Predicting Pseudo-nitzschia harmful algal blooms along the Portuguese Coast using satellite-derived predictors

2026-07-08

AI Summary

This study addresses the threat posed by harmful algal blooms (HABs) of Pseudo-nitzschia along the Portuguese coast to shellfish aquaculture and marine ecosystems by developing a spatiotemporal machine learning prediction framework based on satellite remote sensing data. Innovatively, river-informed spatial clustering is employed to delineate ecologically meaningful subregions, and a rigorous spatiotemporal cross-validation strategy—simultaneously excluding entire years and spatial clusters—is implemented to better reflect real-world forecasting conditions. Integrating over a thousand environmental and biological features, including sea surface temperature, upwelling indices, chlorophyll-a, and plankton functional types, the framework leverages Random Forest and Extra-Trees models. In L1–L2 hotspot zones, the models achieve an AUC of 0.74 ± 0.05 using only environmental variables, which improves to 0.77 ± 0.06 upon inclusion of biological variables, demonstrating strong potential for operational early-warning applications.

Abstract

Pseudo-nitzschia diatoms pose recurrent risks to coastal ecosystems and shellfish harvesting along the Portuguese Atlantic coast. Here we develop and evaluate a spatio-temporal machine-learning framework to predict harmful algal bloom (HAB) occurrence using exclusively satellite-derived predictors under realistic forecasting constraints. We characterised environmental and biological variability across shellfish production zones (L1-L9) using 5,882 observations, providing system-wide context. Predictive models were developed for zones L1-L2, a hotspot for Pseudo-nitzschia and domoic acid events, using a decade-long dataset (2013-2023; 1,440 observations; more than 1,000 satellite-based predictors including sea surface temperature, an upwelling index, chlorophyll-a, and plankton functional types). Sampling locations were partitioned into ecologically meaningful sub-regions using a river-aware spatial clustering scheme. A stringent spatio-temporal cross-validation strategy that simultaneously withholds entire years and spatial clusters prevents leakage and closely mimics real-world forecasting conditions. HAB occurrence proved moderately predictable across model classes and feature configurations. Ensemble tree-based methods achieved the strongest discrimination: Random Forest reached 0.74 +/- 0.05 with environmental predictors; Extra Trees reached 0.77 +/- 0.06 with biological variables added. Feature-importance analyses revealed that seasonal structure, spatial context, and lagged environmental conditions dominate model decisions, while biological indicators refine bloom likelihood within physically favourable periods. The framework demonstrates operationally relevant skill for satellite-supported HAB early-warning systems along eastern boundary upwelling coasts.

Problem

• harmful algal blooms
• Pseudo-nitzschia
• satellite-derived predictors
• early-warning system
• coastal ecosystems

Innovation

• spatio-temporal machine learning
• satellite-derived predictors
• harmful algal bloom forecasting
• river-aware spatial clustering
• strict spatio-temporal cross-validation