Using a partial least squares (PLS) method for estimating cyanobacterial pigments in eutrophic inland waters

A. L. Robertson; L. Li; L. Tedesco; J. Wilson; E. Soyeux

doi:10.1117/12.824632

20 August 2009 Using a partial least squares (PLS) method for estimating cyanobacterial pigments in eutrophic inland waters

A. L. Robertson, L. Li, L. Tedesco, J. Wilson, E. Soyeux

Author Affiliations +

Proceedings Volume 7454, Remote Sensing and Modeling of Ecosystems for Sustainability VI; 745408 (2009) https://doi.org/10.1117/12.824632
Event: SPIE Optical Engineering + Applications, 2009, San Diego, California, United States

Abstract

Midwestern lakes and reservoirs are commonly exposed to anthropogenic eutrophication. Cyanobacteria thrive in these nutrient rich-waters and some species pose three threats: 1) taste & odor (drinking), 2) toxins (drinking + recreational) and 3) water treatment process disturbance. Managers for drinking water production are interested in the rapid identification of cyanobacterial blooms to minimize effects caused by harmful cyanobacteria. There is potential to monitor cyanobacteria through the remote sensing of two algal pigments: chlorophyll a (CHL) and phycocyanin (PC). Several empirical methods that develop spectral parameters (e.g., simple band ratio) sensitive to these two pigments and map reflectance to the pigment concentration have been used in a number of investigations using field-based spectroradiometers. This study tests a multivariate analysis approach, partial least squares (PLS) regression, for the estimation of CHL and PC. PLS models were trained with 35 spectra collected from three central Indiana reservoirs during a 2007 field campaign with dual-headed Ocean Optics USB4000 field spectroradiometers (355 - 802 nm, nominal 1.0 nm intervals), and CHL and PC concentrations of the corresponding water samples analyzed at Indiana University-Purdue University at Indianapolis. Validation of these models with 19 remaining spectra show that PLS (CHL R²=0.90, slope=0.91, RMSE=20.61 μg/L; PC R²=0.65, slope=1.15, RMSE=23.04. μg/L) performed equally well to the band tuning model based on Gitelson et al. 2005 (CHL: R²=0.75, slope=0.84, RMSE=40.16 μg/L; PC: R²=0.59, slope=1.14, RMSE=20.24 μg/L).

Citation Download Citation

A. L. Robertson, L. Li, L. Tedesco, J. Wilson, and E. Soyeux "Using a partial least squares (PLS) method for estimating cyanobacterial pigments in eutrophic inland waters", Proc. SPIE 7454, Remote Sensing and Modeling of Ecosystems for Sustainability VI, 745408 (20 August 2009); https://doi.org/10.1117/12.824632

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available