Explainable machine learning for predicting shellfish toxicity in the Adriatic Sea using long-term monitoring data of HABs

TL;DR

This study applies explainable machine learning to predict shellfish toxicity in the Adriatic Sea, utilizing a 28-year dataset to identify key environmental and biological predictors for early warning and sustainable aquaculture.

Contribution

It introduces an explainable ML approach with long-term data to accurately predict shellfish toxicity and identify influential environmental factors.

Findings

Random forest achieved the best prediction performance.

Key predictors include specific phytoplankton species and environmental variables.

Explainability methods highlighted important biological and environmental factors.

Abstract

In this study, explainable machine learning techniques are applied to predict the toxicity of mussels in the Gulf of Trieste (Adriatic Sea) caused by harmful algal blooms. By analysing a newly created 28-year dataset containing records of toxic phytoplankton in mussel farming areas and toxin concentrations in mussels (Mytilus galloprovincialis), we train and evaluate the performance of ML models to accurately predict diarrhetic shellfish poisoning (DSP) events. The random forest model provided the best prediction of positive toxicity results based on the F1 score. Explainability methods such as permutation importance and SHAP identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP outbreaks. These findings are important for improving early warning systems and supporting sustainable aquaculture practices.