitelson,et al.  Estimation of chlorophyll-a concentration in case II waters using MODIS and MERIS data—successes and challenges , 2009 .

[11]  Annick Bricaud,et al.  Estimation of new primary production in the Benguela upwelling area, using ENVISAT satellite data and a model dependent on the phytoplankton community size structure , 2008 .

[12]  Bunkei Matsushita,et al.  Estimating constituent concentrations in case II waters from MERIS satellite data by semi-analytical model optimizing and look-up tables , 2011 .

[13]  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.

[14]  Luoheng Han,et al.  Estimating chlorophyll‐a concentration using first‐derivative spectra in coastal water , 2005 .

[15]  I. V. Carranzo,et al.  APHA, AWWA, WEF. "Standard Methods for examination of water and wastewater." , 2012 .

[16]  Machteld Rijkeboer,et al.  Effect of a Waveband Shift on Chlorophyll Retrieval from MERIS Imagery of Inland and Coastal Waters , 2004 .

[17]  Yunpeng Wang,et al.  Water quality change in reservoirs of Shenzhen, China: detection using LANDSAT/TM data. , 2004, The Science of the total environment.

[18]  Donald C. Rundquist,et al.  Comparison of NIR/RED ratio and first derivative of reflectance in estimating algal-chlorophyll concentration: A case study in a turbid reservoir , 1997 .

[19]  Vittorio E. Brando,et al.  Satellite hyperspectral remote sensing for estimating estuarine and coastal water quality , 2003, IEEE Trans. Geosci. Remote. Sens..

[20]  H. Gons,et al.  MERIS satellite chlorophyll mapping of oligotrophic and eutrophic waters in the Laurentian Great Lakes , 2008 .

[21]  C. Mobley,et al.  Estimation of the remote-sensing reflectance from above-surface measurements. , 1999, Applied optics.

[22]  R. Leardi,et al.  Genetic algorithms applied to feature selection in PLS regression: how and when to use them , 1998 .

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

[24]  Bai Zhang,et al.  Estimation of chlorophyll-a concentration using field spectral data: a case study in inland Case-II waters, North China , 2009, Environmental monitoring and assessment.

[25]  Peter D. Hunter,et al.  Hyperspectral remote sensing of cyanobacterial pigments as indicators for cell populations and toxins in eutrophic lakes , 2010 .

[26]  Dan G. Cacuci,et al.  Sensitivity & Uncertainty Analysis, Volume 1: Theory , 2003 .

[27]  David Doxaran,et al.  Apparent and inherent optical properties of turbid estuarine waters: measurements, empirical quantification relationships, and modeling. , 2006, Applied optics.

[28]  Arnold G. Dekker,et al.  Detection of optical water quality parameters for eutrophic waters by high resolution remote sensing , 1993 .

[29]  E. V. Thomas,et al.  Partial least-squares methods for spectral analyses. 1. Relation to other quantitative calibration methods and the extraction of qualitative information , 1988 .

[30]  B Gentili,et al.  Diffuse reflectance of oceanic waters. II Bidirectional aspects. , 1993, Applied optics.

[31]  Paul J. Curran,et al.  Derivative Reflectance Spectroscopy to Estimate Suspended Sediment Concentration , 1992 .

[32]  W. T. Liu,et al.  Correction to “CO2 exchange coefficients from remotely sensed wind speed measurements: SSM/I versus QuikSCAT in 2000” by Mary‐Elena Carr, Wenqing Tang, and W. Timothy Liu , 2003 .

[33]  Kaishan Song,et al.  Spectral absorption properties of colored dissolved organic matter (CDOM) and total suspended matter (TSM) of inland waters , 2010, Optical Engineering + Applications.

[34]  H. Paerl,et al.  Blooms Like It Hot , 2008, Science.

[35]  P. Williams,et al.  Near-Infrared Technology in the Agricultural and Food Industries , 1987 .

[36]  J. Pulliainen,et al.  Application of an empirical neural network to surface water quality estimation in the Gulf of Finland using combined optical data and microwave data , 2002 .

