Research ArticleSPACE SCIENCES

A deep learning virtual instrument for monitoring extreme UV solar spectral irradiance

See allHide authors and affiliations

Science Advances  02 Oct 2019:
Vol. 5, no. 10, eaaw6548
DOI: 10.1126/sciadv.aaw6548
  • Fig. 1 Spectral and temperature response of AIA and EVE.

    The spectra measured by the EVE Instrument (A) and spectral response of the narrowband images from the AIA instrument onboard SDO (B) overlap. Each of the 14 emission lines we recover in this project (shown in all panels as vertical lines) has a characteristic temperature associated with them (denoted using shades of color). Given that each of the AIA filters assembles light emitted by plasma of a wide range of temperatures (C), it is possible to combine their information to recover the part of the spectrum that used to be measured by the MEGS-A instrument, which is no longer operational. For these EVE spectra (A), the MEGS-A spectral region contains 60% of the total solar EUV irradiance. AIA images and EVE data from 5 January 2014.

  • Fig. 2 Proposed neural network architecture.

    After computing summary statistics of the input AIA images and making a prediction via a linear model, a CNN makes a prediction that corrects this linear model. The combined linear + CNN model is shown in bold colors and arrows. The numbers attached to the boxes denote the sizes of the representations of the data as they goes through the network, e.g., the first block annotated with 256, 256, and 9 represents an input of 256 × 256 pixels and 9 channels. We produce spatially resolved maps in units of irradiance to validate how the CNN is operating (see Fig. 5) by rearranging commutative operations in the last two layers of the CNN (blue dashed path) and the linear model (red dashed path). These operations yield identical outputs as the original (bold) model (illustrated with faint vertical lines), but recasting them this way enable the diagnosis of the model’s operation.

  • Fig. 3 Emission prediction of Fe XX line for several models.

    We plot a histogram of the results of the prediction on the test set for different model implementations, with a log scale color bar. The closer the points are scattered around the line, the better the predictions are when compared to observations. We can see that the data-driven models greatly improve upon the DEM inversion, and the full model that includes the CNN further increases accuracy, especially on the less frequent, higher amplitude flares.

  • Fig. 4 Linear weights for the Huber Mean + Std model per line.

    We visualize heatmaps, where red indicates positive weights and blue indicates negative weights with intensity proportional to weight. The first row is features that are the average (i.e., total irradiance); the second is features that are the standard deviation (i.e., variance of irradiance). Most MEGS-A lines are primarily a function of nearby AIA observations (e.g., Fe IX is overwhelmingly just a rescaling of the AIA data). Other lines make use of the standard deviation features (e.g., Fe XX is primarily driven by variance in 131 Å).

  • Fig. 5 Spatially rearranged predictions.

    Results from the model after it has been rearranged to produce spatial results. Global (i.e., image-sized 1 × 1) features are due to linear model applied to standard deviation features; low-frequency (i.e., blocky 15 × 15) features are due to the CNN, which has low spatial resolution; high-frequency details are due to the linear model on average AIA features (i.e., 256 × 256). The linear model has learned a largely correct model mapping AIA to MEGS-A, which is corrected, especially during flaring events, by the CNN.

  • Table 1 Per-line average relative error for the methods evaluated in this paper.

    Per-line average relative error for the methods evaluated in this paper.. We provide summary statistics for different models for all lines, where the values are percentages of the average relative error defined in the “Data setup and evaluation criteria” section in Results. The top part of the table indicates results averaged over the entire test set, whereas for the bottom part only data points where the Fe XX line is in the 95th percentile are kept, to focus on flare conditions. Numbers in bold indicate the best result within the given column.

    Line and log THeHeFeFeFeMgFeFeFeFeFeFeFeFeMinMeanMedianMax
    IIIIVIIIIXXIXXIXIIXIIIXIVXVXVIXVIIIXX
    4.74.85.65.86.06.06.16.16.26.36.36.46.87.0
    303 Å256 Å131 Å171 Å177 Å368 Å180 Å195 Å202 Å211 Å284 Å335 Å93 Å132 Å
    Overall
    Physics8.666.093.532.762.863.582.662.622.922.784.905.6913.0713.392.625.393.5513.39
    L2-Mean2.702.481.951.531.953.801.761.632.051.974.2810.031.7811.711.533.542.0111.71
    L2-Mean-Std2.482.402.722.152.774.562.302.302.633.343.817.482.5310.852.153.742.6710.85
    Huber-Mean1.151.361.700.682.004.902.361.831.802.005.6310.511.743.550.682.941.9210.51
    Huber-Mean-Std1.271.741.210.792.044.711.921.391.332.444.927.121.442.670.792.501.837.12
    Linear + CNN1.311.241.671.951.193.211.151.001.502.403.724.611.282.071.002.021.594.61
    Flare conditions (Fe XX 95 percentile)
    Physics18.1815.4816.573.871.913.232.332.604.802.914.414.8366.2064.001.9115.094.6066.20
    L2-Mean2.162.252.992.073.025.062.842.572.942.933.205.984.3611.522.073.852.9711.52
    L2-Mean-Std4.184.645.353.714.797.023.964.134.185.065.625.705.2011.093.715.334.9311.09
    Huber-Mean1.581.472.150.981.964.591.721.271.251.764.318.452.6417.910.983.721.8617.91
    Huber-Mean-Std2.052.391.811.243.074.822.361.942.822.714.505.234.0410.671.243.552.7710.67
    Linear + CNN1.891.551.691.791.483.321.301.412.302.153.273.852.037.551.302.541.967.55

Supplementary Materials

  • Supplementary Materials

    This PDF file includes:

    • Fig. S1. Emission prediction of Fe XVIII line for several models.
    • Fig. S2. Emission prediction of He II line for several models.
    • Fig. S3. Emission prediction of Fe XI line for several models.

    Download PDF

    Files in this Data Supplement:

Stay Connected to Science Advances

Navigate This Article