\n
![\"EarthSnap\"\/](\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2025\/12\/1766790432_598_earthsnap-banner-news.webp.webp\")
\n<\/a><\/p>\n
That type of conversion has to be simulated before any parameter can be adjusted. <\/p>\n
Until now, that simulation was a persistent slowdown. A team of physicists has replaced it with a model that runs in milliseconds.<\/p>\n
The machine behind it<\/p>\n
Jack Hirschman at SLAC National Accelerator Laboratory (SLAC<\/a>) led a team with researchers from the University of California, Los Angeles (UCLA<\/a>). <\/p>\n Together they addressed one of the most stubborn computational bottlenecks in modern laser physics. The target was the Linac Coherent Light Source II (LCLS-II), a next-generation X-ray facility. <\/p>\n The machine produces pulses brief and intense enough to photograph individual molecules in the middle of a reaction. This requires a sequence of steps. <\/p>\n Ultraviolet laser<\/a> light strikes a metal surface, releasing electrons. Those electrons are accelerated to the speed of light, then steered into a magnetic assembly that makes them radiate X-rays.<\/p>\n The ultraviolet pulse that starts that chain begins life as infrared light. It has to be converted twice before it can do the job.<\/p>\n The conversion process<\/p>\n When two light waves enter a specially engineered crystal at the right angle, their electric fields interact.<\/p>\n This generates a new wave at the combined frequency. This is the foundation of nonlinear optics<\/a>. At LCLS-II, that process is called sum-frequency generation. <\/p>\n It happens twice in sequence, infrared becomes green, then green becomes ultraviolet. Each conversion requires a separate crystal and its own precise calibration.<\/p>\n A study<\/a> on the facility\u2019s laser architecture shows how sensitive the electron beam quality is to the precision of those conversions. <\/p>\n Small irregularities in the UV pulse translate directly into the beam degradation.<\/p>\n Looking inside the crystals<\/p>\n Before engineers can adjust any parameter in that chain, they need a simulation of what happens inside the crystals. <\/p>\n The conventional approach solves a wave equation hundreds of times across the crystal\u2019s length. This is done slowly and accurately.<\/p>\n At LCLS-II, that computation was too slow for real-time feedback. <\/p>\n Engineers ran simulations offline, reviewed results, and adjusted manually, creating a cycle with no path to live control.<\/p>\n A network learns physics<\/p>\n Hirschman\u2019s team built a replacement using a type of recurrent neural network called a long short-term memory network. <\/p>\n The network was designed for data that evolves in sequence, offering a fundamentally different way to solve the problem.<\/p>\n Deep learning models of this type learn temporal patterns during training. That makes these models a natural fit for tracking how a light pulse changes step by step as it moves through a crystal<\/a>.<\/p>\n Working entirely in the frequency domain, the network skips the back-and-forth toggling between frequency and time representations.<\/p>\n Training on difficult cases<\/p>\n Thousands of simulations from the conventional solver formed the training data, covering a wide range of pulse shapes. <\/p>\n The team included hard cases deliberately, studying pulses with spectral gaps and strong phase variations, exactly where simpler approximation methods tend to fail.<\/p>\n The LSTM didn\u2019t just predict the main output pulse. It accurately tracked all three light fields<\/a> passing through the crystal simultaneously, including the two input waves and the generated output.<\/p>\n No previous surrogate for this class of interaction had modeled all three coupled fields at once across such difficult pulse shapes.<\/p>\n Several times faster<\/p>\n Run on a graphics processing unit, the surrogate completes each simulation in milliseconds. <\/p>\n This is more than 250 times faster than the conventional solver. The accuracy holds across the full range of test cases, including the more difficult ones.<\/p>\n Earlier research<\/a> on AI surrogates in laser physics had shown that speedups of this scale were achievable.<\/p>\n This study demonstrates the approach using three coupled fields in a working accelerator\u2019s actual laser system. This was a more demanding test than any prior work.<\/p>\n Control is now possible<\/p>\n With a surrogate that runs in milliseconds, the simulation can connect directly to the laser control system. <\/p>\n Engineers could adjust parameters and see predicted outcomes in real time, before making any physical changes.<\/p>\n The team\u2019s broader goal is to create digital twins. These would be full simulation replicas of complex laser systems that update continuously alongside the real hardware. <\/p>\n For the first time, the nonlinear crystal conversion step at the core of LCLS-II\u2019s laser<\/a> chain can be modeled fast enough to inform live operational decisions.<\/p>\n That means operators could adjust the frequency conversion optics with immediate predictive feedback, cutting the trial-and-error cycle that currently requires offline computation.<\/p>\n The approach could extend to other high-power laser systems, short-pulse biomedical imaging platforms, and quantum photonics experiments. <\/p>\n The method could be applied wherever coupled nonlinear crystal physics need to be simulated rapidly.<\/p>\n The study is published in the journal Advanced Photonics<\/a>.<\/p>\n \u2014\u2013<\/p>\n Like what you read? Subscribe to our newsletter<\/a> for engaging articles, exclusive content, and the latest updates.<\/p>\n Check us out on EarthSnap<\/a>, a free app brought to you by Eric Ralls<\/a> and Earth.com.<\/p>\n \u2014\u2013<\/p>\n","protected":false},"excerpt":{"rendered":"Building a world-class X-ray experiment begins with a laser operating at the wrong frequency. Before it becomes useful,…\n","protected":false},"author":2,"featured_media":457817,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[24],"tags":[85,46,370,141],"class_list":["post-457816","post","type-post","status-publish","format-standard","has-post-thumbnail","category-physics","tag-il","tag-israel","tag-physics","tag-science"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/457816","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=457816"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/457816\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/457817"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=457816"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=457816"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=457816"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}