Abstract
Eutrophic semi-enclosed bay can lead to a phytoplankton bloom (red tide) and may result in a fishery damage. The purpose of this study is to develop a real time phytoplankton bloom prediction model by using automatic water quality measurement system and meteorological observation. The model forecast a red tide of the next day using observations from 6:00 to 18:00. Depending on comparison of red tide information and water quality, the red tide was defined surface oxygen saturation of greater than 150% in this study. There was a precursor of the red tide from surface temperature, surface salinity, wind speed and global solar radiation. These SI models were proposed based on observation. At first, the prediction model had a problem for estimating of the continuous red tide. Finally, the suggested prediction model could have 59% accuracy which was 2.8 times higher than normal red tide probability.
