High-Precision Ground Characterization of Test-Mass Magnetic Properties for the Taiji Gravitational Wave Mission via a Physics-Informed Neural Framework
This paper proposes an AI-enhanced Differentiable Weighted Least Squares (AI-WLS) framework that combines a dilated residual network with a physical solver to achieve high-precision characterization of test-mass magnetic properties by effectively suppressing non-stationary noise in torsion-pendulum measurements for the Taiji gravitational wave mission.
Chang Liu, Qiong Deng, Huadong Li, Liwei Yang, Xiaodong Peng, Ziren Luo, Yuzhu Zhang, Chen Gao, Xiaotong Wei, Minghui Du, Zihao Xiao, Peng Xu, Bo Liang, Zhi Wang, Li-e Qiang2026-04-28🔬 physics.app-ph