Operational Dst index prediction model based on combination of artificial neural network and empirical model

In this paper, an operational Dst index prediction model is developed by combining empirical and Artificial Neural Network (ANN) models. ANN algorithms are widely used to predict space weather conditions. While they require a large amount of data for machine learning, large-scale geomagnetic storms have not occurred sufficiently for the last 20 years, Advanced Composition Explorer (ACE) and Deep Space Climate Observatory (DSCOVR) mission operation period. Conversely, the empirical models are based on numerical equations derived from human intuition and are therefore applicable to extrapolate for large storms. In this study, we distinguish between Coronal Mass Ejection (CME) driven and Corotating Interaction Region (CIR) driven storms, estimate the minimum Dst values, and derive an equation for describing the recovery phase. The combined Korea Astronomy and Space Science Institute (KASI) Dst Prediction (KDP) model achieved better performance contrasted to ANN model only. This model could be used practically for space weather operation by extending prediction time to 24 h and updating the model output every hour.

[1]  M. Hudson,et al.  Statistical study of the storm time radiation belt evolution during Van Allen Probes era: CME‐ versus CIR‐driven storms , 2017 .

[2]  Michael Hesse,et al.  Geospace Environmental Modeling (GEM) magnetic reconnection challenge , 2001 .

[3]  R. McPherron,et al.  Forecasting the ring current index Dst in real time , 2000 .

[4]  Daniel T. Welling,et al.  Geospace environment modeling 2008–2009 challenge: Dst index , 2013 .

[5]  H. W. Kroehl,et al.  What is a geomagnetic storm , 1994 .

[6]  Enrico Camporeale,et al.  Multiple‐Hour‐Ahead Forecast of the Dst Index Using a Combination of Long Short‐Term Memory Neural Network and Gaussian Process , 2018, Space Weather.

[7]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[8]  Wolfgang Baumjohann,et al.  The terrestrial ring current: Origin, formation, and decay , 1999 .

[9]  S. Watari.  Geomagnetic storms of cycle 24 and their solar sources , 2017, Earth, Planets and Space.

[10]  Masahisa Sugiura,et al.  Hourly values of equatorial dst for the igy , 1963 .

[11]  R. Lysak,et al.  Magnetospheric Current Systems , 2000 .

[12]  R. Weigel.  Solar wind density influence on geomagnetic storm intensity , 2010 .

[13]  R. Nakamura,et al.  The Scientific Foundations of Forecasting Magnetospheric Space Weather , 2017 .

[14]  L. Kistler,et al.  The Outer Radiation Belt Response to the Storm Time Development of Seed Electrons and Chorus Wave Activity During CME and CIR Driven Storms , 2018, Journal of Geophysical Research: Space Physics.

[15]  J. Raeder,et al.  Foreword [to Special Section on Proton Precipitation Into the Atmosphere] , 2001 .

[16]  Y. Feldstein.  Modelling of the magnetic field of magnetospheric ring current as a function of interplanetary medium parameters , 1992 .

[17]  Fridrich Valach,et al.  Modeling of CME and CIR driven geomagnetic storms by means of artificial neural networks , 2015 .

[18]  J. Habarulema,et al.  Ionospheric Responses to CME‐ and CIR‐Driven Geomagnetic Storms Along 30°E–40°E Over the African Sector From 2001 to 2015 , 2018 .

[19]  C. Russell,et al.  An empirical relationship between interplanetary conditions and Dst , 1975 .

[20]  J. Wanliss,et al.  High-resolution global storm index: Dst versus SYM-H , 2006 .

[21]  Ezequiel Echer,et al.  Introduction to space weather , 2005 .

[22]  S. Kugblenu,et al.  Prediction of the geomagnetic storm associated Dst index using an artificial neural network algorithm , 1999 .

[23]  Hilary V. Cane,et al.  Near-Earth Interplanetary Coronal Mass Ejections During Solar Cycle 23 (1996 – 2009): Catalog and Summary of Properties , 2010 .

[24]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[25]  Fridrich Valach,et al.  A neural network Dst index model driven by input time histories of the solar wind–magnetosphere interaction , 2014 .

[26]  Marina Stepanova,et al.  Prediction of Dst variations from Polar Cap indices using time-delay neural network , 2005 .

[27]  H. Lundstedt,et al.  Prediction of geomagnetic storms from solar wind data using Elman Recurrent Neural Networks , 1996 .

[28]  G. Rangarajan.  Indices of geomagnetic activity. , 1989 .

[29]  Xinlin Li,et al.  A new model for the prediction of Dst on the basis of the solar wind , 2002 .

[30]  Xinlin Li,et al.  Dst model for 1995–2002 , 2006 .

[31]  R. McPherron,et al.  Predicting Geomagnetic Activity: The Dst Index , 2013 .

[32]  P. Wintoft,et al.  Operational forecasts of the geomagnetic Dst index , 2002 .

[33]  Juan A. Lazzús,et al.  Forecasting the Dst index using a swarm‐optimized neural network , 2017 .

[34]  G. Vichare,et al.  Forecasting of SYMH and ASYH indices for geomagnetic storms of solar cycle 24 including St. Patrick’s day, 2015 storm using NARX neural network , 2017, Journal of Space Weather and Space Climate.

[35]  T. Murayama.  Coupling function between solar wind parameters and geomagnetic indices , 1982 .

[36]  P. Wintoft,et al.  Prediction of geomagnetic storms from solar wind data with the use of a neural network , 1994 .

[37]  L. Lyons.  The Geospace Modeling Program Grand Challenge , 1998 .

[38]  N. Ganushkina,et al.  CIR versus CME drivers of the ring current during intense magnetic storms , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[39]  J. Chao,et al.  Influence of the solar wind dynamic pressure on the decay and injection of the ring current , 2003 .

[40]  H. Morgan,et al.  Properties of the HPS‐ICME‐CIR Interaction Event of 9–10 September 2011 , 2018 .

[41]  Henrik Lundstedt,et al.  Geomagnetic storm predictions from solar wind data with the use of dynamic neural networks , 1997 .

[42]  H. Shimazu,et al.  Prediction of the Dst index from solar wind parameters by a neural network method , 2002 .

[43]  Patricia H. Reiff,et al.  Empirical polar cap potentials , 1997 .