Red tides are among the most destructive marine ecological hazards worldwide, posing significant threats to fisheries, biodiversity, and human health. Therefore, it is imperative to accurately and timely predict red tide occurrences to mitigate their ecological and socioeconomic impacts. However, the prediction accuracy of red tides is challenged by the complex, nonlinear relationships between red tide algae and environmental factors. Using 35 years (1986–2020) of continuous in situ records of water quality and red tides in Hong Kong coastal waters, this study developed an integrated prediction framework based on five machine-learning algorithms: Random Forest, Back-Propagation Neural Network, Support Vector Machine, Gaussian Naive Bayes, and Logistic Regression. After feature selection using the Granger causality test and variance inflation factor, the random forest algorithm achieved the highest individual-model accuracy of 84.85% for predicting red tide occurrence. An integrated model combining the top three algorithms further improved performance, reaching an accuracy of 98.5%. Feature-importance analyses indicated that silicon (Si) and suspended solids (SS) are the most influential environmental predictors in the integrated model. Overall, this study provides a high-precision and interpretable framework for predicting red tide occurrence and offers new insights into the environmental mechanisms underlying red tide outbreaks.
Yao et al. (Sun,) studied this question.