Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

Terry Cortez; Tossapon Boongoen; Natthakan Iam-On; Khwunta  Kirimasthong; James  Mullaney

doi:10.1007/978-3-031-47508-5_36

Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

Terry Cortez, Tossapon Boongoen, Natthakan Iam-On, Khwunta Kirimasthong, James Mullaney

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

Abstract

The paper proposes an alternative method to detect transients for an optical telescope using a deep learning algorithm. While the previous studies followed the conventional method, a classification, focusing on the manually extracted features of transients, the alternative method does the detection focusing on imagery instead. The algorithm is based on a famous UNET model which can do both classification and segmentation at the same time. Initial setups are used to test the capability of the model. In the same way, some data is fused with noise to see the model limitation. The result is a map showing where the objects are located, identified by binary class numbers. Both results either with or without noise are provided. This includes a comparison between different batch size setups as one of the key parameters for deep learning. As a preliminary to further studies, a list of possible parameters is also given.

Original language	English
Title of host publication	UKCI 2023: Advances in Computational Intelligence Systems
Subtitle of host publication	Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK
Editors	Nitin Naik, Paul Jenkins, Paul Grace, Longzhi Yang, Shaligram Prajapat
Publisher	Springer Nature
Pages	459-470
Number of pages	12
ISBN (Print)	978-3-031-47507-8, 3031475070
DOIs	https://doi.org/10.1007/978-3-031-47508-5_36
Publication status	Published - 01 Feb 2024
Externally published	Yes
Event	The 22nd UK Workshop on Computational Intelligence - Aston University, Birmingham, United Kingdom of Great Britain and Northern Ireland Duration: 06 Sept 2023 → 08 Sept 2023 Conference number: 22 https://www.uk-ci.org/home

Publication series

Name	Advances in Intelligent Systems and Computing
Publisher	Springer Cham
Volume	1453
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	The 22nd UK Workshop on Computational Intelligence
Abbreviated title	UKCI 2023
Country/Territory	United Kingdom of Great Britain and Northern Ireland
City	Birmingham
Period	06 Sept 2023 → 08 Sept 2023
Internet address	https://www.uk-ci.org/home

Keywords

sky survey
transient detection
convolutional neural network
UNET

Access to Document

10.1007/978-3-031-47508-5_36

Permanent link

Persistent link

Cite this

Cortez, T., Boongoen, T., Iam-On, N., Kirimasthong, K., & Mullaney, J. (2024). Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey. In N. Naik, P. Jenkins, P. Grace, L. Yang, & S. Prajapat (Eds.), UKCI 2023: Advances in Computational Intelligence Systems: Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK (pp. 459-470). (Advances in Intelligent Systems and Computing; Vol. 1453). Springer Nature. https://doi.org/10.1007/978-3-031-47508-5_36

Cortez, Terry ; Boongoen, Tossapon ; Iam-On, Natthakan et al. / Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey. UKCI 2023: Advances in Computational Intelligence Systems: Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK. editor / Nitin Naik ; Paul Jenkins ; Paul Grace ; Longzhi Yang ; Shaligram Prajapat. Springer Nature, 2024. pp. 459-470 (Advances in Intelligent Systems and Computing).

@inproceedings{e28fd797f89c4f8fa778c1677f193954,

title = "Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey",

abstract = "The paper proposes an alternative method to detect transients for an optical telescope using a deep learning algorithm. While the previous studies followed the conventional method, a classification, focusing on the manually extracted features of transients, the alternative method does the detection focusing on imagery instead. The algorithm is based on a famous UNET model which can do both classification and segmentation at the same time. Initial setups are used to test the capability of the model. In the same way, some data is fused with noise to see the model limitation. The result is a map showing where the objects are located, identified by binary class numbers. Both results either with or without noise are provided. This includes a comparison between different batch size setups as one of the key parameters for deep learning. As a preliminary to further studies, a list of possible parameters is also given.",

keywords = "sky survey, transient detection, convolutional neural network, UNET",

author = "Terry Cortez and Tossapon Boongoen and Natthakan Iam-On and Khwunta Kirimasthong and James Mullaney",

year = "2024",

month = feb,

day = "1",

doi = "10.1007/978-3-031-47508-5_36",

language = "English",

isbn = "978-3-031-47507-8",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Nature",

pages = "459--470",

editor = "Nitin Naik and Paul Jenkins and Paul Grace and Longzhi Yang and Shaligram Prajapat",

