Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning
<p><strong>Context:</strong> Solar activity plays a quintessential role in affecting the interplanetary medium and space weather around Earth. Remote-sensing instruments on board heliophysics space missions provide a pool of information about solar activity by measuring the solar m...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
EDP Sciences
2021
|
| _version_ | 1826307493140103168 |
|---|---|
| author | Dos Santos, LFG Bose, S Salvatelli, V Neuberg, B Cheung, MCM Janvier, M Jin, M Gal, Y Boerner, P Baydin, AG |
| author_facet | Dos Santos, LFG Bose, S Salvatelli, V Neuberg, B Cheung, MCM Janvier, M Jin, M Gal, Y Boerner, P Baydin, AG |
| author_sort | Dos Santos, LFG |
| collection | OXFORD |
| description | <p><strong>Context:</strong> Solar activity plays a quintessential role in affecting the interplanetary medium and space weather around Earth. Remote-sensing instruments on board heliophysics space missions provide a pool of information about solar activity by measuring the solar magnetic field and the emission of light from the multilayered, multithermal, and dynamic solar atmosphere. Extreme-UV (EUV) wavelength observations from space help in understanding the subtleties of the outer layers of the Sun, that is, the chromosphere and the corona. Unfortunately, instruments such as the Atmospheric Imaging Assembly (AIA) on board the NASA Solar Dynamics Observatory (SDO), suffer from time-dependent degradation that reduces their sensitivity. The current best calibration techniques rely on flights of sounding rockets to maintain absolute calibration. These flights are infrequent, complex, and limited to a single vantage point, however.</p>
<p><strong>Aims:</strong> We aim to develop a novel method based on machine learning (ML) that exploits spatial patterns on the solar surface across multiwavelength observations to autocalibrate the instrument degradation.</p>
<p><strong>Methods:</strong> We established two convolutional neural network (CNN) architectures that take either single-channel or multichannel input and trained the models using the SDOML dataset. The dataset was further augmented by randomly degrading images at each epoch, with the training dataset spanning nonoverlapping months with the test dataset. We also developed a non-ML baseline model to assess the gain of the CNN models. With the best trained models, we reconstructed the AIA multichannel degradation curves of 2010-2020 and compared them with the degradation curves based on sounding-rocket data.</p>
<p><strong>Results:</strong> Our results indicate that the CNN-based models significantly outperform the non-ML baseline model in calibrating instrument degradation. Moreover, multichannel CNN outperforms the single-channel CNN, which suggests that cross-channel relations between different EUV channels are important to recover the degradation profiles. The CNN-based models reproduce the degradation corrections derived from the sounding-rocket cross-calibration measurements within the experimental measurement uncertainty, indicating that it performs equally well as current techniques.</p>
<p><strong>Conclusions:</strong> Our approach establishes the framework for a novel technique based on CNNs to calibrate EUV instruments. We envision that this technique can be adapted to other imaging or spectral instruments operating at other wavelengths.</p> |
| first_indexed | 2024-03-07T07:03:53Z |
| format | Journal article |
| id | oxford-uuid:e03d8046-b623-4e44-93d4-9c839447d879 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:03:53Z |
| publishDate | 2021 |
| publisher | EDP Sciences |
| record_format | dspace |
| spelling | oxford-uuid:e03d8046-b623-4e44-93d4-9c839447d8792022-04-06T11:27:43ZMultichannel autocalibration for the Atmospheric Imaging Assembly using machine learningJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:e03d8046-b623-4e44-93d4-9c839447d879EnglishSymplectic ElementsEDP Sciences2021Dos Santos, LFGBose, SSalvatelli, VNeuberg, BCheung, MCMJanvier, MJin, MGal, YBoerner, PBaydin, AG<p><strong>Context:</strong> Solar activity plays a quintessential role in affecting the interplanetary medium and space weather around Earth. Remote-sensing instruments on board heliophysics space missions provide a pool of information about solar activity by measuring the solar magnetic field and the emission of light from the multilayered, multithermal, and dynamic solar atmosphere. Extreme-UV (EUV) wavelength observations from space help in understanding the subtleties of the outer layers of the Sun, that is, the chromosphere and the corona. Unfortunately, instruments such as the Atmospheric Imaging Assembly (AIA) on board the NASA Solar Dynamics Observatory (SDO), suffer from time-dependent degradation that reduces their sensitivity. The current best calibration techniques rely on flights of sounding rockets to maintain absolute calibration. These flights are infrequent, complex, and limited to a single vantage point, however.</p> <p><strong>Aims:</strong> We aim to develop a novel method based on machine learning (ML) that exploits spatial patterns on the solar surface across multiwavelength observations to autocalibrate the instrument degradation.</p> <p><strong>Methods:</strong> We established two convolutional neural network (CNN) architectures that take either single-channel or multichannel input and trained the models using the SDOML dataset. The dataset was further augmented by randomly degrading images at each epoch, with the training dataset spanning nonoverlapping months with the test dataset. We also developed a non-ML baseline model to assess the gain of the CNN models. With the best trained models, we reconstructed the AIA multichannel degradation curves of 2010-2020 and compared them with the degradation curves based on sounding-rocket data.</p> <p><strong>Results:</strong> Our results indicate that the CNN-based models significantly outperform the non-ML baseline model in calibrating instrument degradation. Moreover, multichannel CNN outperforms the single-channel CNN, which suggests that cross-channel relations between different EUV channels are important to recover the degradation profiles. The CNN-based models reproduce the degradation corrections derived from the sounding-rocket cross-calibration measurements within the experimental measurement uncertainty, indicating that it performs equally well as current techniques.</p> <p><strong>Conclusions:</strong> Our approach establishes the framework for a novel technique based on CNNs to calibrate EUV instruments. We envision that this technique can be adapted to other imaging or spectral instruments operating at other wavelengths.</p> |
| spellingShingle | Dos Santos, LFG Bose, S Salvatelli, V Neuberg, B Cheung, MCM Janvier, M Jin, M Gal, Y Boerner, P Baydin, AG Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title | Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title_full | Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title_fullStr | Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title_full_unstemmed | Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title_short | Multichannel autocalibration for the Atmospheric Imaging Assembly using machine learning |
| title_sort | multichannel autocalibration for the atmospheric imaging assembly using machine learning |
| work_keys_str_mv | AT dossantoslfg multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT boses multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT salvatelliv multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT neubergb multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT cheungmcm multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT janvierm multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT jinm multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT galy multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT boernerp multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning AT baydinag multichannelautocalibrationfortheatmosphericimagingassemblyusingmachinelearning |