We propose physics-informed digital twin (PIDT): a fiber parameter estimation approach that combines a parameterized split-step method with a physics-informed loss. PIDT improves accuracy and convergence speed with lower complexity compared to previous neural operators.

翻译：本文提出物理信息数字孪生（PIDT）：一种融合参数化分步法与物理信息损失函数的光纤参数估计方法。相较于先前的神经算子方法，PIDT在降低复杂度的同时，显著提升了估计精度与收敛速度。