[37]  Guangxin Zhang,et al.  Identifying key environmental factors influencing spatial variation of water quality in upper Shitoukoumen Reservoir Basin in Jilin Province, China , 2009 .

[38]  Giorgio Dall'Olmo,et al.  Effect of bio-optical parameter variability on the remote estimation of chlorophyll-a concentration in turbid productive waters: experimental results. , 2005, Applied optics.

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

[40]  Karl K. Turekian,et al.  Encyclopedia of Ocean Sciences , 2001 .

[41]  Deyong Sun,et al.  A Unified Model for Remotely Estimating Chlorophyll a in Lake Taihu, China, Based on SVM and In Situ Hyperspectral Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[42]  Xiao‐Hai Yan,et al.  A Neural Network Model for Estimating Sea Surface Chlorophyll and Sediments from Thematic Mapper Imagery , 1998 .

[43]  M A Arnold,et al.  Genetic algorithm-based wavelength selection for the near-infrared determination of glucose in biological matrixes: initialization strategies and effects of spectral resolution. , 1998, Analytical chemistry.

[44]  Lin Li,et al.  Using hyperspectral remote sensing to estimate chlorophyll‐a and phycocyanin in a mesotrophic reservoir , 2010 .

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

[46]  Anatoly A. Gitelson,et al.  Towards a unified approach for remote estimation of chlorophyll‐a in both terrestrial vegetation and turbid productive waters , 2003 .

[47]  H. Gordon,et al.  Computed relationships between the inherent and apparent optical properties of a flat homogeneous ocean. , 1975, Applied optics.

[48]  Donald C. Pierson,et al.  Manual for Monitoring European Lakes using Remote Sensing Techniques , 1999 .

[49]  D. Doxaran,et al.  Spectral signature of highly turbid waters: Application with SPOT data to quantify suspended particulate matter concentrations , 2002 .

[50]  Walker O. Smith,et al.  An evaluation of ocean color model estimates of marine primary productivity in coastal and pelagic regions across the globe , 2010 .

[51]  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 .

[52]  Machteld Rijkeboer,et al.  SHORT COMMUNICATION Effect of a waveband shift on chlorophyll retrieval from MERIS imagery of inland and coastal waters , 2005 .

[53]  Machteld Rijkeboer,et al.  A chlorophyll-retrieval algorithm for satellite imagery (Medium Resolution Imaging Spectrometer) of inland and coastal waters , 2002 .

[54]  H. Gons,et al.  Optical teledetection of chlorophyll a in turbid inland waters , 1999 .

[55]  Stefan G. H. Simis,et al.  Remote sensing of the cyanobacterial pigment phycocyanin in turbid inland water , 2005 .

[56]  D. Rundquist,et al.  The spectral responses of algal chlorophyll in water with varying levels of suspended sediment , 1994 .

[57]  John F. Schalles,et al.  Remote measurement of algal chlorophyll in surface waters: The case for the first derivative of reflectance near 690 nm , 1996 .

[58]  Dale A. Kiefer,et al.  Derivative analysis of spectral absorption by photosynthetic pigments in the western Sargasso Sea , 1989 .

[59]  Tim J. Malthus,et al.  The effect of spectral bandwidth and positioning on the spectral signature analysis of inland waters , 1992 .

[60]  David Doxaran,et al.  Spectral variations of light scattering by marine particles in coastal waters, from the visible to the near infrared , 2009 .

[61]  L. Backer,et al.  Cyanobacterial Harmful Algal Blooms (CyanoHABs): Developing a Public Health Response , 2002 .

[62]  S. Thiria,et al.  Retrieval of pigment concentrations and size structure of algal populations from their absorption spectra using multilayered perceptrons. , 2007, Applied optics.

[63]  William G. Booty,et al.  Spectral absorption properties of dissolved and particulate matter in Lake Erie , 2008 .

[64]  Riccardo Leardi,et al.  Application of genetic algorithm–PLS for feature selection in spectral data sets , 2000 .