A possible converter to denoise the images of exoplanet candidates through machine learning techniques

The method of direct imaging has detected many exoplanets and made important contribution to the field planet formation. standard employs angular differential (ADI) technique, more ADI image frames could lead 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 possibility generate a converter can increase SNR derived smaller number frames. machine learning technique two-dimension convolutional neural network (2D-CNN) is tested here. Several 2D-CNN models trained their performances denoising presented compared. It found that our proposed Modified five-layer Wide Inference Network Residual Batch normalization (MWIN5-RB) give best result. conclude this MWIN5-RB be employed as for future data.