1
Emille E. O. Ishida
Laboratoire de Physique de Clermont - Université Clermont-Auvergne
Clermont Ferrand, France
SNAD: Machine learning assisted discovery in astronomy
IN2P3/IRFU Machine Learning workshop
17 March 2021 - zoom
SuperNova Anomaly Detection … historically
What is SNAD?
International collaboration aimed to develop machine learning tools which can optimize astronomical discovery in the era of big data.
arXiv:astro-ph/1905.11516
arXiv:astro-ph/1909.13260
arXiv:astro-ph/2012.01419
France - Russia - USA
In algorithmic terms ...
Anomaly Detection
“An anomaly is an observation which deviates so much from the other observations as to arouse suspicions that it was generated by a different mechanism”
Hawkins, 1980
Philosophically it is about discovery ...
Machine Learning only produces recommendations
Observed data set
Anomaly detection algorithm
Potentially interesting anomalies:
Expert analysis
Not interesting
Interesting
Very interesting!
SNAD work philosophy:
Machine Learning only produces recommendations
Observed data set
Anomaly detection algorithm
Potentially interesting anomalies:
Expert analysis
Not interesting
Interesting
Very interesting!
Get more data
or
Publication
6
Experiment
First try: the Open Supernova Catalog
Pruzhinskaya et al., 2019 - MNRAS - https://arxiv.org/abs/1905.11516
Public catalog of supernova, known to have some contamination
.. after selection and pre-processing, ~2000 objects
Many trees make a forest …
Isolation Forest
8
Experiment
First try: the Open Supernova Catalog
Pruzhinskaya et al., 2019 - MNRAS - https://arxiv.org/abs/1905.11516
Active Galactic Nuclei
Binary microlensing
Anomaly detection:
Second Try: Zwicky Transient Facility DR3
Figure by Maria Pruzhinskaya
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Experiment
Second Try: Zwicky Transient Facility DR3
Visualization generated with the SNAD ZTF viewer: https://ztf.snad.space/
ZTF Data Release 3
was expected to contain stars and periodic variables (no transients)
Experiment
Second Try: Zwicky Transient Facility DR3
Results:
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Experiment
Second Try: Zwicky Transient Facility DR3
Results:
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Still super high!
Philosophical question:
What is a scientifically interesting anomaly?
Problem: Still high incidence of “non-important” anomalies (68 % for ZTF DR3)
Goal: Maximize the number of scientifically interesting anomalies shown to
the expert
Strategy:
Incorporate human knowledge in the machine learning model
a. k.a. adaptive learning ...
The recommendation system can get better with time ...
Machine Learning only produces recommendations
Observed data set
Anomaly detection algorithm
Potentially interesting anomalies:
Expert analysis
Not interesting
Interesting
Very interesting!
Get more data
or
Publication
15
Human in the loop:
Active Anomaly Detection
Data
Object with highest anomaly score
Anomaly Detection Algorithm
Show to the expert:
Is this an anomaly?
Yes/No
Das, S., et al., 2017, in Workshop on Interactive Data Exploration and Analytics (IDEA’17), KDD workshop, arXiv:1708.09441
16
Ishida et al., 2019 - https://arxiv.org/pdf/1909.13260v1.pdf
Fraction of true anomalies
AAD was able to increase the incidence of true anomalies
presented to the expert in 80%
Then make it more complicated ...
AAD on real data: The Open Supernova Catalog
17
Ishida et al., 2019 - https://arxiv.org/pdf/1909.13260v1.pdf
Then make it more complicated ...
AAD on real data: The Open Supernova Catalog
14
20
18
Ishida et al., 2019 - https://arxiv.org/pdf/1909.13260v1.pdf
33
14
Fast identification of binary microlensing event
Then make it more complicated ...
AAD on real data: The Open Supernova Catalog
19
Summary
We are currently applying AAD in ZTF DR4 …
news should be out soon! Stay tuned!!
20
Thank you, Merci, Спасибо
From the SИAD team!
Extra slides
Experiment
Second Try: Zwicky Transient Facility DR3
Results:
There are no SN in ZTF Data releases ...
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Curiosities
From ZTF DR3: Examples of artifacts
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Curiosities
From ZTF DR3: IW Dra and its echoes
Malanchev et al., 2020 - MNRAS - https://arxiv.org/abs/2012.01419
Curiosities
From ZTF DR3: The Barcelona asteroid
Malanchev et al., 2021 - MNRAS - https://arxiv.org/abs/2012.01419