6 papers
GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
Fabian Paischer, Gianluca Galletti, William Hornsby +5
Nuclear fusion plays a pivotal role in the quest for reliable and sustainable energy production. A major roadblock to viable fusion power is understanding plasma turbulence, which…
Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics
Anna Zimmel, Paul Setinek, Gianluca Galletti +2
Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe perfor…
SIMSHIFT: A Benchmark for Adapting Neural Surrogates to Distribution Shifts
Paul Setinek, Gianluca Galletti, Thomas Gross +3
Neural surrogates for Partial Differential Equations (PDEs) often suffer significant performance degradation when evaluated on problem configurations outside their training distrib…
Towards Multi-Fidelity Scaling Laws of Neural Surrogates in CFD
Paul Setinek, Gianluca Galletti, Johannes Brandstetter
Scaling laws describe how model performance grows with data, parameters and compute. While large datasets can usually be collected at relatively low cost in domains such as languag…
Neural operator surrogate models of plasma edge simulations: feasibility and data efficiency
N. Carey, L. Zanisi, S. Pamela +7
The inclusion of high-fidelity simulations of SOL turbulence and transient MHD events such as ELMs in highly iterative applications remains computationally prohibitive, limiting th…
5D Neural Surrogates for Nonlinear Gyrokinetic Simulations of Plasma Turbulence
Gianluca Galletti, Fabian Paischer, Paul Setinek +5
Nuclear fusion plays a pivotal role in the quest for reliable and sustainable energy production. A major roadblock to achieving commercially viable fusion power is understanding pl…