Author(s)
| Name | Institution | Mail Address | |
|---|---|---|---|
| Luca Rei | INFN Sezione diGenova | luca.rei@ligo.org |
How to Obtain Support
| luca.rei@ligo.org |
General Information
| ML/DL Technologies | LSTM |
|---|---|
| Science Fields | General Relativity |
| Difficulty | Low |
| Language | English |
| Type | fully annotated / runnable / external resource / ... |
Software and Tools
| Programming Language | Python |
|---|---|
| ML Toolset | Keras + Tensorflow |
| Suggested Environments | bare Linux Node |
Needed datasets
| Data Creator | Virgo/Ligo |
|---|---|
| Data Type | real acquisition |
| Data Size | 1 GB |
| Data Source | IGWN collaboration |
Short Description of the Use Case
Gravitational waves are 'ripples' in space-time caused by some of the most violent and energetic processes in the Universe. Albert Einstein predicted the existence of gravitational waves in 1916 in his general theory of relativity. Einstein's mathematics showed that massive accelerating objects (such as neutron stars or black holes orbiting each other) would disrupt space-time in such a way that 'waves' of undulating space-time would propagate in all directions away from the source. These cosmic ripples would travel at the speed of light, carrying with them information about their origins, as well as clues to the nature of gravity itself.
While the processes that generate gravitational waves can be extremely violent and destructive, by the time the waves reach Earth they are thousands of billions of times smaller! In fact the amount of space-time wobbling they generated is of the magnitude of a 1000 times smaller than the nucleus of an atom!
A sensitive class of detector uses a laser Michelson interferometer to measure gravitational-wave induced motion between separated 'free' masses.
Interferometers are investigative tools used in many fields of science and engineering. They are called interferometers because they work by merging two or more sources of light to create an interference pattern, which can be measured and analyzed; hence 'Interfere-o-meter', or interferometer. The interference patterns generated by interferometers contain information about the object or phenomenon being studied. They are often used to make very small measurements that are not achievable any other way. This is why they are so powerful for detecting gravitational waves--LIGO's interferometers are designed to measure a distance 1/10,000th the width of a proton.
The basic configuration of a Michelson laser interferometer is shown at right. It consists of a laser, a beam splitter, a series of mirrors, and a photodetector (the black dot) that records the interference pattern.
simple example on how use an autoenconder to efficient data codings and foldings
"An autoencoder is a type of artificial neural network used to learn efficient data codings in an unsupervised manner. The aim of an autoencoder is to learn a representation (encoding) for a set of data, typically for dimensionality reduction, by training the network to ignore signal “noise”."
In the following we will use the autoencoder to analyse a gravitation wave format file and learn how to ignore some sources of noise, obtain a signal cleaned and size reductioned
All data files used for this exercise are public and can be obtained from the Ligo website at https://www.gw-openscience.org/archive/O2_16KHZ_R1/ in the gwf format or hdf5 format
At https://www.gw-openscience.org/ you could find many interesting tutorial on how read plot and analyze with standard technique the gravitational files
How to execute it
Download data files (any files at https://www.gw-openscience.org/data/ will be good) and execute the Jupyter notebook (https://github.com/luca-rei/ml-genoa). For convenience in the Jupyter we assume to work with hdf5 files,the interesting part is how the output of an encoded signal (gw) differ from an encoded noise (compare their size and their entropy). For example try to encode different data...
Annotated Description
References
https://blog.keras.io/building-autoencoders-in-keras.html