Compréhension, prédiction et contrôle du transport turbulent des particules énergétiques dans les plasmas de fusion nucléaire par des simulations de trajectoires et des techniques d’intelligence artificielle (Thèse 2022 - 2025)
Activités
Fusion par confinement magnétique
Particules énergétiques
Simulation de trajectoires : codes gyro-cinétiques, trajectoires full-orbit
Intelligence artificielle
Publications scientifiques au M2P2
2025
B. Clavier, D. Zarzoso, D. Del-Castillo-Negrete, E. Frénod. Generative-machine-learning surrogate model of plasma turbulence. Physical Review E , 2025, 111 (1), pp.L013202. ⟨10.1103/PhysRevE.111.L013202⟩. ⟨hal-04966199⟩ Plus de détails...
Generative artificial intelligence methods are employed for the first time to construct a surrogate model for plasma turbulence that enables long-time transport simulations. The proposed GAIT (Generative Artificial Intelligence Turbulence) model is based on the coupling of a convolutional variational autoencoder that encodes precomputed turbulence data into a reduced latent space, and a recurrent neural network and decoder that generate new turbulence states 400 times faster than the direct numerical integration. The model is applied to the Hasegawa-Wakatani (HW) plasma turbulence model, which is closely related to the quasigeostrophic model used in geophysical fluid dynamics. Very good agreement is found between the GAIT and the HW models in the spatiotemporal Fourier and Proper Orthogonal Decomposition spectra, and the flow topology characterized by the Okubo-Weiss decomposition. The GAIT model also reproduces Lagrangian transport including the probability distribution function of particle displacements and the effective turbulent diffusivity.
B. Clavier, D. Zarzoso, D. Del-Castillo-Negrete, E. Frénod. Generative-machine-learning surrogate model of plasma turbulence. Physical Review E , 2025, 111 (1), pp.L013202. ⟨10.1103/PhysRevE.111.L013202⟩. ⟨hal-04966199⟩
B. Clavier, D. Zarzoso, Diego Del-Castillo-Negrete, E. Frénod. A generative machine learning surrogate model of plasma turbulence. Physical Review E , 2025, 111 (1), pp.L013202. ⟨10.1103/PhysRevE.111.L013202⟩. ⟨hal-04600564⟩ Plus de détails...
State-of-the-art techniques in generative artificial intelligence are employed for the first time to construct a surrogate model for plasma turbulence that enables long time transport simulations. The proposed GAIT (Generative Artificial Intelligence Turbulence) model is based on the coupling of a convolutional variational auto-encoder, that encodes precomputed turbulence data into a reduce latent space, and a deep neural network and decoder that generate new turbulence states 400 times faster than the direct numerical integration. The model is applied to the Hasegawa-Wakatani (HW) plasma turbulence model, that is closely related to the quasigeostrophic model used in geophysical fluid dynamics. Very good agreement is found between the GAIT and the HW models in the spatio-temporal Fourier and Proper Orthogonal Decomposition spectra as well as in the flow topology characterized by the Okubo-Weiss decomposition. Agreement is also found in the probability distribution function of particle displacements and the effective turbulent diffusivity.
B. Clavier, D. Zarzoso, Diego Del-Castillo-Negrete, E. Frénod. A generative machine learning surrogate model of plasma turbulence. Physical Review E , 2025, 111 (1), pp.L013202. ⟨10.1103/PhysRevE.111.L013202⟩. ⟨hal-04600564⟩
