activity
20242026
collaborators

8 papers

cs.LG2026

RECAST: A Machine-Learning Framework for Correction and Super-Resolution of Coarse-Grid PDE Solvers

Maryam Reza, Farbod Faraji

Coarse-grid numerical solvers can substantially reduce the computational cost of time-dependent PDE simulation, but under-resolution often degrades both the trajectory and the spat…

cs.IT2026

Space-Time Information Interchangeability in Dynamical Systems: Conditions and Bounds for Replacing Spatial Sensors with Temporal Histories

Maryam Reza, Farbod Faraji

Many dynamical-state reconstruction problems seek to infer a high-dimensional spatial state from measurements at only a few locations. Because the governing dynamics couple evoluti…

physics.plasm-ph2026

Machine-Learning-Enabled Full-State Reconstruction of Fusion Plasmas from Minimal Sensor Measurements

Maryam Reza, Farbod Faraji

Plasma in nuclear fusion reactors is only partially observable: diagnostics are constrained by limited access, cost, and the harsh plasma environment, while high-fidelity simulatio…

physics.plasm-ph2025

Benchmark for two-dimensional large scale coherent structures in partially magnetized ExB plasmas -- Community collaboration & lessons learned

Andrew T. Powis, Eduardo Ahedo, Alejandro Álvarez Laguna +38

Low-temperature plasmas are essential to both fundamental scientific research and critical industrial applications. As in many areas of science, numerical simulations have become a…

physics.plasm-ph2025

Investigation of the influence of electrostatic excitation on instabilities and electron transport in ExB plasma configurations

Maryam Reza, Farbod Faraji, Aaron Knoll +1

Partially magnetized plasmas in ExB configurations - where the electric and magnetic fields are mutually perpendicular - exhibit a cross-field transport behavior, which is widely b…

physics.plasm-ph2025

Multiscale autonomous forecasting of plasma systems' dynamics using neural networks

Farbod Faraji, Maryam Reza

Plasma systems exhibit complex multiscale dynamics, resolving which poses significant challenges for conventional numerical simulations. Machine learning (ML) offers an alternative…