LSTM Nonlinear Dynamics Predictor for Accelerating Data Generation in Ultrafast Optics and Laser System Design
Jack Hirschman, Minyang Wang, Sergio Carbajo · 2023
Ultrafast optics and high power laser systems are the backbone of nearly every major industry from semiconductor manufacturing and telecommunications to advanced medical procedures and next-generation energy and defense solutions. With the increasing integration of machine learning (ML) into laser system design, there is a growing demand for efficient data generation. We present a novel start-to-end (S2E) framework aimed at complex laser systems, not only achieving this large data generation but also enabling reverse engineering, ground-up design, and inverse design. The S2E framework is modular and can be tailored to the specific application under test. The simulation output can then be used in a wide variety of ML tasks from predicting pulse propagation behavior and laser system controls optimization to diagnostic characteristics extraction. However, the models, by necessity, involve solving complex cascaded nonlinear systems of equations, a significant time bottleneck in generating large quantities of data. To demonstrate a broad impact application of ML enhancing ultrafast optics simulations, we aim our studies on using long short-term memory (LSTM) networks to replace solving the nonlinear Schrödinger equation for a complex nonlinear process. We demonstrate how these models can provide significant speed-up for large data generation and can ultimately further enable an S2E framework to be applied broadly across applications in the ultrafast optics field.