Job offer

European Commission; France; Sur place; EUR 40 000 - 60 000; Plein temps

Résumé du poste

Un projet postdoctoral passionnant sur le biomonitoring aquatique cherche un candidat ayant un doctorat en biologie marine ou écologie. Le projet 'BioIndic-IA' utilise l'apprentissage automatique pour améliorer les outils d'évaluation écologique des écosystèmes aquatiques. Le candidat idéal aura des compétences en identification taxonomique et une bonne connaissance des technologies modernes en IA.

Qualifications

• Doit avoir un doctorat en biologie marine, écologie ou géologie.
• Bonne connaissance de l'anglais et niveau de base en français.
• 1 à 4 ans d'expérience en recherche.

Responsabilités

• Identification taxonomique des micro-organismes, notamment des foraminifères benthiques.
• Utilisation de l'apprentissage automatique pour des études morphologiques.
• Développement de nouvelles technologies pour l'acquisition automatique d'images.

Connaissances

Identification taxonomique

Connaissance écologique des foraminifères

Technologies basées sur le machine learning

Formation

Doctorat en biologie marine/ecologie ou géologie

Description du poste

Organisation/Company UNIVERSITE ANGERS Department Human Resources - Recruitment Research Field Biological sciences Researcher Profile Established Researcher (R3) Positions Postdoc Positions Country France Application Deadline 28 Jun 2025 - 23:59 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 1 Sep 2025 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Name of the project : BioIndic-IA«Deep learning for automatic image-based biomonitoring of aquatic ecosystems».

The scientific project is founded by the French ANR project BioIndic-IAdealing with «Deep learning for automatic image-based biomonitoring of aquatic ecosystems».This global project is supervised by M. Laviale (LIEC, Lorraine University) in collaboration with different French (Marseille University CEREGE, Angers University LPG…) and Luxemburg (LIST) institutions. The post-doc grant is founded by the ANR.

Description of the research project in which the research activities entrusted to the officer take place:

Worldwide intensification of land and coastal use and aquatic resources has led to a drastic increase in the intensity and diversity of anthropogenic pressures, simultaneously driving changes in local biotic communities which ultimately impair ecosystem functioning and ecosystem services over multiple spatial and temporal scales. This highlights the urgent need for developing innovative ecological diagnostic tools supporting robust management responsesto every pressure of human origin impairing the water physical and chemical quality and/or the integrity of habitats. Biomonitoring has been initially based on diversity indices, which rely on taxonomic inventories, and later on biotic indices, which combine the relative abundance of indicator species to their ecological profile, i.e. their sensitivity or tolerance to environmental variables. Within the European Water Framework Directive (WFD) and the Marine Strategy Framework Directive (MSFD), these approaches have already proven their efficiency for assessing the global ecological quality of water bodies using a given biological compartment, such as BENTHIC DIATOMS or BENTHIC FORAMINIFERA, that are both unicellular organisms with shells living on the bottom of aquatic ecosystems.

BENTHIC FORAMINIFERA-based indices are recent and still seldom included in regulatory ecological assessmentsdespite their confirmed potential to track the ecological quality status of coastal ecosystems. Besides taxonomy, the assessment of traits should be also now considered. However using foraminiferal based indices and developing new tools based on traits are time consuming studies. This is a lock to include such relevant tools to European and National regulatory ecological assessments.

For any group of organisms, classical bioindication relies on visual recognition by human experts of indicator speciesbased on morphological criteria (for foraminifera: chamber and aperture shape, texture of the test…). Some of these morphological traits hold more than just taxonomic information. Indeed, variability in traits can be observed across species (e.g. big vs. small species) but also at the intraspecific level (e.g. porosity for foraminiferal shell) in response to environmental changes. However, manual identification of species or routine measurements of traits is too time-consuming, often subject to multiple biases (human expert’s experience, imaging system quality) and requires a high level of expertise. Nevertheless, automatic images acquisition and machine learning for identifying foraminiferal species and measuring morphological traits are promising methods. State-of-the-art methods from artificial intelligence, such as deep learning based on convolutional neural networks (CNNs) can be used for taxonomic classification and the quantification of morphological traits9. However, the performance of these methods is strongly dependent on the availability and quality of curated image datasetsused for model training, a common bottleneck when implementing machine learning (ML) for ecological image automatic processing.

• Taxonomic identification of micro-organisms particularly of benthic foraminifera
• Ecological knowledge of foraminifera

Know-how:

• New technologies based on machine learning

Specific Requirements

Candidate should have a PhD in marine biology/ecology or geology(micropaleontology for example).

Languages ENGLISH Level Good

Languages FRENCH Level Basic

Research Field Biological sciences Years of Research Experience 1 - 4

Additional Information

Monthly wage : 3200€ gross

Eligibility criteria

Candidate should have a PhD in marine biology/ecology or geology(micropaleontology for example).