Prediction of Mode Structure Using A Novel Physics-Embedded Neural ODE Method
We designed a new artificial neural network by modifying the neural ordinary differential equation (NODE) framework to successfully predict the time evolution of the 2D mode profile in both the linear growth and nonlinear saturated stages. Starting from the magnetohydrodynamic (MHD) equations, simplifying assumptions were applied based on physical properties and symmetry considerations of the energetic-particle-driven geodesic acoustic mode (EGAM) to reduce complexity. Our approach embeds physical laws directly into the neural network architecture by exposing latent differential states, enabling the model to capture complex features in the nonlinear saturated stage that are difficult to describe analytically, and thus, the new artificial neural network is named as ExpNODE (Exposed latent state Neural ODE). ExpNODE was evaluated using a data set generated from first-principles simulations of the EGAM instability, focusing on the pre-saturated stage and the nonlinear saturated stage where the mode properties are most complex. Compared to state-of-the-art models such as ConvLSTM, ExpNODE with physical information not only achieved lower test loss but also converged faster during training. Specifically, it outperformed ConvLSTM method in both the 20-step and 40-step prediction horizons, demonstrating superior accuracy and efficiency. Additionally, the model exhibited strong generalization capabilities, accurately predicting mode profiles outside the training data set. Visual comparisons between model predictions and ground truth data showed that ExpNODE with physical information closely captured detailed features and asymmetries inherent in the EGAM dynamics that were not adequately captured by other models. These results suggest that integrating physical knowledge into neural ODE frameworks enhances their performance, and provides a powerful tool for modeling complex plasma phenomena.