A deep-learning search for technosignatures from 820 nearby stars

2023/01/30 by Peter Xiangyuan, Peter Xiangyuan Ma, Cherry Ng +18 · 1 voice · 3 citations
Computer Science · Physics and Astronomy · #Gamma-ray bursts and supernovae #Planetary Science and Exploration #Space Science and Extraterrestrial Life #astro-ph.IM #cs.LG

paper · pdf · doi:10.1038/s41550-022-01872-z

openalex publication_date 2023/01/30 · openalex created_date 2023/01/31 · openalex updated_date 2026/07/29

Abstract

The goal of the Search for Extraterrestrial Intelligence (SETI) is to quantify the prevalence of technological life beyond Earth via their "technosignatures". One theorized technosignature is narrowband Doppler drifting radio signals. The principal challenge in conducting SETI in the radio domain is developing a generalized technique to reject human radio frequency interference (RFI). Here, we present the most comprehensive deep-learning based technosignature search to date, returning 8 promising ETI signals of interest for re-observation as part of the Breakthrough Listen initiative. The search comprises 820 unique targets observed with the Robert C. Byrd Green Bank Telescope, totaling over 480, hr of on-sky data. We implement a novel beta-Convolutional Variational Autoencoder to identify technosignature candidates in a semi-unsupervised manner while keeping the false positive rate manageably low. This new approach presents itself as a leading solution in accelerating SETI and other transient research into the age of data-driven astronomy.

Citations

• Auto-Encoding Variational Bayes
• Practical Bayesian Optimization of Machine Learning Algorithms
• Backpropagation Applied to Handwritten Zip Code Recognition
• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python

Cited by

• COSMIC’s Large-scale Search for Technosignatures during the VLA Sky Survey: Survey Description and First Results
• Blink and you'll miss it -- How Technological Acceleration Shrinks SETI's Narrow Detection Window
• Using anomaly detection to search for technosignatures in Breakthrough Listen observations

Discussions

• A deep-learning search for technosignatures of 820 nearby stars [hn, 4 points, 0 comments]

Related

• A Novel Technosignature Search in the Breakthrough Listen Green Bank Telescope Archive
• Using anomaly detection to search for technosignatures in Breakthrough Listen observations
• A Search for Technosignatures Around 11,680 Stars with the Green Bank Telescope at 1.15–1.73 GHz
• SETI@home: Data Analysis and Findings
• A Search for Extraterrestrial Technosignatures in Archival FAST Survey Data Using a New Procedure