Exoplanet Cartography using Convolutional Neural Networks

Abstract

In the near-future, dedicated telescopes observe Earth-like exoplanets in reflected light, allowing their characterization. Because of the huge distances, every exoplanet will be a single pixel, but temporal variations in its spectral flux hold information about the planet's surface and atmosphere. We test convolutional neural networks for retrieving a planet's rotation axis, surface and cloud map from simulated single-pixel flux and polarization observations. We investigate the assumption that the planets reflect Lambertian in the retrieval while their actual reflection is bidirectional, and of including polarization in retrievals. We simulate observations along a planet's orbit using a radiative transfer algorithm that includes polarization and bidirectional reflection by vegetation, desert, oceans, water clouds, and Rayleigh scattering in 6 spectral bands from 400 to 800 nm, at various photon noise levels. The surface-types and cloud patterns of the facets covering a model planet are based on probability distributions. Our networks are trained with simulated observations of millions of planets before retrieving maps of test planets. The neural networks can constrain rotation axes with a mean squared error (MSE) as small as 0.0097, depending on the orbital inclination. On a bidirectionally reflecting planet, 92% of ocean and 85% of vegetation, desert, and cloud facets are correctly retrieved, in the absence of noise. With realistic noise, it should still be possible to retrieve the main map features with a dedicated telescope. Except for face-on orbits, a network trained with Lambertian reflecting planets, yields significant retrieval errors when given observations of bidirectionally reflecting planets, in particular, brightness artefacts around a planet's pole. Including polarization improves retrieving the rotation axis and the accuracy of the retrieval of ocean and cloud facets.

arXiv comment38 pages, 25 figures, 5 tables, accepted for publication in Astron. Astrophys

References in corpus (22)

• Deep Learning in Neural Networks: An Overview
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Measurement of areas on a sphere using Fibonacci and latitude-longitude lattices
• Vegetation's Red Edge: A Possible Spectroscopic Biosignature of Extraterrestrial Plants
• Characterization of extrasolar terrestrial planets from diurnal photometric variability
• Bayesian search for low-mass planets around nearby M dwarfs. Estimates for occurrence rate based on global detectability statistics
• Spectropolarimetric signatures of Earth-like extrasolar planets
• Mapping Earth Analogs from Photometric Variability: Spin-Orbit Tomography for Planets in Inclined Orbits
• A Probabilistic Approach to Kepler Completeness and Reliability for Exoplanet Occurrence Rates
• Looking for the rainbow on exoplanets covered by liquid and icy water clouds
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• Earth as an Exoplanet: A Two-dimensional Alien Map
• exocartographer: A Bayesian Framework for Mapping Exoplanets in Reflected Light
• Frequency Modulation of Directly Imaged Exoplanets: Geometric Effect as a Probe of Planetary Obliquity
• Blue, white, and red ocean planets - Simulations of orbital variations in flux and polarization colors
• PyMieDAP: a Python--Fortran tool to compute fluxes and polarization signals of (exo)planets
• RefPlanets: Search for reflected light from extra-solar planets with SPHERE/ZIMPOL
• PEXO: a global modeling framework for nanosecond timing, microsecond astrometry, and $\mu$m/s radial velocities
• Bayesian Dynamic Mapping of an Exo-Earth from Photometric Variability
• Colors of an Earth-like exoplanet -- Temporal flux and polarization signals of the Earth
• Fourier spectra from exoplanets with polar caps and ocean glint
• Planet cartography with neural learned regularization