Post-Doc – AI simulation of European sea bass trajectories on French coastlines (F/M/X)
- Reference : FEM-SAS-2026-006
- Position type: Fixed-term contract
- Duration: 18 month
- Localisation: Brest (29) - France Energies Marines
- Download the offer
Job Description
The growing number of offshore wind farms raises critical environmental and societal questions about their impact on marine ecosystems. These questions are at the heart of the « Biodiversity & Monitoring » team of France Energies Marines and the FISHOWF+ R&D project of which this position is a part. The FISHOWF+ project aims to deepen knowledge of the interactions between fish and offshore wind farms. It proposes to improve the understanding of European sea bass seasonal movements (Dicentrarchus Labrax), their functional areas and the potential overlap with the areas where wind farms are located on French coastlines.
To do this, we propose to rely on a unique database of sea bass trajectories collected as part of the BARGIP project led by Ifremer (de Pontual et al. 2019, 2023). These trajectories provide information on both the seasonal migrations of the individuals monitored, but also the environmental conditions they went through. The development of movement models from this database could thus make it possible to (1) better characterize the way these individuals have interacted with their environment and (2) simulate their movements in other oceanographic conditions. A trajectory simulation tool could thus be strategic to better estimate the connectivity between the different wind farm development areas and the probabilities of occurrence of individuals in these areas.
Missions
The objective of this post-doctoral fellowship is therefore to develop movement models to simulate the migratory movements of fish on the French coastlines. We will thus focus on the classic tools of movement ecology (random walks, hidden Markov models, etc.) (Florko et al., 2025), but also generative artificial intelligence tools (Goodfellow et al., 2014). Indeed, in recent years, generative neural networks, such as GANs (i.e. Generative Adversarial Networks) and diffusion models, have shown promising ability to simulate human (Cao et al., 2019; Gao et al., 2020) and animal trajectories (Roy et al., 2022; Roy, 2022).
The simulation of realistic trajectories with regard to the description of a habitat will make it possible to:
- Estimate sea bass trajectories at sites where movement tracking by deploying archival tags has not been possible
- Estimate the spatial variations of sea bass distributions by simulating the trajectories of individuals at the population scale
- Estimate the probabilities of sea bass occurrence at current and future offshore wind farms
The candidate will collaborate at the European level (WUR, GEOMAR) on the development of these trajectory simulation methods within the framework of the European project DTOTRACK. This project aims to map the movements and distribution of marine life in the North Sea, and then use this data to create a digital twin of the area. This digital twin can then be used to make more ecologically informed decisions in the blue economy and marine spatial planning sector.
Required Skills
Initial training
PhD in quantitative ecology, or deep learning
Specific knowledge
- Good knowledge of marine ecology
- Movement ecology
- Programming in Python and/or R
- Deep Learning tools (torch, lightning, hydra)
Professional qualities
- Ability to work in a team environment in an interdisciplinary research environment
- Autonomy, rigor, sense of organization
- Analytical and synthesis skills
The +:
Interest in environmental issues and marine renewable energies
WARNING: If you are unable to submit your application via our website, please send it by e-mail to contactrh@france-energies-marines.org, specifying the job reference in the subject field.
Job : Post-Doc – AI simulation of European sea bass trajectories on French coastlines (F/M/X)
Reference : FEM-SAS-2026-006
"*" indicates required fields