booktitle = "UKCI 2023: Advances in Computational Intelligence Systems",

address = "Switzerland",

note = "The 22nd UK Workshop on Computational Intelligence, UKCI 2023 ; Conference date: 06-09-2023 Through 08-09-2023",

url = "https://www.uk-ci.org/home",

}

Cortez, T, Boongoen, T , Iam-On, N, Kirimasthong, K & Mullaney, J 2024, Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey. in N Naik, P Jenkins, P Grace, L Yang & S Prajapat (eds), UKCI 2023: Advances in Computational Intelligence Systems: Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK. Advances in Intelligent Systems and Computing, vol. 1453, Springer Nature, pp. 459-470, The 22nd UK Workshop on Computational Intelligence, Birmingham, United Kingdom of Great Britain and Northern Ireland, 06 Sept 2023. https://doi.org/10.1007/978-3-031-47508-5_36

Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey. / Cortez, Terry; Boongoen, Tossapon ; Iam-On, Natthakan et al.
UKCI 2023: Advances in Computational Intelligence Systems: Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK. ed. / Nitin Naik; Paul Jenkins; Paul Grace; Longzhi Yang; Shaligram Prajapat. Springer Nature, 2024. p. 459-470 (Advances in Intelligent Systems and Computing; Vol. 1453).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

TY - GEN

T1 - Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

AU - Cortez, Terry

AU - Boongoen, Tossapon

AU - Iam-On, Natthakan

AU - Kirimasthong, Khwunta

AU - Mullaney, James

N1 - Conference code: 22

PY - 2024/2/1

Y1 - 2024/2/1

N2 - The paper proposes an alternative method to detect transients for an optical telescope using a deep learning algorithm. While the previous studies followed the conventional method, a classification, focusing on the manually extracted features of transients, the alternative method does the detection focusing on imagery instead. The algorithm is based on a famous UNET model which can do both classification and segmentation at the same time. Initial setups are used to test the capability of the model. In the same way, some data is fused with noise to see the model limitation. The result is a map showing where the objects are located, identified by binary class numbers. Both results either with or without noise are provided. This includes a comparison between different batch size setups as one of the key parameters for deep learning. As a preliminary to further studies, a list of possible parameters is also given.

AB - The paper proposes an alternative method to detect transients for an optical telescope using a deep learning algorithm. While the previous studies followed the conventional method, a classification, focusing on the manually extracted features of transients, the alternative method does the detection focusing on imagery instead. The algorithm is based on a famous UNET model which can do both classification and segmentation at the same time. Initial setups are used to test the capability of the model. In the same way, some data is fused with noise to see the model limitation. The result is a map showing where the objects are located, identified by binary class numbers. Both results either with or without noise are provided. This includes a comparison between different batch size setups as one of the key parameters for deep learning. As a preliminary to further studies, a list of possible parameters is also given.

KW - sky survey

KW - transient detection

KW - convolutional neural network

KW - UNET

U2 - 10.1007/978-3-031-47508-5_36

DO - 10.1007/978-3-031-47508-5_36

M3 - Conference Proceeding (Non-Journal item)

SN - 978-3-031-47507-8

SN - 3031475070

T3 - Advances in Intelligent Systems and Computing

SP - 459

EP - 470

BT - UKCI 2023: Advances in Computational Intelligence Systems

A2 - Naik, Nitin

A2 - Jenkins, Paul

A2 - Grace, Paul

A2 - Yang, Longzhi

A2 - Prajapat, Shaligram

PB - Springer Nature

T2 - The 22nd UK Workshop on Computational Intelligence

Y2 - 6 September 2023 through 8 September 2023

ER -

Cortez T, Boongoen T , Iam-On N, Kirimasthong K, Mullaney J. Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey. In Naik N, Jenkins P, Grace P, Yang L, Prajapat S, editors, UKCI 2023: Advances in Computational Intelligence Systems: Contributions Presented at the 22nd UK Workshop on Computational Intelligence (UKCI 2023), September 6–8, 2023, Birmingham, UK. Springer Nature. 2024. p. 459-470. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-031-47508-5_36

Image-Based Transient Detection Algorithm for Gravitational-Wave Optical Transient Observer (GOTO) Sky Survey

Abstract

Publication series

Conference

Keywords

Access to Document

Permanent link

Fingerprint

Cite this