Keywords: automatic differentiation, plasma physics, simulations, partial differential equations, differentiable programming, kinetic plasma physics, automated physics discovery
TL;DR: We train a neural network through a differentiable, plasma physics, PDE solver using the maximum entropy principle in a setting relevant to inertial fusion and find that the optimization process discovers a novel non-linear physical mechanism.
Abstract: Plasma supports collective modes and particle-wave interactions that leads to complex behavior in inertial fusion energy applications. While plasma can sometimes be modeled as a charged fluid, a kinetic description is useful towards the study of nonlinear effects in the higher dimensional momentum-position phase-space that describes the full complexity of plasma dynamics. We create a differentiable solver for the plasma kinetics 3D partial-differential-equation and introduce a domain-specific objective function based on the maximum entropy principle. Using this framework, we perform gradient-based optimization of neural networks that provide forcing function parameters to the differentiable solver given a set of initial conditions. We apply this to an inertial-fusion relevant configuration and find that the optimization process exploits a novel physical effect that has previously remained undiscovered.
Track: Original Research Track