Karenia brevis blooms occur nearly annually along the southwest coast of Florida, and effective mitigation of ecological, public health, and economic impacts requires reliable real-time forecasting. We present two boosted random forest models that predict the weekly maximum K. brevis abundance category across the Greater Charlotte Harbor estuaries over one-week and four-week forecast horizons. The feature set was restricted to data available in near-real time, consistent with adoption of the models as decision-support tools. Features include current and lagged K. brevis abundance statistics, Loop Current position, sea surface temperature, sea level, and riverine discharges and nitrogen concentrations. During cross-validation, the one-week and four-week forecasts exhibited 73 % and 84 % accuracy, respectively, during the 2010–2023 study period. In addition, we assessed the models’ reliability in forecasting the onset of 10 bloom events on time or in advance; the one-week and four-week models anticipated the onset eight times and five times, respectively.
Read full abstract