{"id":73347,"date":"2023-01-31T17:45:01","date_gmt":"2023-01-31T15:45:01","guid":{"rendered":"https:\/\/forklog.com\/en\/?p=73347"},"modified":"2025-09-09T13:40:08","modified_gmt":"2025-09-09T10:40:08","slug":"ai-detects-potential-extraterrestrial-radio-signals","status":"publish","type":"post","link":"https:\/\/forklog.com\/en\/ai-detects-potential-extraterrestrial-radio-signals\/","title":{"rendered":"AI Detects Potential Extraterrestrial Radio Signals"},"content":{"rendered":"

Researchers have developed a neural network that filters out noise and more effectively detects unusual cosmic radio signals in the search for extraterrestrial intelligence, as reported by Motherboard<\/a>.<\/p>\n

Participants in the SETI<\/span> project used observations of 820 stars in the form of 115 million data fragments. Then a model developed with TensorFlow and Python Keras libraries identified about 3 million signals of interest.<\/p>\n

The group reduced their number to 20,515 items. This is 100 times less than in the previous analysis conducted on the same dataset.<\/p>\n

In total, the team identified eight previously undetected potentially interesting signals. Further analysis could confirm their extraterrestrial origin. In that case, scientists would need to determine what technology they encountered.<\/p>\n

According to the study’s lead author Peter Ma, at best the signals could include embedded information about developments or even a set of technosignatures<\/a> of an extraterrestrial civilization.<\/p>\n

\n

\u201cBut we are not counting on that,\u201d Ma said.<\/p>\n<\/blockquote>\n

According to the study, the new approach completely removes the human factor from the search process.<\/p>\n

\n

\u201cEarlier, humans inserted machine-learning components into various pipelines to facilitate detection. This work relies entirely on the neural network [\u2026] and yields results unavailable to traditional algorithms,\u201d he said.<\/p>\n<\/blockquote>\n

They also noted that radio waves arriving from space can be easily confused with terrestrial ones. Separating these signals from one another could require enormous amounts of power and time, they added.<\/p>\n

According to Ma, the neural network significantly speeds up the process. The algorithm not only identifies and classifies data but also filters out terrestrial interference.<\/p>\n

Beyond a doubling of signal-processing speed compared with traditional methods, the neural network also enables a form of unconventional thinking.<\/p>\n

\n

\u201cTraditional algorithms operate with a predefined set of instructions developed by humans [\u2026]. Therefore, the model will only discover what we tell it,\u201d Ma said.<\/p>\n<\/blockquote>\n

According to him, the problem lies in the unknown nature of extraterrestrial signals. The neural network’s unconventional thinking will help study it without human bias, the scientist believes.<\/p>\n

In December 2022, researchers using AI discovered 1,000 previously unknown supernovae<\/a>.<\/p>\n

In July, the AI algorithm was trained to classify thousands of galaxies<\/a> in a second.<\/p>\n

Subscribe to ForkLog news on Telegram: ForkLog AI<\/a> \u2014 all the news from the world of AI!<\/p>\n","protected":false},"excerpt":{"rendered":"

Researchers have developed a neural network that filters out noise and more effectively detects unusual cosmic radio signals in the search for extraterrestrial intelligence.<\/p>\n","protected":false},"author":1,"featured_media":73348,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"select":"1","news_style_id":"1","cryptorium_level":"","_short_excerpt_text":"","creation_source":"","_metatest_mainpost_news_update":false,"footnotes":""},"categories":[3],"tags":[438,1170],"class_list":["post-73347","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-analysis","tag-artificial-intelligence","tag-space"],"aioseo_notices":[],"amp_enabled":true,"views":"13","promo_type":"1","layout_type":"1","short_excerpt":"","is_update":"","_links":{"self":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/73347","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/comments?post=73347"}],"version-history":[{"count":1,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/73347\/revisions"}],"predecessor-version":[{"id":73349,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/posts\/73347\/revisions\/73349"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media\/73348"}],"wp:attachment":[{"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/media?parent=73347"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/categories?post=73347"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/forklog.com\/en\/wp-json\/wp\/v2\/tags?post=73347"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}