# Pushing the Limits of Exoplanet Discovery via Direct Imaging with Deep Learning

## TL;DR

This paper introduces a deep learning framework combining generative and discriminative models to improve exoplanet detection via direct imaging, especially in low SNR conditions, overcoming limited ground truth data.

## Contribution

It presents a novel approach using GANs to generate training data for CNN classifiers, enhancing detection robustness across various SNR levels in exoplanet direct imaging.

## Key findings

- Detectors perform well on artificial data across SNRs.
- Models can re-confirm bright sources in real data.
- Provides pixel-wise maps of detection precision and recall.

## Abstract

Further advances in exoplanet detection and characterisation require sampling a diverse population of extrasolar planets. One technique to detect these distant worlds is through the direct detection of their thermal emission. The so-called direct imaging technique, is suitable for observing young planets far from their star. These are very low signal-to-noise-ratio (SNR) measurements and limited ground truth hinders the use of supervised learning approaches. In this paper, we combine deep generative and discriminative models to bypass the issues arising when directly training on real data. We use a Generative Adversarial Network to obtain a suitable dataset for training Convolutional Neural Network classifiers to detect and locate planets across a wide range of SNRs. Tested on artificial data, our detectors exhibit good predictive performance and robustness across SNRs. To demonstrate the limits of the detectors, we provide maps of the precision and recall of the model per pixel of the input image. On real data, the models can re-confirm bright source detections.