Offre en lien avec l’Action/le Réseau : – — –/Doctorants
Laboratoire/Entreprise : CRISTAL Lab – UMR CNRS 9189/University of Lille
Durée : 24 months – Ideally
Contact : hayfa.zgaya-biau@univ-lille.fr
Date limite de publication : 2025-12-31
Contexte :
The IARISQ project, funded by the French National Research Agency (ANR), aims to develop advanced artificial intelligence (AI) models to predict the toxicity thresholds of airborne particles, taking into account their physico-chemical properties and environmental dynamics. The project combines AI, probabilistic modeling, fuzzy logic, and explainable AI (XAI) to build a robust decision support system for public health and environmental risk assessment.
Sujet :
We are seeking a highly motivated postdoctoral researcher with strong expertise in machine learning and data science. The selected candidate will contribute to the design, implementation, and evaluation of predictive AI models for toxicity thresholds, with a focus on:
– Developing deep learning models (e.g., GANs, Transformers, TabNet)
– Managing uncertainty with probabilistic (e.g., GPR, Bayesian Neural Networks) and fuzzy logic approaches (e.g., Interval Type-2 Fuzzy Logic)
– Applying explainable AI techniques (e.g., SHAP, LIME, GrC) to identify influential variables
– Collaborating with environmental scientists and air quality experts
– Preparing scientific publications and sharing code (GitHub, open-source)
Related Publications
The candidate will contribute to a project with a strong publication record in top-tier journals and conferences. Recent related publications include:
1. Idriss Jairi, Sarah Ben-Othman, Ludivine Canivet, Hayfa Zgaya-Biau, Explainable-based approach for the air quality classification on the granular computing rule extraction technique, Engineering Applications of Artificial Intelligence, 2024. (Q1, IF: 7.5, AI/Software) https://doi.org/10.1016/j.engappai.2024.108096
2. Idriss Jairi, Sarah Ben-Othman, Ludivine Canivet, Hayfa Zgaya-Biau, Enhancing Air Pollution Prediction: A Neural Transfer Learning Approach across Different Air Pollutants, Environmental Technology & Innovation, 2024. (Q1, IF: 6.7, Environmental Engineering) https://doi.org/10.1016/j.eti.2024.103793
3. Idriss Jairi, Amelle Rekbi, Sarah Ben-Othman, Slim Hammadi, Ludivine Canivet, Hayfa Zgaya-Biau, Enhancing particulate matter risk assessment with novel machine learning-driven toxicity threshold prediction, Engineering Applications of Artificial Intelligence, 2025. (Q1, IF: 7.5, AI/Software) https://doi.org/10.1016/j.engappai.2024.109531
Conference
Doctoral Consortium Participant, ECAI 2024 – European Conference on Artificial Intelligence, Santiago de Compostela, Spain – October 2024. https://anaellewilczynski.pages.centralesupelec.fr/ecai-2024-dc/accepted.html
Profil du candidat :
PhD in Artificial Intelligence, Machine Learning, Data Science, or a closely related field.
– Strong experience in developing and evaluating deep learning models (e.g., GANs, Transformers, LSTM).
– Solid background in uncertainty modeling, explainable AI (XAI), or hybrid AI approaches is a plus.
– Excellent programming skills (Python, PyTorch or TensorFlow).
– Proven ability to conduct high-quality research, with publications in top-tier conferences or journals.
– Autonomy, creativity, and ability to work in a multidisciplinary environment (AI + environment + public health).
– Strong communication skills (oral and written) in English.
Formation et compétences requises :
PhD in computer Science – Artificial Intelligence
Adresse d’emploi :
https://www.cristal.univ-lille.fr
UMR CRIStAL
Université de Lille – Campus scientifique
Bâtiment ESPRIT
Avenue Henri Poincaré
59655 Villeneuve d’Ascq