Utilizing Knowledge Bases in Filtering IoT Data to Predict Algal Blooms

The proliferation of algal blooms in aquatic habitats has emerged as a matter of worldwide significance, owing to their consequential ecological and economic ramifications. Conventional forecast techniques frequently encounter difficulties in comprehensively capturing the intricate interaction of environmental variables that contribute to bloom occurrences. This research study presents a novel methodology incorporating knowledge bases into the data preprocessing stage to predict algal blooms. This approach aims to improve the accuracy of predictions by integrating expert knowledge, historical data, and real-time observations. The methodology encompasses obtaining and organizing domain-specific information, merging it with environmental data, and constructing prediction models. The experimental findings provide evidence of the strategy’s efficacy in enhancing predicting accuracy. This research makes a valuable contribution to the proactive algal bloom control field by integrating data-driven methodologies with ecological experience, resulting in the development of a comprehensive framework.