File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Artificial Intelligence Techniques for Uncovering Resolved Planetary Nebula Candidates from Wide-field VPHAS+ Survey Data

TitleArtificial Intelligence Techniques for Uncovering Resolved Planetary Nebula Candidates from Wide-field VPHAS+ Survey Data
Authors
Issue Date22-Dec-2023
PublisherOxford University Press
Citation
Monthly Notices of the Royal Astronomical Society, 2023, v. 528, n. 3, p. 4733-4745 How to Cite?
Abstract

AI and deep learning techniques are playing an increasing role in astronomy to deal with the data avalanche. Here we describe an application for finding resolved Planetary Nebulae (PNe) in crowded, wide-field, narrow-band Hα survey imagery in the Galactic plane, to test and facilitate more objective, reproducible, efficient and reliable trawls for them. PNe are important to study late-stage stellar evolution of low to intermediate-mass stars. However, the confirmed ∼3800 Galactic PNe fall far short of the numbers expected. Traditional visual searching for resolved PNe is time-consuming due to the large data size and areal coverage of modern astronomical surveys. The training and validation dataset of our algorithm was built with IPHAS survey and true PNe from the HASH database. Our algorithm correctly identified 444 PNe in the validation set of 454 ones, with only 16 explicable ‘false’ positives, achieving a precision rate of 96.5% and a recall rate of 97.8%. After transfer learning, it was then applied to VPHAS+ survey, examining 979 out of 2284 survey fields, each covering 1 × 1. It returned ∼20,000 detections, including 2637 known PNe and other kinds of catalogued non-PNe. A total of 815 new high-quality PNe candidates were found, 31 of which were selected as top-quality targets for optical spectroscopic follow-up. We found 74% of them are true, likely and possible PNe. Representative preliminary confirmatory spectroscopy results are presented here to demonstrate the effectiveness of our techniques with full details to be given in paper-II.


Persistent Identifierhttp://hdl.handle.net/10722/341947
ISSN
2023 Impact Factor: 4.7
2023 SCImago Journal Rankings: 1.621

 

DC FieldValueLanguage
dc.contributor.authorSun, Ruiqi-
dc.contributor.authorLi, Yushan-
dc.contributor.authorParker, Quentin-
dc.contributor.authorLi, Jiaxin-
dc.contributor.authorLi, Xu-
dc.contributor.authorCao, Liang-
dc.contributor.authorJia, Peng-
dc.date.accessioned2024-03-26T05:38:26Z-
dc.date.available2024-03-26T05:38:26Z-
dc.date.issued2023-12-22-
dc.identifier.citationMonthly Notices of the Royal Astronomical Society, 2023, v. 528, n. 3, p. 4733-4745-
dc.identifier.issn0035-8711-
dc.identifier.urihttp://hdl.handle.net/10722/341947-
dc.description.abstract<p>AI and deep learning techniques are playing an increasing role in astronomy to deal with the data avalanche. Here we describe an application for finding resolved Planetary Nebulae (PNe) in crowded, wide-field, narrow-band Hα survey imagery in the Galactic plane, to test and facilitate more objective, reproducible, efficient and reliable trawls for them. PNe are important to study late-stage stellar evolution of low to intermediate-mass stars. However, the confirmed ∼3800 Galactic PNe fall far short of the numbers expected. Traditional visual searching for resolved PNe is time-consuming due to the large data size and areal coverage of modern astronomical surveys. The training and validation dataset of our algorithm was built with IPHAS survey and true PNe from the HASH database. Our algorithm correctly identified 444 PNe in the validation set of 454 ones, with only 16 explicable ‘false’ positives, achieving a precision rate of 96.5% and a recall rate of 97.8%. After transfer learning, it was then applied to VPHAS+ survey, examining 979 out of 2284 survey fields, each covering 1<sup>○</sup> × 1<sup>○</sup>. It returned ∼20,000 detections, including 2637 known PNe and other kinds of catalogued non-PNe. A total of 815 new high-quality PNe candidates were found, 31 of which were selected as top-quality targets for optical spectroscopic follow-up. We found 74% of them are true, likely and possible PNe. Representative preliminary confirmatory spectroscopy results are presented here to demonstrate the effectiveness of our techniques with full details to be given in paper-II.<br></p>-
dc.languageeng-
dc.publisherOxford University Press-
dc.relation.ispartofMonthly Notices of the Royal Astronomical Society-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleArtificial Intelligence Techniques for Uncovering Resolved Planetary Nebula Candidates from Wide-field VPHAS+ Survey Data-
dc.typeArticle-
dc.identifier.doi10.1093/mnras/stad3954-
dc.identifier.volume528-
dc.identifier.issue3-
dc.identifier.spage4733-
dc.identifier.epage4745-
dc.identifier.eissn1365-2966-
dc.identifier.issnl0035-8711-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats