A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques

TL;DR

This paper explores a machine learning-based converter using 2D-CNNs to enhance the signal-to-noise ratio in exoplanet imaging, potentially reducing observational time needed for high-quality images.

Contribution

The study introduces a novel 2D-CNN model, MWIN5-RB, optimized for denoising exoplanet images, demonstrating improved performance over other models.

Findings

MWIN5-RB achieves the best denoising performance among tested models.

The method can enhance SNR with fewer ADI frames, saving telescope observation time.

The proposed converter is suitable for future observational data applications.

Abstract

The method of direct imaging has detected many exoplanets and made important contribution to the field of planet formation. The standard method employs angular differential imaging (ADI) technique, and more ADI image frames could lead to the results with larger signal-to-noise-ratio (SNR). However, it would need precious observational time from large telescopes, which are always over-subscribed. We thus explore the possibility to generate a converter which can increase the SNR derived from a smaller number of ADI frames. The machine learning technique with two-dimension convolutional neural network (2D-CNN) is tested here. Several 2D-CNN models are trained and their performances of denoising are presented and compared. It is found that our proposed Modified five-layer Wide Inference Network with the Residual learning technique and Batch normalization (MWIN5-RB) can give the best result. We conclude that this MWIN5-RB can be employed as a converter for future observational data.