Deep Learning Based Reconstruction of Total Solar Irradiance

The Earth's primary source of energy is the radiant energy generated by the Sun, which is referred to as solar irradiance, or total solar irradiance (TSI) when all of the radiation is measured. A minor change in the solar irradiance can have a significant impact on the Earth's climate and atmosphere. As a result, studying and measuring solar irradiance is crucial in understanding climate changes and solar variability. Several methods have been developed to reconstruct total solar irradiance for long and short periods of time; however, they are physics-based and rely on the availability of data, which does not go beyond 9,000 years. In this paper we propose a new method, called TSInet, to reconstruct total solar irradiance by deep learning for short and long periods of time that span beyond the physical models' data availability. On the data that are available, our method agrees well with the state-of-the-art physics-based reconstruction models. To our knowledge, this is the first time that deep learning has been used to reconstruct total solar irradiance for more than 9,000 years.

[1]  G. Kopp,et al.  A new, lower value of total solar irradiance: Evidence and climate significance , 2011 .

[2]  S. Solanki,et al.  Solar activity over nine millennia: A consistent multi-proxy reconstruction , 2018, Astronomy & Astrophysics.

[3]  Seokjun Seo,et al.  Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classification , 2017, IJCAI.

[4]  S. Solanki,et al.  Reconstruction of solar total irradiance since 1700 from the surface magnetic flux , 2007 .

[5]  Richard Walker,et al.  PD Disease State Assessment in Naturalistic Environments Using Deep Learning , 2015, AAAI.

[6]  C. Timmreck,et al.  The PMIP4 contribution to CMIP6 - Part 3: the Last Millennium, scientific objective and experimental design for the PMIP4 past1000 simulations (in open review for GMD - doi: 10.5194/gmd-2016-278) , 2016 .

[7]  Xiangxiang Zeng,et al.  KGNN: Knowledge Graph Neural Network for Drug-Drug Interaction Prediction , 2020, IJCAI.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  S. Criscuoli.  Effects of Continuum Fudging on Non-LTE Synthesis of Stellar Spectra. I. Effects on Estimates of UV Continua and Solar Spectral Irradiance Variability , 2018, The Astrophysical Journal.

[10]  S. Solanki,et al.  Reconstruction of total and spectral solar irradiance from 1974 to 2013 based on KPVT, SoHO/MDI and SDO/HMI observations , 2014, 1408.1229.

[11]  N. Krivova,et al.  Solar Surface Magnetism and Irradiance on Time Scales from Days to the 11-Year Cycle , 2009 .

[12]  Mike Lockwood,et al.  SOLAR INFLUENCES ON CLIMATE , 2009 .

[13]  Bingsheng He,et al.  PewLSTM: Periodic LSTM with Weather-Aware Gating Mechanism for Parking Behavior Prediction , 2020, IJCAI.

[14]  J. Pongratz,et al.  Climate forcing reconstructions for use in PMIP simulations of the last millennium (v1.0) , 2011 .

[15]  S. Solanki,et al.  Solar total and spectral irradiance reconstruction over the last 9000 years , 2016, Astronomy & Astrophysics.

[16]  J. Hansen.  The Sun's Role in Long-Term Climate Change , 2000 .

[17]  Judith Lean,et al.  Evolution of the Sun's Spectral Irradiance Since the Maunder Minimum , 2000 .

[18]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

[19]  Fei Wang,et al.  Pairwise-Ranking based Collaborative Recurrent Neural Networks for Clinical Event Prediction , 2018, IJCAI.

[20]  J. Haigh,et al.  Solar Irradiance Variability and Climate , 2013, 1306.2770.

[21]  Haodi Jiang,et al.  Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning , 2020, The Astrophysical Journal Supplement Series.

[22]  Chini,et al.  The PMIP 4 contribution to CMIP 6 – Part 3 : the Last Millennium , 2016 .

[23]  Andrew Gordon Wilson,et al.  Learning Scalable Deep Kernels with Recurrent Structure , 2016, J. Mach. Learn. Res..

[24]  Xueqi Cheng,et al.  NeuCast: Seasonal Neural Forecast of Power Grid Time Series , 2018, IJCAI.

[25]  Yvonne C. Unruh,et al.  Solar irradiance variability: a six-year comparison between SORCE observations and the SATIRE model , 2011, 1104.0885.

[26]  Gary J. Rottman,et al.  The SORCE Mission , 2005 .

[27]  Monica G. Bobra,et al.  PREDICTING CORONAL MASS EJECTIONS USING MACHINE LEARNING METHODS , 2016, 1603.03775.

[28]  Fabio Tozeto Ramos,et al.  Predicting Spatio-Temporal Propagation of Seasonal Influenza Using Variational Gaussian Process Regression , 2016, AAAI.

[29]  J. Pratt.  Remarks on Zeros and Ties in the Wilcoxon Signed Rank Procedures , 1959 .

[30]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[31]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[32]  S. Solanki,et al.  EMPIRE: A robust empirical reconstruction of solar irradiance variability , 2017, 1704.07652.

[33]  P. Pilewskie,et al.  Where does Earth’s atmosphere get its energy? , 2017 .

[34]  I. Usoskin.  A History of Solar Activity over Millennia , 2008, Living Reviews in Solar Physics.

[35]  G. Kopp.  Magnitudes and timescales of total solar irradiance variability , 2016, 1606.05258.

[36]  Luyan Liu,et al.  Cross-denoising Network against Corrupted Labels in Medical Image Segmentation with Domain Shift , 2020, IJCAI.

[37]  Haimin Wang,et al.  Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Products and the Random Forest Algorithm , 2017, 1706.02422.

[38]  Jing Li,et al.  Learning Data-Driven Drug-Target-Disease Interaction via Neural Tensor Network , 2020, IJCAI.