Short-Term and Seasonal Forecasts of Harmful Algal Blooms on the West Florida Shelf

Both short-term and seasonal forecast tools are developed to help federal, state, and local end users monitor and manage harmful algal blooms on the west coast of Florida. The short-term forecasts are based on the West Florida Coastal Ocean Model (WFCOM) that downscales from the deep ocean, across the continental shelf and into the estuaries. Observed Karenia brevis cell count data are uploaded daily into the WFCOM to generate 3.5 day forecasts of the bloom trajectories on the shelf and in the estuaries. The tracking tool displays modeled bloom trajectories at the surface and the bottom with five categories of cell concentrations (present, very low, low, medium, and high, each differing approximately by an order of magnitude). The seasonal forecasts are based on a hypothesis that interactions by the Gulf of Mexico Loop Current with the shelf slope under certain conditions can reset the West Florida Shelf (WFS) nutrient structure in ways that may obviate bloom development. The Self-Organizing Map (SOM), an unsupervised neural network technique is used to identify such Loop Current patterns and their cumulative duration of occurrences from more than two decades satellite altimetry data, and this serves as an indicator of offshore forcing of anomalous upwelling. Given its consistency in hindcasting the occurrence of (or lack of) severe WFS coastal blooms in 20 of 25 years for which joint altimetry and cell count data exist, the offshore forcing index may serve as a seasonal predictor for major K. brevis blooms on the WFS.