Unsupervised Discovery of Inertial-Fusion Plasma Physics using Differentiable Kinetic Simulations and a Maximum Entropy Loss Function
This work addresses the challenge of understanding nonlinear plasma behavior for inertial fusion energy applications, representing a novel method for discovery rather than an incremental improvement.
The researchers tackled the problem of modeling complex plasma dynamics in inertial fusion by developing a differentiable kinetic solver and a domain-specific objective function, which led to the discovery of a previously unknown physical effect in an inertial-fusion configuration.
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. 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.