On the remote monitoring of Karenia brevis blooms of the west Florida shelf

In situ surveys (1997-2002) of Karenia brevis distribution on the west Florida shelf were used to explain spectral remote sensing reflectance, chlorophyll-a concentration, and backscattering coefficient estimates derived using SeaWiFS satellite data. Two existing approaches were tested in an attempt to differentiate K. brevis blooms from other blooms or plumes. A chlorophyll-anomaly method used operationally by the National Oceanic and Atmospheric Administration (NOAA) sometimes correctly identified K. brevis blooms but also generated false positives and false negatives. The method identified approximately 1000 km(2) of high chlorophyll-anomalies (> 1 mg m(-3)) off southwest Florida between the 10 and 50-m isobaths nearly every day from summer to late fall. Whether these patches were K. brevis blooms or not is unknown. A second method used a backscattering:chlorophyll-a ratio to identify K. brevis patches. This method separated K. brevis from other blooms using in situ optical data, but it yielded less satisfactory results with SeaWiFS data. Spectral reflectance (Rrs) estimates for K. brevis blooms, diatom blooms, and coastal river plumes are statistically similar for many cases. Large pixel size, shallow water, and imperfect algorithms distort satellite retrievals of bio-optical parameters in patchy blooms. At present, a combination of chlorophyll-a, chlorophyll-anomaly, backscattering:chlorophyll-a ratio, RGB composites, MODIS fluorescence data, as well as time-series analysis and ancillary data such as winds, currents, and sea surface temperature can improve K brevis bloom assessments. Progress in atmospheric correction and bio-optical inversion algorithms is required to help improve capabilities to monitor K. brevis blooms from space. Further, satellite sensors with improved radiometric capabilities and temporal/spatial resolutions are also required. (c) 2007 Elsevier Ltd. All rights reserved.