AI & Control · Applied Mathematics
Victor Bertret
Machine learning & stochastic control for real industrial systems.
I design algorithms at the intersection of physical modeling, data assimilation and optimal control, and take them all the way to deployment on live plants at Purecontrol. PhD in Applied Mathematics, Université de Rennes.
Journal Articles
01Data assimilation for prediction of ammonium in wastewater treatment plant: from physical to data driven models
Water Research (2025) - A systematic comparison of white-box, grey-box and black-box models combined with data assimilation to forecast ammonium concentration in WWTPs.
Conference Proceedings
04Contrôleur prédictif par apprentissage machine pour la déphosphatation sans capteur en ligne : application et validation en conditions opérationnelles
Uncertainty Analysis in Predictive Control for Wastewater Treatment Plants
A stochastic expectation maximization algorithm for the estimation of wastewater treatment plant ammonium concentration
Optimization of a biogas upgrading unit's operation
Talks & Posters
03Stochastic Control for Industrial Processes: Open-Loop Performance vs. Closed-Loop Robustness
Data assimilation for prediction of ammonium in WWTP: from physical to data driven models
Lessons Learned from Solving Data-Driven Optimal Control Problems as MILPs
PhD Thesis
01Machine Learning and Stochastic Control for the Optimized Automatic Piloting of Industrial Systems
PhD thesis (Université de Rennes, 2025) - Machine learning and stochastic control for the energy-optimal, constraint-aware piloting of wastewater treatment plant aeration.