C. Taklis

Merman Conservation Expeditions Ltd., Edinburgh, United Kingdom
Author    Correspondence author
International Journal of Marine Science, 2025, Vol. 15, No. 6   
Received: 21 Aug., 2025    Accepted: 23 Oct., 2025    Published: 06 Nov., 2025

This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Jellyfish blooms are increasing in frequency and intensity across the Mediterranean Sea, posing growing challenges to tourism, fisheries, public safety, and coastal ecosystem monitoring. Despite the rise of citizen science platforms and the availability of real-time environmental data, no operational system currently exists to forecast jellyfish movement. This paper introduces the Predictive Displacement Theory (PDT), the first proposed framework for forecasting jellyfish drift by combining user-submitted sightings with environmental drivers such as wind, wave direction, sea surface currents, and atmospheric pressure. The concept is designed to operate through an AI-assisted application that ingests real-time observations and oceanographic data to generate short- and medium-term forecasts of jellyfish aggregations. As a proof of concept, the framework was retrospectively tested on the 2020~2023 Pelagia noctiluca blooms in Greece, with a focus on the Corinthian Gulf during 2021 and 2022, using Windy.com datasets and geo-referenced observations from the iNaturalist platform and a Facebook group. Even without AI support, the model predicted southward jellyfish movement with up to 90% accuracy over five-day periods. These findings demonstrate the viability of PDT and its potential to evolve into the first real-time jellyfish forecasting system, supporting both ecological forecasting and timely public warning mechanisms.

Jellyfish blooms; Predictive Displacement Theory; AI-assisted forecasting; Citizen science; Coastal ecosystem management