Machine Learning–based Separation of the He I 10830 Å Chromospheric Signal: Quantitative Analysis of Chromosphere–Corona Intensity in the Quiet Sun

The He I 10830 Å line, a crucial optically thin chromospheric line, is frequently used to study coronal heating and vertical coupling across the chromosphere–corona interface. However, its images are severely contaminated by the strong photospheric background signal, hindering the analysis of fine chromospheric structures. Given the morphological differences between the active region and the quiet Sun (QS), we propose separating the He I 10830 Å chromospheric signal using two deep learning convolutional neural network models. Our model utilizes TiO images and crossband learning to infer the He I 10830 Å photospheric background. The output is combined with an exponential absorption model to achieve quantitative analysis of the pure chromospheric component. Joint analysis of Solar Dynamics Observatory data and the separated QS structures reveals a strong spatial negative correlation between chromospheric He I 10830 Å intensities ( R ≈ −0.84 in 304 Å) and significant layered coupling with EUV (171, 193, and 304 Å) radiation. Furthermore, strong He I 10830 Å absorption areas are highly correlated with regions of strong magnetic fields, while 171 Å radiative enhancement areas extend to the strong magnetic field edges and the mixed-polarity regions. These findings quantify the radiation intensity relationship between He I 10830 Å and EUV bands in the QS. It also demonstrates the differences in heating characteristics between unipolar and mixed-polarity magnetic fields.