Machine Learning Pushes High-Power Lasing Limits

Collaborating scientists from Lawrence Livermore National Laboratory (LLNL), Fraunhofer Institute for Laser Technology ILT (Fraunhofer ILT), and Extreme Light Infrastructure (ELI) are leading an effort to optimize high-intensity high-repetition rate laser technology using machine learning. The collaboration, the researchers said, aims to increase understanding and practical application of high-intensity lasers.

“Our goal was to demonstrate robust diagnosis of laser-accelerated ions and electrons from solid targets at a high intensity and repetition rate,” said LLNL lead researcher Matthew Hill. “Supported by rapid feedback from a machine-learning optimization algorithm to the laser front end, it was possible to maximize the total ion yield of the system.”

International team of researchers from LLNL, Fraunhofer ILT, and ELI at the ELI Beamlines Facility, Prague. Courtesy of ELI ERIC.

Over 4000 shots were fired during the campaign, which consistently exceeded laser intensities of 3 × 10²¹ W/cm² onto solid targets, demonstrating optimization of ion yield above the nominal baseline performance. The experiment took place at the ELI Beamlines Facility in Czechia, where the researchers used the state of the art High-Repetition-Rate Advanced Petawatt Laser System (L3-HAPLS) to generate protons in the ELIMAIA laser-plasma ion accelerator. The L3-HAPLS laser is renowned for its laser performance repeatability, precision, and beam quality, and has the ability to generate intense laser pulses at a high repetition rate to drive the generation of secondary sources such as electrons, ions, and x-rays. The shot-to-shot repeatability of L3-HAPLS allows scientists to focus on the understanding of laser-plasma interaction physics.

According to the researchers, the effort supports future advancements in fields such as medical therapy, materials science, and non-destructive analysis in areas such as cultural heritage and archaeology.