AI Predicts Harmful Algal Blooms Using Satellite Data Off Portugal.

Ayman Bnoussaad, El Khalil Cherif, Ligia Pinto, Ramiro Neves, Alexandra D. Silva, Alexandre Bernardino· July 10, 2026 View original

Summary

Researchers developed a machine learning framework using satellite data to predict harmful Pseudo-nitzschia algal blooms along the Portuguese coast, achieving moderate predictability with ensemble tree-based methods. The system identifies key environmental and biological factors influencing bloom occurrence, offering a new tool for early warning.

A new study introduces a machine learning system designed to forecast harmful algal blooms (HABs) caused by Pseudo-nitzschia diatoms along Portugal's Atlantic coast. This framework leverages exclusively satellite-derived predictors, such as sea surface temperature, chlorophyll-a, and plankton types, to predict bloom occurrences under realistic forecasting conditions. The models were developed using a decade of data from specific shellfish production zones, employing a stringent spatio-temporal cross-validation to ensure real-world applicability. Ensemble tree-based methods, particularly Random Forest and Extra Trees, demonstrated the strongest predictive power, with feature importance analysis highlighting seasonal patterns, spatial context, and lagged environmental conditions as primary drivers. This research provides a robust, operationally relevant early-warning system for HABs in eastern boundary upwelling coasts, enhancing environmental monitoring and public health safety.

Why it matters

This research offers a critical advancement for environmental monitoring and public health, enabling earlier detection and mitigation of harmful algal blooms that impact coastal ecosystems and industries.

How to implement this in your domain

  1. 1Integrate satellite data streams into existing environmental monitoring platforms.
  2. 2Develop or adapt machine learning models for specific regional HAB prediction.
  3. 3Establish protocols for disseminating early warnings to affected industries and communities.
  4. 4Collaborate with research institutions to refine predictive models and incorporate new data sources.

Who benefits

AquacultureFisheriesTourismPublic HealthEnvironmental Monitoring

Key takeaways

  • Satellite data can effectively predict harmful algal blooms using machine learning.
  • Ensemble tree-based models show strong performance in spatio-temporal HAB forecasting.
  • Seasonal, spatial, and lagged environmental factors are crucial predictors.
  • The framework supports operationally relevant early-warning systems for coastal regions.

Original post by Ayman Bnoussaad, El Khalil Cherif, Ligia Pinto, Ramiro Neves, Alexandra D. Silva, Alexandre Bernardino

"arXiv:2607.07834v1 Announce Type: new 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 blo…"

View on X

Originally posted by Ayman Bnoussaad, El Khalil Cherif, Ligia Pinto, Ramiro Neves, Alexandra D. Silva, Alexandre Bernardino on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research

AI Research

New Algorithm Learns AC^0 Circuits Under Correlated Distributions

Researchers present a quasipolynomial-time algorithm for learning constant-depth circuits (AC^0) under graphical models that allow efficient local sampling. This work extends prior guarantees by circumventing the polynomial-growth requirement, offering a framework applicable to two-spin systems on arbitrary bounded-degree graphs.

Weiming Feng, Xiongxin Yang, Yixiao Yu, Yiyao ZhangJul 10, 2026
AI ResearchAI Engineering & DevTools

AI System Recommends Pathological Tests, Improving Diagnostic Efficiency

A new study introduces a pathological test recommendation system using Classifier Chain (CC) techniques to suggest diagnostic tests based on patient symptoms before physician consultation. The system, leveraging machine learning and Explainable AI (XAI), achieved high accuracy and provided clinically interpretable reasoning consistent with medical knowledge.

Abu Rafe Md Jamil, Nayan MalakarJul 10, 2026
AI ResearchAI Engineering & DevTools

CASL-VAE Learns Latent Variables from Unpaired Data for Disease Analysis

Researchers introduce CASL-VAE, a deep contrastive latent variable model that learns structured latent generative factors from unpaired data to quantify population variability. It factorizes variation into common and hierarchical salient factors, enabling improved subtype recovery and paired-sample generation, validated on neuroimaging data for Alzheimer's disease.

Sai Spandana Chintapalli, Pratik Chaudhari, Christos DavatzikosJul 10, 2026