Solar flares are among the most intense forms of solar activity. Understanding the evolution of physical parameters in the solar atmosphere during flare events is key to studying their mechanisms and improving prediction capabilities, but directly measuring quantities such as electron number density, temperature, and plasma velocity remains challenging. Here, we introduce a novel, fully connected neural network, trained on synthetic data from the radiative hydrodynamics code simulations, to perform rapid inversion of physical parameters from H spectral line profiles. The spectral data were processed to align with the observational resolution of the Chinese H Solar Explorer satellite, enabling seamless application of the model to real-world observations. Results are highly consistent with simulations, achieving low errors under diverse flare conditions. We applied the developed model to analyze observations of a class X7. 1 solar flare on October 1, 2024, revealing reasonable spatial and temporal evolution of key parameters throughout different flare phases. This work demonstrates the potential of deep learning techniques for fast and reliable spectral inversion, providing new tools for solar flare diagnostics based on H data.
Xu et al. (Mon,) studied this question.