A Unified Model for Remotely Estimating Chlorophyll a in Lake Taihu, China, Based on SVM and In Situ Hyperspectral Data

Accurate estimation of chlorophyll a (Chla) in inland turbid lake waters by means of remote sensing is a challenging task due to their optical complexity. In order to explore the best solution, we observed water quality parameters and measured water reflectance spectra in Lake Taihu for 14 days in November 2007. After initial wavelength analysis and iterative optimization, the best three-wavelength factor (TWF) was determined as [R rs -1(661) - R rs -1(691)] R rs(727). Linear models and a support vector machine (SVM) model with TWFs as the inputs were established for retrieving Chla concentration level. It is found that linear models with a single TWF performed worse than the SVM model. The SVM model is highly accurate, whose R 2 and root-mean-square error are 0.8961 and 2.67 mg/m3, respectively. Validation of the SVM model using data sets obtained at another sampling time reveals small errors. Thus, this model can be used to extract Chla concentration levels in Lake Taihu waters but is not restricted by the sampling time. These findings underline the rationale of the TWF model and demonstrate the robustness of the SVM algorithm for remotely estimating Chla in Lake Taihu waters.

[1]  Lorenzo Bruzzone,et al.  A Support Vector Domain Description Approach to Supervised Classification of Remote Sensing Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

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

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

[4]  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 .

[5]  Gu Xing.  COMPARISON OF LST RETRIEVAL PRECISION BETWEEN SINGLE-CHANNEL AND SPLIT-WINDOWS FOR HIGH-RESOLUTION INFRARED CAMERA , 2008 .

[6]  J. Schalles.  OPTICAL REMOTE SENSING TECHNIQUES TO ESTIMATE PHYTOPLANKTON CHLOROPHYLL a CONCENTRATIONS IN COASTAL , 2006 .

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

[8]  J. Schalles.  Optical remote sensing techniques to estimate phytoplankton chlorophyll a concentrations in coastal waters with varying suspended matter and cdom concentrations , 2006 .

[9]  B. G. Mitchell,et al.  Algorithms for determining the absorption coefficient for aquatic particulates using the quantitative filter technique , 1990, Defense, Security, and Sensing.

[10]  Jing-Ping Xu.  ESTIMATION OF CHLOROPHYLL-a CONCENTRATION IN LAKE XINMIAO BASED ON A SEMI-ANALYTICAL MODEL: ESTIMATION OF CHLOROPHYLL-a CONCENTRATION IN LAKE XINMIAO BASED ON A SEMI-ANALYTICAL MODEL , 2008 .

[11]  Anatoly A. Gitelson,et al.  Remote chlorophyll-a retrieval in turbid, productive estuaries : Chesapeake Bay case study , 2007 .

[12]  J. Gao,et al.  Estimation of chlorophyll‐a concentration in Lake Tai, China using in situ hyperspectral data , 2006 .

[13]  Anatoly A. Gitelson,et al.  Real-time quality monitoring by remote sensing of contaminated water-bodies: Waste stabilization pond effluent , 1996 .

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

[15]  H. Gordon,et al.  Remote Assessment of Ocean Color for Interpretation of Satellite Visible Imagery: A Review , 1983 .

[16]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[17]  R. C. Williamson,et al.  Support vector regression with automatic accuracy control. , 1998 .

[18]  Qing Li,et al.  Comparison of LST retrieval algorithms between single-channel and split-windows for high-resolution infrared camera , 2009, 2009 IEEE International Geoscience and Remote Sensing Symposium.

[19]  Giulietta S. Fargion,et al.  Ocean Optics Protocols for Satellite Ocean Color Sensor Validation. Revised , 2000 .

[20]  A. Gitelson,et al.  Assessing the potential of SeaWiFS and MODIS for estimating chlorophyll concentration in turbid productive waters using red and near-infrared bands , 2005 .

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

[22]  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.

[23]  Deyong Sun,et al.  Parameterization of water component absorption in an inland eutrophic lake and its seasonal variability: a case study in Lake Taihu , 2009 .

[24]  Xu Jing.  ESTIMATION OF CHLOROPHYLL-a CONCENTRATION IN LAKE XINMIAO BASED ON A SEMI-ANALYTICAL MODEL , 2008 .

[25]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[26]  R. Ma,et al.  Bio‐optical model with optimal parameter suitable for Taihu Lake in water colour remote sensing , 2006 .

[27]  Chih-Jen Lin,et al.  Training nu-support vector regression: theory and algorithms. , 2002, Neural computation.

[28]  Howard R. Gordon,et al.  Remote Assessment of Ocean Color for Interpretation of Satellite Visible Imagery , 1983, Lecture Notes on Coastal and Estuarine Studies.

[29]  C. Davis,et al.  Model for the interpretation of hyperspectral remote-sensing reflectance. , 1994, Applied optics.

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

[31]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[32]  Chih-Jen Lin,et al.  Training v-Support Vector Regression: Theory and Algorithms , 2002, Neural Computation.

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

[34]  Liu Qinhuo,et al.  Inversion of chlorophyll-a concentration in turbid water of Lake Taihu based on optimized multi-spectral combination , 2008 .

[35]  Lorenzo Bruzzone,et al.  Semisupervised Classification of Hyperspectral Images by SVMs Optimized in the Primal , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[36]  J. Sobrino,et al.  A generalized single‐channel method for retrieving land surface temperature from remote sensing data , 2003 .

[37]  Davide D'Alimonte,et al.  A Statistical Index of Bio-Optical Seawater Types , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Anatoly A. Gitelson,et al.  Remote estimation of chlorophyll concentration in hyper-eutrophic aquatic systems: Model tuning and accuracy optimization , 2006 .