Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations

TL;DR

This paper introduces Spin-Neural ODEs, a neural network approach that accurately predicts spintronic device behavior with minimal data, significantly accelerating simulations and handling noisy experimental data effectively.

Contribution

The authors adapt Neural Ordinary Differential Equations to spintronics, enabling fast, accurate predictions of device dynamics and experimental responses with minimal training data.

Findings

Achieved over 200x speedup in simulating magnetic skyrmions

Successfully predicted noisy responses of spintronic nano-oscillators

Demonstrated generalization to other electronic device dynamics

Abstract

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation of an experimental physical system. Here we show that a dynamical neural network, trained on a minimal amount of data, can predict the behavior of spintronic devices with high accuracy and an extremely efficient simulation time, compared to the micromagnetic simulations that are usually employed to model them. For this purpose, we re-frame the formalism of Neural Ordinary Differential Equations (ODEs) to the constraints of spintronics: few measured outputs, multiple inputs and internal parameters. We demonstrate with Spin-Neural ODEs an acceleration factor over 200 compared to micromagnetic simulations for a complex problem -- the simulation of a reservoir computer made of magnetic skyrmions (20 minutes compared to three days). In a second realization, we show that we can predict the noisy response of experimental spintronic nano-oscillators to varying inputs after training Spin-Neural ODEs on five milliseconds of their measured response to different excitations. Spin-Neural ODE is a disruptive tool for developing spintronic applications in complement to micromagnetic simulations, which are time-consuming and cannot fit experiments when noise or imperfections are present. Spin-Neural ODE can also be generalized to other electronic devices involving dynamics.