Alaa El-Din Karim K, Forte Alessandro, Kasim Muhammad Firmansyah, Miniati Francesco, Vinko Sam M
Department of Physics, University of Oxford, Oxford, UK.
Machine Discovery, Oxford OX4 4GP, UK.
R Soc Open Sci. 2024 Jun 5;11(5):231374. doi: 10.1098/rsos.231374. eCollection 2024 Jun.
A prevalent class of challenges in modern physics are inverse problems, where physical quantities must be extracted from experimental measurements. End-to-end machine learning approaches to inverse problems typically require constructing sophisticated estimators to achieve the desired accuracy, largely because they need to learn the complex underlying physical model. Here, we discuss an alternative paradigm: by making the physical model auto-differentiable we can construct a neural surrogate to represent the unknown physical quantity sought, while avoiding having to relearn the known physics entirely. We dub this process surrogate training embedded in physics (STEP) and illustrate that it generalizes well and is robust against overfitting and significant noise in the data. We demonstrate how STEP can be applied to perform dynamic kernel deconvolution to analyse resonant inelastic X-ray scattering spectra and show that surprisingly simple estimator architectures suffice to extract the relevant physical information.
现代物理学中一类普遍存在的挑战是逆问题，即必须从实验测量中提取物理量。解决逆问题的端到端机器学习方法通常需要构建复杂的估计器以达到所需的精度，这主要是因为它们需要学习复杂的潜在物理模型。在此，我们讨论一种替代范式：通过使物理模型具有自动微分能力，我们可以构建一个神经代理来表示所寻求的未知物理量，同时避免完全重新学习已知的物理知识。我们将这个过程称为物理嵌入代理训练（STEP），并说明它具有良好的泛化能力，并且对数据中的过拟合和显著噪声具有鲁棒性。我们展示了如何应用STEP进行动态核反卷积以分析共振非弹性X射线散射光谱，并表明令人惊讶的是，简单的估计器架构就足以提取相关的物理信息。
