Physics-Informed Neural Networks for Complex Eigenfrequency Identification and Mode Structure Reconstruction of the Ground-State ITG Branch
2026-08-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed a special type of neural network called a physics-informed neural network (PINN) to study complicated wave patterns in plasma inside tokamak reactors. They focused on a tricky area where plasma behavior is closely linked to how well the reactor confines it. To handle the complex math and fluctuating data, they used a new method combining special encoding techniques and a careful training process. Their approach successfully figured out important wave properties from limited data and worked better than previous methods. This work helps in understanding detailed plasma wave behaviors in fusion devices.
Physics-informed neural networksTokamakPlasma confinementIon-temperature-gradient (ITG) drift wavesComplex eigenfrequencyMode fieldFourier feature encodingEdge transportHigh-confinement modeNeural network training
Authors
Dengdi Sun, Bingbing Zhang, Xiao Wang, Zikang Yan, Yuqiang Tao, Qingquan Yang, Guosheng Xu, Jin Tang
Abstract
Physics-informed neural networks (PINNs) combine sparse observations with physical equations, providing an important approach for modeling complex plasma processes and inferring unknown physical quantities. The steep-gradient pedestal of high-confinement-mode tokamaks is closely linked to plasma confinement and edge transport. Analyzing ion-temperature-gradient (ITG) drift waves in this region requires jointly identifying complex eigenfrequencies and reconstructing two-dimensional complex-valued mode fields. Localized high-frequency oscillations, strong real-imaginary coupling, and nonlinear coupling between the mode field and eigenfrequency challenge PINN representation and joint optimization. To address these challenges, we propose a physics-informed neural framework combining Fourier feature encoding, complex-valued feature propagation, and three-stage training. Under sparse observations and physical constraints, it jointly solves for the complex eigenfrequency and mode field of a representative ground-state ITG branch. Experiments show that the framework accurately recovers the target complex eigenfrequency and two-dimensional complex-valued mode field and outperforms representative PINN baselines. It also provides a basis for analyzing higher-order and multiple-branch drift-wave modes.