CV

Ph.D. in Computer Science Inria Paris & École normale supérieure – PSL University, VALDA team. Supervised by Paul Boniol and Michael Thomazo. Segmentation, interpretability and representation in (multivariate) time series.

• Summer school: 9th Advanced Course on Data Science & Machine Learning, Italy, 2026

M.Sc. in Computer Science Research track National University of Singapore Neural networks, deep learning, data mining, knowledge discovery, NLP, trustworthy ML.

• Thesis: Data-Driven Discovery of State Variables from Dynamical System Observations

M.Sc. in Applied Mathematics Grande École Engineering Degree ENSTA Paris – Institut Polytechnique de Paris Optimization, statistics, probability, PDEs, scientific programming, signal processing, databases, time series.

• M1 thesis: Neural Networks for Turbulence Modeling, Harvard University

B.Sc. in Applied Mathematics Université de Toulouse Calculus, algebra, topology, probability, numerical methods, stochastic simulation.

Okinawa Institute of Science and Technology Interpretable methods for time series segmentation, with Prof. Makoto Yamada at OIST, Machine Learning and Data Science unit. Japan.

European Space Agency Analysis of the ESA Climate Change Initiative contribution to IPCC climate science reports. Harwell, UK.

• Report is private, but the analysis code and results are open

CNRS Physics-informed neural networks for dynamical systems at CNRS@CREATE (Centre National de la Recherche Scientifique), Singapore, with Stéphane Bressan.

• Physics-informed Discovery of State Variables in Second-Order and Hamiltonian Systems, NeurIPS'24 (ML4PS)
• Physics-informed Discovery of State Variables in Second-Order and Hamiltonian Systems, ACIIDS'25
• Assessing the Effectiveness of Intrinsic Dimension Estimators for Uncovering the Phase Space Dimensionality of Dynamical Systems from State Observations, DEXA'23

IPCC Meta-analysis of the 6th Assessment Report of the Intergovernmental Panel on Climate Change, with Sarah Connors.

• What 13,500 citations reveal about the IPCC's climate science report, Carbon Brief
• Analysis of the WGI contribution to the Sixth Assessment Report: Review of the WGI AR6 references
• Textual analysis of the WGI contribution to the AR6

Harvard University Physics-informed neural networks for Navier-Stokes equations in turbulent channel flow, in the StellarDNN team at the John A. Paulson School of Engineering and Applied Sciences, with David Sondak and Pavlos Protopapas.

• Solving Reynolds-Averaged Navier-Stokes equations in Turbulent Channel Flow

IRIT Machine learning for predictive maintenance of aircraft engines, in the SAMoVA team at IRIT in collaboration with ISAE-Supaéro, with Thomas Pellegrini.

• Data-driven predictive maintenance of aircraft engines

Météo France Statistical modelling of visibility and fog phenomena, Forecasting Operations Department, with Olivier Mestre.