Abstract
Astrometric detection involves precise measurements of stellar positions, and it is widely regarded as the leading concept presently ready to find Earth-mass planets in temperate orbits around nearby sun-like stars. The TOLIMAN space telescope [39] is a low-cost, agile mission concept dedicated to narrow-angle astrometric monitoring of bright binary stars. In particular the mission will be optimised to search for habitable-zone planets around \(\alpha \) Centauri AB. If the separation between these two stars can be monitored with sufficient precision, tiny perturbations due to the gravitational tug from an unseen planet can be witnessed and, given the configuration of the optical system, the scale of the shifts in the image plane are about one-millionth of a pixel. Image registration at this level of precision has never been demonstrated (to our knowledge) in any setting within science. In this paper, we demonstrate that a Deep Convolutional Auto-Encoder is able to retrieve such a signal from simplified simulations of the TOLIMAN data and we present the full experimental pipeline to recreate out experiments from the simulations to the signal analysis. In future works, all the more realistic sources of noise and systematic effects present in the real-world system will be injected into the simulations.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimization of nonlinear transform codes for perceptual quality (2016)
Bessel, F.W.: On the variations of the proper motions of Procyon and Sirius. Mon. Not. R. Astron. Soc. 6, 136–141 (1844). https://doi.org/10.1093/mnras/6.11.136
Casertano, S., Lattanzi, M.G., Sozzetti, A., Spagna, A., Jancart, S., Morbidelli, R., Pannunzio, R., Pourbaix, D., Queloz, D.: Double-blind test program for astrometric planet detection with Gaia. Astron. Astrophys. 482(2), 699–729 (2008). https://doi.org/10.1051/0004-6361:20078997
Chen, D.: STEP mission: high-precision space astrometry to search for terrestrial exoplanets. J. Instrum. 9(04), C04040–C04040 (2014). https://doi.org/10.1088/1748-0221/9/04/c04040
Cheng, T.-Y., Li, N., Conselice, C.J., Aragón-Salamanca, A., Dye, S., Metcalf, R.B.: Identifying strong lenses with unsupervised machine learning using convolutional autoencoder. Mon. Not. R. Astron. Soc. 494(3), 3750–3765 (2020). https://doi.org/10.1093/mnras/staa1015
Clevert, D.-A., Unterthiner, T., Hochreiter S.: Fast and accurate deep network learning by exponential linear units (elus). In: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2–4, 2016, Conference Track Proceedings (2016). arXiv:1511.07289
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Signals Syst. 2(4), 303–314 (1989). https://doi.org/10.1007/BF02551274
d’Aspremont, A., Ghaoui, L.E., Jordan, M.I., Lanckriet, G.R.: A direct formulation for sparse PCA using semidefinite programming. In: Advances in Neural Information Processing Systems, pp. 41–48 (2005)
Dunteman, G.H.: Principal Components Analysis, vol. 69. Sage, Thousand Oaks (1989)
Dumas, T., Roumy, A., Guillemot, C.: Autoencoder based image compression: can the learning be quantization independent? (2018)
ESA SP-1200: The HIPPARCOS and TYCHO catalogues. Astrometric and photometric star catalogues derived from the ESA HIPPARCOS Space Astrometry Mission. ESA Special Publication 1200, January (1997)
Frontera-Pons, J., Sureau, F., Bobin, J., Le Floc’h, E.: Unsupervised feature-learning for galaxy SEDs with denoising autoencoders. Astron. Astrophys. (2017). https://doi.org/10.1051/0004-6361/201630240
