\n
\n
![\"EarthSnap\"\/](\"https:\/\/www.newsbeep.com\/nz\/wp-content\/uploads\/2026\/05\/earthsnap-banner-news.webp.webp\")
\n<\/a><\/p>\n
The software is called RAVEN, short for RAnking and Validation of ExoplaNets. A team at the University of Warwick<\/a> built it to handle a stubborn problem: separating genuine planets from a long list of imposters that fool detection tools.<\/p>\n Dr. Marina Lafarga Magro, a Postdoctoral Researcher there, led the work. Running RAVEN on TESS data<\/a> from the first four years of the mission, her team turned up more than 100 new exoplanets and flagged thousands more strong candidates.<\/p>\n \u201cUsing our newly developed RAVEN pipeline, we were able to validate 118 new planets, and over 2,000 high-quality planet candidates, nearly 1,000 of them entirely new,\u201d said Lafarga, lead author of the study.<\/p>\n How RAVEN works<\/p>\n Telescopes flag planet candidates by spotting tiny dips in starlight. Plenty of other things can mimic that signal \u2013 a pair of stars eclipsing<\/a> each other, a faint background star bleeding in, instrument noise. Sorting real from fake takes time.<\/p>\n RAVEN takes a different route. Its developers fed it hundreds of thousands of simulated examples \u2013 synthetic planets and synthetic look-alikes \u2013 and let machine-learning models learn the difference.<\/p>\n Once trained, RAVEN handles the whole chain. Finding signals, screening them, confirming the strongest with math. The full pipeline design appears in a separate paper<\/a> from earlier this year.<\/p>\n \u201cWe trained machine learning models to identify patterns in the data that can tell us the type of event we have detected,\u201d said Dr. Andreas Hadjigeorghiou, who led the pipeline\u2019s development at Warwick.<\/p>\n New exoplanets among the haul<\/p>\n The team aimed RAVEN at roughly 2.2 million ordinary stars observed by TESS during sectors 1 through 55, the mission\u2019s first four years of full-sky scanning.<\/p>\n They limited the search to planets with orbits shorter than 16 days. Short, but still wide enough to capture the most interesting close-in worlds.<\/p>\n All told, 118 planets cleared validation, 31 of which had never been spotted before. Beyond that, RAVEN flagged more than 2,000 high-confidence candidates that haven\u2019t been formally validated yet.<\/p>\n About 1,000 of those are brand new. A handful are unusual single-transit candidates \u2013 signals that crossed a star only once or twice during the observation window, suggesting a much longer orbit.<\/p>\n Strange new worlds<\/p>\n Some of the most interesting finds belong to two rare categories. Ultra-short-period planets \u2013 worlds that complete a full orbit in less than 24 hours \u2013 turned up several times in the haul.<\/p>\n So did residents of the Neptunian desert, a stretch of orbits and sizes where Neptune-sized planets are weirdly absent. A 2016 paper<\/a> first mapped its boundaries, but counting the few inhabitants precisely had been harder.<\/p>\n The catalog also picks up tightly packed multi-planet systems with previously unknown companions. In these systems, worlds are packed close enough to one star to tug on each other gravitationally.<\/p>\n Counting close-in planets<\/p>\n The bigger payoff shows up in a companion study<\/a> led by Dr. Kaiming Cui, also at Warwick. With a clean planet sample in hand, the team measured how often close-in planets show up around Sun-like stars.<\/p>\n Their answer: about 9 to 10 percent of Sun-like stars host one. That tracks earlier results from NASA\u2019s Kepler mission, but the new measurement cuts the uncertainty by up to a factor of 10.<\/p>\n That same clean sample also produced the Neptunian desert\u2019s first head count. Such planets show up around only 0.08 percent of Sun-like stars.<\/p>\n \u201cFor the first time, we can put a precise number on just how empty this desert is,\u201d said Cui, lead author of the population paper.<\/p>\n The road ahead<\/p>\n All of it is now public \u2013 the full catalog of validated planets, the unvalidated candidates, and tools to inspect them. Other researchers can pick targets for follow-up \u2013 telescope time to confirm a planet\u2019s mass, or probe its atmosphere with instruments already in use.<\/p>\n Neptunian desert candidates and ultra-short-period worlds will be especially attractive to researchers studying atmospheres, since they sit at the strange edges of what current planet<\/a>-formation theories predict.<\/p>\n ESA\u2019s upcoming PLATO mission will need exactly this kind of curated target list when it launches. Cleaner samples mean faster science when new instruments come online.<\/p>\n A clearer count of new exoplanets<\/p>\n Until this work, no one had directly measured how rare planets in the Neptunian desert really are. Now there is a number. A solid one.<\/p>\n And the Kepler-era estimates for close-in planet occurrence, which were long the gold standard, have been independently confirmed and tightened by a different mission, telescope, and pipeline.<\/p>\n For exoplanet researchers, that opens up planet-formation questions that were previously stuck in statistical fog. Why are some orbits empty? How do tightly packed systems stay stable?<\/p>\n With a cleaner planet count to anchor the math, the next round of theory has more to work with than guesswork \u2013 and the same approach can sweep through years of TESS data that is still waiting in the archive.<\/p>\n The study is published in Monthly Notices of the Royal Astronomical Society<\/a>.<\/p>\n \u2014\u2013<\/p>\n Like what you read?\u00a0Subscribe to our newsletter\u00a0<\/a>for engaging articles, exclusive content, and the latest updates.<\/p>\n Check us out on\u00a0EarthSnap\u00a0<\/a>, a free app brought to you by\u00a0Eric Ralls\u00a0<\/a>and Earth.com.<\/p>\n \u2014\u2013<\/p>\n","protected":false},"excerpt":{"rendered":"Seven years into its mission, NASA\u2019s TESS satellite has already confirmed roughly 700 exoplanets. That sounds like a…\n","protected":false},"author":2,"featured_media":422865,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[23],"tags":[111,139,69,147,392],"class_list":["post-422864","post","type-post","status-publish","format-standard","has-post-thumbnail","category-space","tag-new-zealand","tag-newzealand","tag-nz","tag-science","tag-space"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/422864","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/comments?post=422864"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/posts\/422864\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media\/422865"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/media?parent=422864"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/categories?post=422864"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/nz\/wp-json\/wp\/v2\/tags?post=422864"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}