Dr Mufei Luo

Abstract:

We introduce a time-embedded convolutional neural network (TCNN) for modeling spatiotemporal heat transport in plasmas, particularly under strongly nonlocal conditions. In our earlier work, the Luciani-Mora-Virmont (LMV) Informed Neural Network (LINN) (Luo , ) combined prior knowledge from the LMV model with kinetic Particle-in-Cell (PIC) data to improve kernel-based heat-flux predictions. While effective under moderately nonlocal conditions, LINN produced physically inconsistent kernels in strongly time-dependent regimes due to its reliance on the quasistationary LMV formulation. To overcome this limitation, TCNN is designed to capture the coupled evolution of both the normalized heat flux and the characteristic nonlocality parameter using a unified neural architecture informed by underlying physical principles. Trained on fully kinetic PIC simulations, TCNN accurately reproduces nonlocal dynamics across a broad range of collisionalities. Our results demonstrate that the combination of time modulation, coupled prediction, and convolutional depth significantly enhances predictive performance, offering a data-driven yet physically consistent framework for multiscale plasma transport problems.

Abstract:

<jats:p>We present a data-driven framework for the modeling of nonlocal heat transport in plasmas using a nonlocal theory-informed neural network trained on kinetic particle-in-cell simulations that span both local and nonlocal regimes. The model learns spatio-temporal heat flux kernels directly from simulation data, capturing dynamic transport behaviors beyond the reach of classical formulations. Unlike time-independent kernel models such as Luciani-Mora-Virmont and Schurtz-Nicolaï-Busquet models, our approach yields physically grounded, time-evolving kernels that adapt to varying plasma conditions. The resulting predictions show strong agreement with kinetic benchmarks across regimes. This offers a promising direction for data-driven modeling of nonlocal heat transport and contributes to a deeper understanding of plasma dynamics.</jats:p>

Abstract:

Autoresonant phase locking of the plasma wakefield to the beat frequency of two driving lasers offers advantages over conventional wakefield acceleration methods, since it requires less demanding laser parameters and is robust to variations in the target plasma density. Here, we investigate the kinetic and nonlinear processes that come into play during autoresonant plasma beat-wave acceleration of electrons, their impact on the field amplitude of the accelerating structure, and on acceleration efficiency. Particle-in-cell simulations show that the process depends on the plasma density in a nontrivial way but can be reliably modeled under specific conditions. Beside recovering previous fluid results in the deeply underdense plasma limit, we demonstrate that robust field excitation can be achieved within a fully kinetic self-consistent modeling. By adjusting the laser properties, we can amplify the electric field to the desired level, up to wave breaking, and efficiently accelerate particles; we provide suggestions for optimized laser and plasma parameters. This versatile and efficient acceleration scheme, producing electrons from tens to hundreds of MeV energies, holds promise for a wide range of applications in research industry and medicine.

Abstract: