Machine learning predicts harmful algal blooms using satellite data

Researchers have developed a machine-learning framework to predict harmful algal blooms (HABs) caused by Pseudo-nitzschia diatoms along the Portuguese coast. The system utilizes satellite-derived environmental and biological data, achieving moderate predictability. Ensemble tree-based methods, specifically Random Forest and Extra Trees, demonstrated the strongest performance, with Extra Trees reaching an accuracy of 0.77 +/- 0.06 when incorporating biological variables. The study highlights the importance of seasonal structure, spatial context, and lagged environmental conditions in predicting bloom occurrences, suggesting the framework's operational relevance for early-warning systems on similar coastlines. AI

IMPACT Provides a novel machine learning framework for ecological forecasting, potentially improving early-warning systems for harmful algal blooms.

RANK_REASON Academic paper detailing a new machine learning framework for ecological prediction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Extra Trees
• Portuguese Atlantic coast
• Pseudo-nitzschia
• random forest

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →