# Self-supervised Anomaly Detection for Narrowband SETI

## TL;DR

This paper introduces a self-supervised deep learning model for anomaly detection in SETI data, capable of handling large unlabeled datasets and complex interference, with potential to generalize to various signal types.

## Contribution

It presents a novel generative self-supervised model for anomaly detection in SETI spectrograms, enhancing generalization to different signal types without requiring labeled data.

## Key findings

- Effective anomaly detection on narrowband signals
- Demonstrates potential for generalization to other signal types
- Operates well with large unlabeled datasets

## Abstract

The Search for Extra-terrestrial Intelligence (SETI) aims to find technological signals of extra-solar origin. Radio frequency SETI is characterized by large unlabeled datasets and complex interference environment. The infinite possibilities of potential signal types require generalizable signal processing techniques with little human supervision. We present a generative model of self-supervised deep learning that can be used for anomaly detection and spatial filtering. We develop and evaluate our approach on spectrograms containing narrowband signals collected by Breakthrough Listen at the Green Bank telescope. The proposed approach is not meant to replace current narrowband searches but to demonstrate the potential to generalize to other signal types.