Diag2Diag: Multimodal super-resolution diagnostics for physics discovery with application to fusion

This paper introduces a groundbreaking multimodal neural network model designed for resolution enhancement, which innovatively leverages inter-diagnostic correlations within a system. Traditional approaches have primarily focused on unimodal enhancement strategies, such as pixel-based image enhancement or heuristic signal interpolation. In contrast, our model employs a novel methodology by harnessing the diagnostic relationships within the physics of fusion plasma. Initially, we establish the correlation among diagnostics within the tokamak. Subsequently, we utilize these correlations to substantially enhance the temporal resolution of the Thomson Scattering (TS) diagnostic, which assesses plasma density and temperature. This enhancement goes beyond simple interpolation, offering a super resolution that preserves the underlying physics inherent in inter-diagnostic correlation. Increasing the resolution of TS from conventional 0.2 kHz to 500 kHz could show the diagnostic capability of capturing the structural evolution of plasma instabilities and the response to external field perturbations, that were challenging with conventional diagnostics. This physics-preserving super-resolution technique may enable the discovery of new physics that were previously undetectable due to resolution limitations or allow for the experimental verification of phenomena that had only been predicted through computationally intensive simulations.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.