Gaia Collaboration, Prusti, T., de Bruijne, J.H.J., Brown, A.G.A., Vallenari, A., Babusiaux, C., et al.: The Gaia mission. Astron. Astrophys. 595, A1 (2016). https://doi.org/10.1051/0004-6361/201629272
Gaia Collaboration, Brown, A.G.A., Vallenari, A., Prusti, T., de Bruijne, J.H.J., Babusiaux, C., et al.: Gaia data release 2. Summary of the contents and survey properties. Astron. Astrophys. 616, A1 (2018). https://doi.org/10.1051/0004-6361/201833051
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
GRAVITY Collaboration, Abuter, R., Accardo, M., Amorim, A., Anugu, N., Ávila, G., et al.: First light for gravity: phase referencing optical interferometry for the very large telescope interferometer. A&A 602, A94 (2017). https://doi.org/10.1051/0004-6361/201730838
Guyon, O., Bendek, E.A., Eisner, J.A., Angel, R., Woolf, N.J., et al.: High-precision astrometry with a diffractive pupil telescope. Astrophys. J. Suppl. 200(2), 11 (2012). https://doi.org/10.1088/0067-0049/200/2/11
Hao-ran, Q., Ji-ming, L., Jun-yi, W.: Stacked denoising autoencoders applied to star/galaxy classification. Chin. Astron. Astrophys. 41(2), 282–292 (2017). ISSN 0275-1062. https://doi.org/10.1016/j.chinastron.2017.04.009, http://www.sciencedirect.com/science/article/pii/S0275106217300656
Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4–5), 411–430 (2000)
Jia, P., Li, X., Li, Z., Wang, W., Cai, D.: Point spread function modelling for wide-field small-aperture telescopes with a denoising autoencoder. Mon. Not. R. Astron. Soc. 493(1), 651–660 (2020). ISSN 0035-8711. https://doi.org/10.1093/mnras/staa319
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015). https://doi.org/10.1038/nature14539
Lee, C.-H.: Exoplanets: past, present, and future. Galaxies 6(2), 51 (2018). ISSN 2075-4434. https://doi.org/10.3390/galaxies6020051
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Advances in Neural Information Processing Systems, pp. 556–562 (2001)
Li, W., Xu, H., Ma, Z., Zhu, R., Hu, D., Zhu, Z., Gu, J., Shan, C., Zhu, J., Wu, X.-P.: Separating the EoR signal with a convolutional denoising autoencoder: a deep-learning-based method. Mon. Not. R. Astron. Soc. 485(2), 2628–2637 (2019). ISSN 0035-8711. https://doi.org/10.1093/mnras/stz582
Lomb, N.R.: Least-squares frequency analysis of unequally spaced data. Astrophys. Space Sci. 39(2), 447–462 (1976). https://doi.org/10.1007/BF00648343
Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 689–696 (2009)
Mayor, M., Queloz, D.: A Jupiter-mass companion to a solar-type star. Nature 378(6555), 355–359 (1995). https://doi.org/10.1038/378355a0
Mousavi, A., Patel, A.B., Baraniuk, R.G.: A deep learning approach to structured signal recovery. In: Proceeding of 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) (2015). https://doi.org/10.1109/ALLERTON.2015.7447163
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation (2015). CoRR arXiv:1505.04366
Pearson, K.: On lines of closes fit to system of points in space. Lond. Edinb. Dublin Philos. Mag. J. Sci. 2, 559–572 (1901)
Ranalli, P., Hobbs, D., Lindegren, L.: Astrometry and exoplanets in the Gaia era: a Bayesian approach to detection and parameter recovery. Astron. Astrophys. 614, A30 (2018). https://doi.org/10.1051/0004-6361/201730921
Resnick, A.: Fourier optics and computational imaging, by Kedar Khare. Contemp. Phys. 58(1), 102–103 (2017). https://doi.org/10.1080/00107514.2016.1248491
Scargle, J.D.: Studies in astronomical time series analysis. II. Statistical aspects of spectral analysis of unevenly spaced data. Astrophys. J. 263, 835–853 (1982). https://doi.org/10.1086/160554
