Abstract

Predicting harmful algal blooms (HABs) remains a major challenge for coastal management and aquaculture. This study compares three forecasting approaches developed under the Monitoring of Algae in Chile (MACH) project: a particle dispersion model, an LSTM neural network, and an empirical dynamic model (EDM) to evaluate their ability to forecast bloom events. Consequently, we applied the EDM to forecast two Pseudo-nitzschia species groups using data collected from Metri, Quell & oacute;n, and Melinka in southern Chile. The results showed that the genus Ceratium and Leptocylindrus were commonly associated with both Pseudo-nitzschia species groups, and the best prediction by causal species was obtained for the P. seriata group, with a correlation coefficient of 0.733 (P < 0.0001) between observed and predicted values. This case study demonstrated that species interactions can be used to predict specific HAB species; however, the prediction performance may vary depending on location and species. This study provides one of the first applications of EDM for HAB forecasting using causal species in a real-world monitoring context, demonstrating the potential of hybrid modeling frameworks to improve early warning systems and mitigate aquaculture losses.