EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data

Martin Marzidovšek, Janja Francé, Vid Podpečan, Stanka Vadnjal, Jožica Dolenc, Patricija Mozetič

Harmful Algae · 2024-11 · 139 · 102728

DOI: 10.1016/j.hal.2024.102728 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Harmful Algae, 2024-11. Verfasst von Martin Marzidovšek und 5 weiteren Autor:innen. Beteiligte Einrichtung: Jožef Stefan Institute, Department of Knowledge Technologies, Slovenia; Jožef Stefan International Postgraduate School, Slovenia. Electronic address:…. Hauptthemen laut MEDLINE: Machine Learning, Shellfish Poisoning. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Slovenian Research and Innovation Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 diarrhetic shellfish toxins in mussels (Mytilus galloprovincialis), we train and evaluate the performance of machine learning (ML) models to accurately predict diarrhetic shellfish poisoning (DSP) events. Based on the F1 score, the random forest model provided the best prediction of toxicity results at which the harvesting of mussels is stopped according to EU regulations. Explainability methods such as permutation importance and Shapley Additive Explanations (SHAP) identified key species (Dinophysis fortii and D. caudata) and environmental factors (salinity, river discharge and precipitation) as the best predictors of DSP toxins above regulatory limits. These findings are important for improving early warning systems, which until now were based solely on empirically defined alert abundances of DSP species. They provide experts, aquaculture practitioners, and authorities with additional information to make informed risk management decisions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningShellfish PoisoningAnimalsHarmful Algal BloomMytilusEnvironmental MonitoringDinoflagellidaMarine ToxinsPhytoplankton

Stichwörter der Autor:innen

Adriatic SeaAquacultureDSP toxinsExplainable artificial intelligenceHarmful algal bloomsMachine learningMarine ecology

Substanzen

Marine Toxins

Autor:innen und Institutionen

  • Jožef Stefan Institute, Department of Knowledge Technologies, Slovenia; Jožef Stefan International Postgraduate School, Slovenia. Electronic address: martin.marzidovsek@ijs.si.
  • National Institute of Biology, Marine Biology Station Piran, Slovenia.
  • Jožef Stefan Institute, Department of Knowledge Technologies, Slovenia.
  • University of Ljubljana, Veterinary Faculty, National Veterinary Institute, Slovenia.

Förderung

  • The Slovenian Research and Innovation Agency

Zitieren

APA

Marzidovšek, M., Francé, J., Podpečan, V., Vadnjal, S., Dolenc, J., & Mozetič, P. (2024). Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data. Harmful Algae, 139, 102728. https://doi.org/10.1016/j.hal.2024.102728

Vancouver

Marzidovšek M, Francé J, Podpečan V, Vadnjal S, Dolenc J, Mozetič P. Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data. Harmful Algae. 2024;139:102728. doi:10.1016/j.hal.2024.102728

BibTeX
@article{Marzidovek2024,
  author = {Marzidovšek, Martin and Francé, Janja and Podpečan, Vid and Vadnjal, Stanka and Dolenc, Jožica and Mozetič, Patricija},
  title = {Explainable machine learning for predicting diarrhetic shellfish poisoning events in the Adriatic Sea using long-term monitoring data},
  journal = {Harmful Algae},
  year = {2024},
  volume = {139},
  pages = {102728},
  doi = {10.1016/j.hal.2024.102728}
}
Kostenlos starten →