First discovery and confirmation of planetary nebula candidates from AI and deep learning techniques applied to VPHAS+ survey data

¹ The Department of Physics, The University of Hong Kong, Hong Kong SAR, China
² The Laboratory for Space Research, The University of Hong Kong, Hong Kong 999077, China
³ College of Electronic Information and Optical Engineering, Taiyuan University of Technology, Taiyuan 030024, China
⁴ Peng Cheng Lab, Shenzhen 518066, China

^★ Corresponding author; quentinp@hku.hk

Received: 5 June 2024
Accepted: 3 October 2024

Abstract

Context. We have developed tools based on deep learning and artificial intelligence (AI) to search extant narrow-band wide-field Hα surveys of the Galactic Plane for elusive planetary nebulae (PNe) hidden in dense star fields towards the Galactic centre. They are faint, low-surface-brightness, usually resolved sources, which had not discovered by previous automatic searches that depend on photometric data for point-like sources. These sources are very challenging to locate by traditional visual inspection in such crowded fields and many have been missed. We have successfully adopted a novel ‘Swin-Transformer’ AI algorithm, which we describe in detail in the preceding Techniques paper (Paper I).

Aims. Here, we present preliminary results from our first spectroscopic follow-up run for 31 top-quality PN candidates found by the algorithm from the high-resolution Hα survey VPHAS+. This survey has not yet undergone extensive manual, systematic searching.

Methods. Our candidate PNe were observed with the SpUpNIC spectrograph on the 1.9 m telescope at the South African Astronomical Observatory (SAAO) in June 2023. We performed standard IRAF spectroscopic reduction, followed by our normal HASH PN identification and classification procedures.

Results. Our reduced spectra confirmed that these candidates include 22 true, likely, and possible PNe (70.97%), 3 emission-line galaxies, 2 emission-line stars, 2 late-type star contaminants, and 2 other Hα sources including a newly identified detached fragment of supernova remnants (SNRs) RCW 84. We present the imaging and spectral data of these candidates and a preliminary analysis of their properties. These data provide strong input for evaluating and refining the behaviour of the AI algorithm when searching for PNe in wide-field Hα surveys.