Luxembourg Institute of Science and Technology
We are seeking a motivated PhD candidate to join an interdisciplinary research project focused on leveraging deep learning and advanced image processing techniques to improve the current tools for biomonitoring of aquatic ecosystems. This position involves the development and application of machine learning algorithms to automatically classify freshwater benthic diatoms at the species level and quantify key morphological traits. These advancements aim to improve ecological diagnostics compared to traditional methods by reducing time, cost and variability, therefore supporting robust management responses to anthropogenic pressures on aquatic ecosystems.
Applicants should have a background in aquatic ecology and biomonitoring, or related fields, with experience in image acquisition, large dataset processing, and statistical analysis. A passion for interdisciplinary research that bridges AI-driven technology and environmental sciences is essential. This position offers an exciting opportunity to develop innovative cutting-edge tools for improving ecological monitoring, therefore addressing urgent societal needs for sustainable ecosystem management.
Within the recently funded project BIOINDIC-IA (funded by the FNR under the ANR programme), you will be mainly in charge of:
· Data assembly and curation: using a state-of-the-art image acquisition set-up, compile and curate high-quality image datasets of freshwater diatoms for training, validation, and performance improvement of deep learning-based workflows for diatoms species identification and trait quantification (e.g. size, deformation intensity).
· Benchmarking and validation: Compare automated approaches with traditional methods based on relevant case studies within regulatory frameworks (such as the European Water Framework Directive: WFD), which will be representative of various taxonomic and morphologic trait diversity levels (in terms of species richness, abundance, distribution, …), the overall water class quality (good, bad and intermediate situations) but also the type of human pressures (eutrophication, habitat degradation, contamination by specific chemicals, etc).
· Develop innovative biomonitoring tools: Identify the most efficient combination of machine learning-based taxonomic and morphological metrics able to distinguish among different categories of pressure (e.g., nutrient contamination, pesticide pollution or habitat degradation).
· Real-world impact: lay the groundwork for implementing these innovative tools within institutional biomonitoring frameworks for practical applications by contributing to dedicated activities involving end-users, stakeholders and managers (OFB and Water Agencies in France, Administration de la gestion de l'eau (AGE) in Luxembourg).