Hybrid FDTD and Machine Learning Framework for Nonlinear Wave Dynami in Cold Plasma

Author: Mr. Arjun Singh
Affiliation: Mechatronics Engineering Department, Parul University, Vadodara, Gujarat, India
Published: September 3, 2025
DOI: Yet to assign
Journal: Vijoriya International Journal for Research & Innovation
ISSN: Yet to Assign

📄 Abstract

We present a novel hybrid computational framework that couples classical finite-difference timedomain (FDTD) simulation with machine learning (ML) to model and forecast nonlinear wave propagation in a cold plasma. In this study, a one-dimensional (1D) FDTD Maxwell–Drude solver is implemented in Google Colab to simulate electromagnetic waves in a cold (collisionless) plasma. The governing equations (Maxwell’s curl equations coupled to the cold-plasma polarization equation) are solved with absorbing boundary conditions. To extract nonlinear features (such as wave steepening) and to predict future wave profiles, we employ an autoencoder to compress the simulated field snapshots into a lowdimensional latent space, and a shallow neural network to forecast the wave evolution in that latent space. Quantitative results are presented, including the dispersion relation versus plasma frequency and time-domain field amplitude growth. We demonstrate that the ML model accurately reproduces the FDTD wave envelopes and can forecast beyond the simulation horizon. Compared to pure simulation methods, our hybrid pipeline offers interpretable latent variables and rapid

extrapolation capabilities, making it a novel and impactful tool for plasma wave dynamics and forecasting.

🔑 Keywords

Cold plasma, FDTD, Maxwell–Drude solver, machine learning, autoencoder, nonlinear wave propagation, forecasting, electromagnetic simulation