R. Kono

We develop a physics-informed neural network (PINN)-based framework for simulating electron–ion two-fluid plasmas with large scale separation. As a benchmark, we examine the one-dimensional diffusion of a magnetized low-temperature plasma and compute the spatiotemporal evolution of the two-fluid variables. The governing equations, initial conditions, and boundary conditions are embedded into the composite loss function, and the forward problem is solved by minimizing this loss function. Accuracy is evaluated by comparison with conventional numerical simulations. To handle the intrinsic electron–ion multiscale nature, we adopt a species-dependent normalization that scales each variable by appropriate thermal and characteristic quantities, yielding improved stability and a mean relative error of 3.08 × 10−3. Although training instability occurs for certain hyperparameter choices, such as different learning rates or random initializations, well-converged cases can be clearly identified from the loss evolution. Therefore, this instability does not constitute a serious practical limitation. The results further indicate that learning stability depends on how strongly the solution is anchored by boundary constraints. Neumann-type boundary conditions exhibit sensitivity to learning rate and initialization, whereas Dirichlet conditions improve reproducibility and robustness. Overall, this study clarifies how normalization and boundary-condition design jointly govern training stability in PINN-based two-fluid plasma simulations.

This study demonstrates the feasibility of applying Physics‐Informed Neural Networks (PINNs) to reconstruct the spatial and temporal evolution of two‐dimensional magnetohydrodynamic (MHD) reconnection structures from limited in situ observational data. By embedding the complete set of MHD equations into the loss function, the reconstructed solutions naturally satisfy the governing physical laws. The reconstruction accuracy is systematically evaluated by varying the number, spatial distribution, and sampling interval of observation points. The analysis reveals that placing observation points both upstream and downstream of the plasmoid significantly enhances reconstruction accuracy, highlighting the importance of capturing both the early‐time evolution near the ‐point and the well‐developed downstream structures. These findings demonstrate the potential of PINNs as a powerful tool for recovering large‐scale MHD reconnection structures from sparse data, while also providing practical guidance for the design and operation of future multi‐satellite observation missions.