Description du sujet de thèse

PhD : Population scaling of individual-centered digital twins of seabirds M/F. Seabirds play a crucial role in the balance of marine ecosystems, but are also strongly impacted by the erosion of biodiversity. With the increase in data on seabird behavior and the emergence of artificial intelligence tools, projects have emerged to develop digital avatars of seabirds. The thesis is funded by the Mission for Transverse and Interdisciplinary Initiatives, winner of the 2025 edition of the CNRS Transverse program. The main objective of this thesis is to create a framework for evaluating individual-centered AI simulators based on biologging observation data, allowing the transition to conclusions at the population level.
This thesis will be based on a longitudinal database collected over twenty years in the tropical Atlantic and the Pacific, covering four sites and six species. These data will be supplemented by those from international databases. The thesis will be divided into four stages: 1. Selection of a pre-existing individual-based simulation architecture (S1). 2. Development of a model allowing to move from the individual to the population scale (S2/S3). 3. Construction of an evaluation framework for population models (S3/S4). 4. Predictions on the future viability of colonies under different scenarios of climate change and anthropogenic pressures (S5/S6).

Contexte de travail

The recruited person will join the UMR MARBEC. The Joint Research Unit (UMR) MARBEC, MARine Biodiversity, Exploitation and Conservation, was created on January 1, 2015. Its supervisory authorities are the IRD, Ifremer, the University of Montpellier and the CNRS. MARBEC is one of the largest laboratories working on marine biodiversity and its uses in France with approximately 300 staff, including 90 researchers and lecturer-researchers. The unit is located in Sète, Montpellier and Palavas-les-flots, as well as in the Indian Ocean, Asia, Africa and South America. It studies the marine biodiversity of lagoon, coastal and offshore ecosystems, mainly Mediterranean and tropical. Its research focuses on different levels of integration, from molecular, individual, population and community aspects, to the uses of this biodiversity by humans.
The recruited person must have strong skills and experience in ecology AND mathematics, machine learning, and computer science. An appetite for teamwork, in an international and multilingual environment is expected. Fieldwork skills with unhoused wildlife would be an advantage. The recruited person will carry out the majority of their work in office conditions, at the Marbec laboratory in Sète, with stays to be planned in the laboratory of their co-thesis director in Nantes. Field activities in Brazil will be possible even if the feasibility of the thesis does not directly depend on it since existing databases are already available and sufficient. These will always be carried out as a team, with the thesis director and/or their senior Brazilian partners, who will take care of all security procedures and authorization requests.
The recruited person will have an internet connection, the laboratory's institutional tools (access to journals, computing resources), an office and the necessary equipment to carry out their work. In addition to their two thesis supervisors, the recruited person will work in a team of 3 other doctoral students, and will benefit from the thesis supervisor's close partnerships with IMT Atlantique (Brest), LIRMM (Montpellier) and the U. Federal de Rio Grande do Sul (UFRGS, Brazil).

Contraintes et risques

Possible field missions in Brazil. Mission risk.
Otherwise, work on a computer, therefore static.