Abstract
This paper introduces a groundbreaking multi-modal neural network model designed for resolution enhancement, which innovatively leverages inter-diagnostic correlations within a system. Traditional approaches have primarily focused on uni-modal 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 diagnostic, which assesses plasma density and temperature. By increasing its resolution from conventional 200Hz to 500kHz, we facilitate a new level of insight into plasma behavior, previously attainable only through computationally intensive simulations. This enhancement goes beyond simple interpolation, offering novel perspectives on the underlying physical phenomena governing plasma dynamics.
Abstract (translated)
本文提出了一种在分辨率增强方面具有突破性的多模态神经网络模型,该模型创新地利用了系统内诊断关系。传统方法主要集中在单模态增强策略,例如基于像素的图像增强或启发式信号插值。相比之下,我们的模型通过利用融合 plasma 物理学中诊断关系的方法来创新性地实现了一种新的方法。首先,我们在 tokamak 中建立了诊断之间的关系。接着,我们利用这些关系大大增强了汤姆逊散射诊断的时域分辨率,该诊断评估了 plasma 密度和温度。通过将分辨率从传统的 200Hz 提高到 500kHz,我们促进了对 plasma 行为的深入洞察,这一般仅通过计算密集型模拟才能实现。这种增强超越了简单的插值,提供了一种新颖的视角,揭示了控制 plasma 动力学背后的物理现象。
URL
https://arxiv.org/abs/2405.05908