Shao, M., Marcy, G., Catanzarite, J.H., Edberg, S.J., Léger, A., Malbet, F., Queloz, D., Muterspaugh, M.W., Beichman, C., Fischer, D., Ford, E., Olling, R., Kulkarni, S., Unwin, S.C., Traub, W.: Astrometric detection of earthlike planets. In: Astro2010: The Astronomy and Astrophysics Decadal Survey, vol. 2010, p. 271, January (2009)
STScI Development Team: pysynphot: synthetic photometry software package (2013)
The Theia Collaboration, Boehm, C., Krone-Martins, A., Amorim, A., Anglada-Escude, G., Brandeker, A., et al.: Theia: Faint objects in motion or the new astrometry frontier (2017). arXiv e-prints arXiv:1707.01348
Theis, L., Shi, W., Cunningham, A., Huszár, F.: Lossy image compression with compressive autoencoders (2017)
Toderici, G., Vincent, D., Johnston, N., Jin Hwang, S., Minnen, D., Shor, J., Covell, M.: Full resolution image compression with recurrent neural networks (2016)
Tuthill, P., Bendek, E., Guyon, O., Horton, A., Jeffries, B., Jovanovic, N., Klupar, P., Larkin, K., Norris, B., Pope, B., Shao, M.: The TOLIMAN space telescope. In: Creech-Eakman, M.J., Tuthill, P.G., Mérand, A. (eds.) Optical and Infrared Interferometry and Imaging VI, vol. 10701, pp. 432–441. International Society for Optics and Photonics, SPIE (2018). https://doi.org/10.1117/12.2313269
Unwin, S.C., Shao, M., Tanner, A.M., Allen, R.J., Beichman, C.A., et al.: Taking the measure of the universe: precision astrometry with SIM PlanetQuest. Publ. Astron. Soc. Pac. 120(863), 38 (2008). https://doi.org/10.1086/525059
van den Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks (2016)
VanderPlas, J.T.: Understanding the lomb-scargle periodogram. Astrophys. J. Suppl. Ser. 236(1), 16 (2018). https://doi.org/10.3847/1538-4365/aab766
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Zhang, R.: Making convolutional networks shift-invariant again. In: ICML (2019)
Zhao, J.J., Mathieu, M., Goroshin, R., LeCun, Y.: Stacked what-where auto-encoders (2015). CoRR arXiv:1506.02351, http://dblp.uni-trier.de/db/journals/corr/corr1506.htmlZhaoMGL15
Acknowledgements
This work was partially produced during the \({2}^{\text {nd}}\) COIN-Focus: Toliman Event (COIN-Focus # 2) held in Rome, Italy, in November 2019. The COIN-Focus: Toliman participants acknowledge the fundamental support of the Breakthrough Initiatives. The Breakthrough Watch initiative and committee (notably Olivier Guyon, Pete Klupar & Pete Worden) have supported and framed the problem. We also acknowledge input and ideas from people in the wider TOLIMAN collaboration including Ben Pope, Barnaby Norris, Bryn Jeffries, Anthony Horton and others. MB acknowledges financial contributions from the agreement ASI/INAF 2018-23-HH.0, Euclid ESA mission - Phase D and the INAF PRIN-SKA 2017 program 1.05.01.88.04. EEOI acknowledges financial support from CNRS 2017 MOMENTUM grant under project Active Learning for Large Scale Sky Surveys. AKM acknowledges the support from the Portuguese Fundação para a Ciência e a Tecnologia (FCT) through grants SFRH/BPD/74697/2010, PTDC/FIS-AST/31546/2017 and from the Portuguese Strategic Programme UID/FIS/00099/2013 for CENTRA.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Veneri, M.D. et al. (2021). Periodic Astrometric Signal Recovery Through Convolutional Autoencoders. In: Zelinka, I., Brescia, M., Baron, D. (eds) Intelligent Astrophysics. Emergence, Complexity and Computation, vol 39. Springer, Cham. https://doi.org/10.1007/978-3-030-65867-0_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-65867-0_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65866-3
Online ISBN: 978-3-030-65867-0
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)