# Using AI for GW detection, Classification and Parameter Estimation

- Institution: CERN
- Speaker: Huw Haigh
- Year: 2026
- Language: English
- Source: [CERN](https://videos.cern.ch/record/3025582)
- Licence: [CERN](https://copyright.web.cern)
- Who can watch: Teens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

We present a study of deep convolutional autoencoders applied to anomaly detection of GW signals. This initial work focuses on short-duration signals (< 2s), corresponding to mergers that involve, or form, intermediate mass black holes. These burst-like signals are notably difficult to disentangle from both background noise and glitches that may occur during data taking. We utilise the simulated noise and merger catalogue provided as part of the Einstein Telescope Mock Data Challenge. Weak supervision is employed during training, whereby the model is directly optimised to separate 2D spectrograms containing IMBH merger signals (injected into ET noise) from those containing only noise.

The model shows excellent results in recovering the targeted IMBH merger signals, and a strong ability to generalise to masses below those seen during training. Current work focuses on the inclusion of glitches in training, with more complex network architecture being tested to provide 3-way noise, glitch and signal classification. Furthermore, the inclusion of networks purposed towards parameter estimation is under investigation, with the aim to thereby develop a classification and parameter estimation pipeline that is able to handle the high rate and diversity of signals we can expect in the Einstein Telescope era.

00:00:00 Slide 1

00:00:26 Slide 2

00:00:52 Slide 3

00:01:12 Slide 4

00:03:14 Slide 5

00:04:36 Slide 6

00:05:20 Slide 7

00:06:38 Slide 8

00:07:48 Slide 9

00:08:39 Slide 10

00:09:31 Slide 11

00:10:14 Slide 12

00:12:03 Slide 13

00:12:42 Slide 14

00:13:10 Slide 15

00:13:22 Slide 16

00:14:23 Slide 17

00:14:56 Slide 18

00:17:15 Slide 19

00:19:01 Slide 20

## Lectures

1. [Using AI for GW detection, Classification and Parameter Estimation](https://invisiblenetwork.ai/learn/cern/3025582/40698db2da02), 21 min (CERN's player)