Classification of Planetary Nebulae through Deep Transfer Learning

Awang Iskandar, Dayang N. F.; Zijlstra, Albert A.; McDonald, Iain; Abdullah, Rosni; Fuller, Gary A.; Fauzi, Ahmad H. and Abdullah, Johari (2020). Classification of Planetary Nebulae through Deep Transfer Learning. Galaxies, 8(4), article no. 88.

DOI: https://doi.org/10.3390/galaxies8040088

Abstract

This study investigate the effectiveness of using Deep Learning (DL) for the classification of planetary nebulae (PNe). It focusses on distinguishing PNe from other types of objects, as well as their morphological classification. We adopted the deep transfer learning approach using three ImageNet pre-trained algorithms. This study was conducted using images from the Hong Kong/Australian Astronomical Observatory/Strasbourg Observatory H-alpha Planetary Nebula research platform database (HASH DB) and the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS). We found that the algorithm has high success in distinguishing True PNe from other types of objects even without any parameter tuning. The Matthews correlation coefficient is 0.9. Our analysis shows that DenseNet201 is the most effective DL algorithm. For the morphological classification, we found for three classes, Bipolar, Elliptical and Round, half of objects are correctly classified. Further improvement may require more data and/or training. We discuss the trade-offs and potential avenues for future work and conclude that deep transfer learning can be utilized to classify wide-field astronomical images.

Viewing alternatives

Metrics

Item Actions

Export

You can export this page using these formats Digital Object Identifier - DOI

About

• Item ORO ID
• 74163
• Item Type
• Journal Item
• ISSN
• 2075-4434
• Project Funding Details

• Funded Project Name	Project ID	Funding Body
  “Deep Learning for Classification of Astronomical Archives”	ST/R006768/1	UK Science and Technology Facilities Council
  Newton-Ungku Omar Fund	F08/STFC/1792/2018	Not Set

• Keywords
• deep learning; transfer learning; planetary nebulae; morphology; classification; HASH DB; Pan-STARRS
• Academic Unit or School
• Faculty of Science, Technology, Engineering and Mathematics (STEM) > Physical Sciences
  Faculty of Science, Technology, Engineering and Mathematics (STEM)
• Copyright Holders
• © 2020 Dayang N. F. Awang Iskandar, © 2020 Albert A. Zijlstra, © 2020 Iain McDonald, © 2020 Rosni Abdullah, © 2020 Gary A. Fuller, © 2020 Ahmad H. Fauzi, © 2020 Johari Abdullah
• SWORD Depositor
• Jisc Publications-Router
• Depositing User
• Jisc Publications-Router