• Corpus ID: 226222106

Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots

  title={Lessons Learned from the 1st ARIEL Machine Learning Challenge: Correcting Transiting Exoplanet Light Curves for Stellar Spots},
  author={N. Nikolaou and Ingo P. Waldmann and Angelos Tsiaras and Mario Morvan and Billy Edwards and Kai Hou Yip and Giovanna Tinetti and Subhajit Sarkar and James M. Dawson and Vadim Borisov and Gjergji Kasneci and Matej Petkovi{\'c} and Tomaz Stepisnik and Tarek Al-Ubaidi and Rachel Louise Bailey and Michael Granitzer and Sahib Julka and Roman Kern and Patrick Ofner and Stefan Wagner and Lukas Heppe and Mirko Bunse and Katharina Morik},
The last decade has witnessed a rapid growth of the field of exoplanet discovery and characterisation. However, several big challenges remain, many of which could be addressed using machine learning methodology. For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots. The current practice in the literature is to identify the effects of spots visually and correct for… 

Figures and Tables from this paper

ESA-Ariel Data Challenge NeurIPS 2022: Inferring Physical Properties of Exoplanets From Next-Generation Telescopes
The study of extra-solar planets, or simply, exoplanets, planets outside our own Solar System, is fundamentally a grand quest to understand our place in the Universe. Discoveries in the last two
Theory-inspired machine learning—towards a synergy between knowledge and data
This short survey introduces and discusses several prominent approaches to theory-inspired machine learning and shows how they were applied in the fields of welding, joining, additive manufacturing, and metal forming.


Correcting for chromatic stellar activity effects in transits with multiband photometric monitoring: application to WASP-52
Context.The properties, distribution, and evolution of inhomogeneities on the surface of active stars, such as dark spots and bright faculae, significantly influence the determination of the
Exoplanet transit spectroscopy: development and application of a generic time domain simulator
IN this thesis I describe the development and validation of a generic time domain simulator of exoplanet transit spectroscopy called ExoSim, and apply it to various problems in the field. ExoSim
Accurate Machine-learning Atmospheric Retrieval via a Neural-network Surrogate Model for Radiative Transfer
A novel approach to retrieval is presented by training a forward ML surrogate model that predicts spectra given model parameters, providing a fast approximate RT simulation that can be used in a conventional Bayesian retrieval framework without significant loss of accuracy.
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Toward Extremely Precise Radial Velocities. II. A Tool for Using Multivariate Gaussian Processes to Model Stellar Activity
It is found that local kernels could significantly increase the sensitivity and precision of Doppler planet searches relative to the widely used quasi-periodic kernel.
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
IEEE circuits and systems magazine
Ground-based and Airborne Telescopes II, Vol. 7012 (International Society for Optics and Photonics)
  • 2008
Ground-based and Airborne Telescopes IV, Vol. 8444 (International Society for Optics and Photonics)
  • 2012