Sam Ahmed (Distinguished Professor of Electrical Engineering, CCNY-CUNY),
Alex Gilerson (Associate Professor, Electrical Engineering, CCNY-CUNY)
Algae are the most abundant photosynthetic organisms in marine ecosystems and are essential components of marine food webs. Harmful algal bloom or “HAB” species are a small subset of algal species that negatively impact humans or the environment. HABs can pose health hazards for humans or animals through the production of toxins or bioactive compounds. They also can cause deterioration of water quality through the buildup of high biomass, which degrades the ecological, aesthetic and recreational value of coastlines.
We have applied a statistical approach to find a K.brevis binary classifier for West Florida Shore waters. Our approach relies on the largest existing database from the Fish and Wildlife Research Institute (Database Records), which contains over 64,053 records of the concentration of K.brevis red tide in Florida waters from 1954 to 2006. We have used variables from the historic HAB database: location (latitude/longitude), time (day) and the degree to which K.brevis was present. Associated with each observation in the database, there is a satellite product based observational vector. This vector is made up of the following variables: chlorophyll, normalized water leaving radiance at wavelengths 443, 551, and 667, and sea surface temperature, matching the time and location of the HAB database measurement. The HAB measured ground truths and the corresponding observation vector values are used as training set to train a binary classifier. Once trained, this classifier is used to predict the HAB or no HAB state from the satellite based observation vector alone.
Conference Paper: Characterizing bio-optical and ecological features of algal bloom waters for detection amd tracking from space
Student Poster: HAB Student Poster