UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

PyLightcurve-torch: a transit modeling package for deep learning applications in PyTorch

Morvan, M; Tsiaras, A; Nikolaou, N; Waldmann, IP; (2021) PyLightcurve-torch: a transit modeling package for deep learning applications in PyTorch. Publications of the Astronomical Society of the Pacific , 133 (1021) , Article 034505. 10.1088/1538-3873/abe6e8. Green open access

[thumbnail of Morvan_2021_PASP_133_034505.pdf]
Preview
Text
Morvan_2021_PASP_133_034505.pdf - Published Version

Download (500kB) | Preview

Abstract

We present a new open source python package, based on PyLightcurve and PyTorch Paszke et al., tailored for efficient computation and automatic differentiation of exoplanetary transits. The classes and functions implemented are fully vectorised, natively GPU-compatible and differentiable with respect to the stellar and planetary parameters. This makes PyLightcurve-torch suitable for traditional forward computation of transits, but also extends the range of possible applications with inference and optimization algorithms requiring access to the gradients of the physical model. This endeavour is aimed at fostering the use of deep learning in exoplanets research, motivated by an ever increasing amount of stellar light curves data and various incentives for the improvement of detection and characterization techniques.

Type: Article
Title: PyLightcurve-torch: a transit modeling package for deep learning applications in PyTorch
Open access status: An open access version is available from UCL Discovery
DOI: 10.1088/1538-3873/abe6e8
Publisher version: http://dx.doi.org/10.1088/1538-3873/abe6e8
Language: English
Additional information: Original content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Keywords: Exoplanets, Transits, Photometry, Neural networks
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Physics and Astronomy
URI: https://discovery.ucl.ac.uk/id/eprint/10125418
Downloads since deposit
Loading...
112Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
1.United States
5
2.Russian Federation
1
3.China
1
4.Germany
1

Archive Staff Only

View Item View Item