Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
This work unrolls the curvilinear mesh into three fixed-size image tensors whose layout preserves cell adjacency and inverts exactly, letting a convolutional network act on the geometry without loss of information.
Gabriele Gianuzzo, S. Dasbach, Fleur Hendriks et al.
· 0 citations