Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery

Joseph Liu

doi:10.47297/taposatWSP2633-456901.20210206

PDF
Export
Share
Collection
Album

Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery

Volume 2, Issue 6

Views: 0 Downloads: 11

Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery
Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery
Santa Clara University
Vol. 2, Issue 6, Pages: 4-12(2021)
Published： 2021 ，
DOI：10.47297/taposatWSP2633-456901.20210206
Accepted：

Scan QR Code

JOSEPH LIU. (2021). Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery. Theory and Practice of Science and Technology, 2(6), 4-12..
DOI：

JOSEPH LIU. (2021). Using Convolutional Neural Networks to Identify Exoplanet Candidates From Imagery. Theory and Practice of Science and Technology, 2(6), 4-12.. DOI： 10.47297/taposatWSP2633-456901.20210206.

摘要

Abstract

We introduce astronomical imagery as a dataset to identify exoplanet candidates. By viewing data as a series of images

we can use video recognition techniques

such as 3D Convolutional Neural Networks

to classify stars. We use TESS’s observations as our dataset. Because of the lack of known exoplanets and exoplanet candidates

we additionally use simulations to generate imagery. Using this data

we train a 3D CNN written with Pytorch to classify stars as exoplanet candidates or non-exoplanet candidates. Our final results show 61% accuracy in classification. We discover that our method is prone to overfitting

lowering our accuracy. Additionally

the lack of a cleaned and labeled dataset meant that our data was noisy with potential misclassifications.

关键词

Keywords

Exoplanet CandidatesConvolutional Neural NetworksAstronomical imagery

references

Brasseur, C. E., Phillip, C., Fleming, S. W., Mullally, S. E., & White, R. L. (2019). Astrocut: Tools for creating cutouts of TESS images. Astrophysics Source Code Library, ascl-1905.[2] Cardoso, J. V. D. M., Hedges, C., Gully-Santiago, M., Saunders, N., Cody, A. M., Barclay, T., ... & Lightkurve Collaboration. (2018). Lightkurve: Kepler and TESS time series analysis in Python. Astrophysics Source Code Library, ascl-1812.[3] Charbonneau, D., Brown, T. M., Latham, D. W., & Mayor, M. (1999). Detection of planetary transits across a sun-like star. The Astrophysical Journal Letters, 529(1), L45.[4] Ginsburg, A., Sipőcz, B. M., Brasseur, C. E., Cowperthwaite, P. S., Craig, M. W., Deil, C., ... & Woillez, J. (2019). Astroquery: an astronomical web-querying package in python. The Astronomical Journal, 157(3), 98.[5] Guerrero, N. M., Seager, S., Huang, C. X., Vanderburg, A., Soto, A. G., Mireles, I., ... & Winn, J. N. (2021). The TESS Objects of Interest Catalog from the TESS Prime Mission. The Astrophysical Journal Supplement Series, 254(2), 39.[6] Harris, C. R., Millman, K. J., van der Walt, S. J., Gommers, R., Virtanen, P., Cournapeau, D., ... & Oliphant, T. E. (2020). Array programming with NumPy. Nature, 585(7825), 357-362.[7] Hunter, J. D. (2007). Matplotlib: A 2D graphics environment. Computing in science & engineering, 9(03), 90-95.[8] Ji, S., Xu, W., Yang, M., & Yu, K. (2012). 3D convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221-231.[9] Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.[10]McCauliff, S. D., Jenkins, J. M., Catanzarite, J., Burke, C. J., Coughlin, J. L., Twicken, J. D., ... & Cote, M. (2015). Automatic classification of Kepler planetary transit candidates. The Astrophysical Journal, 806(1), 6.[11]Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., ... & Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 8026-8037.[12]Price-Whelan, A. M., Sipőcz, B. M., Günther, H. M., Lim, P. L., Crawford, S. M., Conseil, S., ... & Astropy Coordination Committee. (2018). The Astropy project: building an open-science project and status of the v2. 0 core package. The Astronomical Journal, 156(3), 123.[13]Ricker, G. R., Latham, D. W., Vanderspek, R. K., Ennico, K. A., Bakos, G., Brown, T. M., ... & Worden, S. P. (2010, January). Transiting exoplanet survey satellite (tess). In American Astronomical Society Meeting Abstracts# 215 (Vol. 215, pp. 450-06).[14]Robitaille, T. P., Tollerud, E. J., Greenfield, P., Droettboom, M., Bray, E., Aldcroft, T., ... & Streicher, O. (2013). Astropy: A community Python package for astronomy. Astronomy & Astrophysics, 558, A33.[15]Shallue, C. J., & Vanderburg, A. (2018). Identifying exoplanets with deep learning: A five-planet resonant chain around kepler-80 and an eighth planet around kepler-90. The Astronomical Journal, 155(2), 94.

Alert me when the article has been cited

Submit

A Study of the Hexagonal Chess Game Program Based on the Monte Carlo Algorithm

Empirical Advancements in Convolutional Neural Networks for Image Recognition: A Comparative Analysis

Related Author

Shangyuan Luan University of Science and Technology Liaoning

Zhifeng Wang University of Science and Technology Liaoning

Fuyu Li University of Science and Technology Liaoning

Hejun Yang

Related Institution

University of Science and Technology Liaoning

Faculty of Information Technology, Beijing University of Technology

⁰