000007474 001__ 7474
000007474 005__ 20250204102831.0
000007474 037__ $$aSCART-2025-0104
000007474 100__ $$aSayez, Niels
000007474 245__ $$aMitigating hallucination with non-adversarial strategies for image-to-image translation in solar physics
000007474 260__ $$c2025
000007474 520__ $$aContext. Image-to-image translation using generative adversarial networks (GANs) has become a standard approach across numerous scientific domains, including heliophysics research. However, GANs are inherently prone to generating hallucinations in their outputs - a characteristic that, while acceptable in some applications, becomes problematic in physics-bound domains. Given that heliophysics research requires strict adherence to physical events, this tendency to produce artificial artifacts should raise significant concerns about their reliability in scientific applications. Aims. This work aim at measuring the discrepancy between GAN-generated solar images and real observations in two heliophysics applications. Another model producing outputs significantly more faithful to the underlying solar phenomena is proposed and com- pared with a GAN-based solution. Methods. We compare two deep learning models: a generative adversarial network architecture based on Pix2Pix, widely adopted in heliophysics and a model trained in a non-adversarial setup and leveraging input-dependent guidance. Results. GANs consistently fall short of conventional models in physics-constrained applications due to hallucinated features. Ad- ditional conditioning of deep learning networks with physics-based constraints significantly enhances cross-modal image-to-image translation.
000007474 536__ $$aB2 /$$c191/$$fP2/DeepSun
000007474 594__ $$aSTCE
000007474 6531_ $$aImage-to-image Translation 
000007474 6531_ $$aGenerative Adversarial Networks
000007474 6531_ $$aFeature Modulation
000007474 6531_ $$aStyle Transfer 
000007474 6531_ $$aPhotosphere 
000007474 6531_ $$aChromosphere
000007474 6531_ $$aSolar corona
000007474 700__ $$aDe Vleeschouwer, Christophe
000007474 700__ $$aDelouille, Veronique
000007474 700__ $$aBechet, Sabrina 
000007474 700__ $$aLefèvre, Laure
000007474 773__ $$pAstronomy & Astrophysics$$y2025
000007474 8560_ $$fveronique.delouille@ksb-orb.be
000007474 905__ $$asubmitted to
000007474 980__ $$aREFERD