Planet cartography with neural learned regularization

Introduction

Finding potential life harboring exo-Earths is one of the aims of exoplanetary science with the use of future telescopes. Detecting signatures of life in exoplanets will likely first be accomplished by determining the bulk composition of the planetary atmosphere via reflected/transmitted spectroscopy. However, a complete understanding of the habitability conditions will surely require mapping the presence of liquid water, continents and/or clouds. Spin-orbit tomography is a technique that allows us to obtain maps of the surface of exoplanets around other stars using the light scattered by the planetary surface.

We leverage the enormous potential of deep learning and propose a mapping technique for exo-Earths in which the regularization is learned from mock surfaces. The solution of the inverse mapping problem is posed as a deep neural network that can be trained end-to-end with suitable training data. Since we still lack observational data of the surface albedo of exoplanets, we propose in this work to use methods based on the procedural generation of planets, inspired by what we found on Earth. We also consider mapping the recovery of surfaces and the presence of persistent cloud in cloudy planets, a much more challenging problem.

We show that a reliable mapping can be carried out with our approach, producing very compact continents, even when using single passband observations. More importantly, if exoplanets are partially cloudy like the Earth is, we show that one can potentially map the distribution of persistent clouds that always occur on the same position on the surface (associated to orography and sea surface temperatures) together with non-persistent clouds that move across the surface. This will become the first test one can perform on an exoplanet for the detection of an active climate system. For small rocky planets in the habitable zone of their stars, this weather system will be driven by water, and the detection can be considered as a strong proxy for truly habitable conditions.

Generating training and validation sets

The data for training can be generated by running db_libnoise.py. It will generate modulation matrices, surface albedos and cloud covering maps.

Training

Run train_denoise.py or train_denoise_clouds.py for training. These scripts accepts several variables. To reproduce the results in the paper, we used:

python train_denoise.py --model='conv1d' --k=15
python train_denoise.py --model='conv2d' --k=15

Dependencies for training

Libnoise https://github.com/mhilker/libnoise-example
numpy
zarr
PyTorch >v1.0
OpenSimplex (pip install opensimplex)

Dependencies for evaluation