Prediction of the level of ionospheric scintillation at equatorial latitudes in Brazil using a neural network

Electron density irregularity structures, often associated with ionospheric plasma bubbles, drive amplitude and phase fluctuations in radio signals that, in turn, create a phenomenon known as ionospheric scintillation. The phenomenon occurs frequently around the magnetic equator where plasma instability mechanisms generate postsunset plasma bubbles and density depletions. A previous correlation study suggested that scintillation at the magnetic equator may provide a forecast of subsequent scintillation at the equatorial ionization anomaly southern peak. In this work, it is proposed to predict the level of scintillation over Sao Luis (2.52°S, 44.3°W; dip latitude: ~2.5°S) near the magnetic equator with lead time of hours but without specifying the moment at which the scintillation starts or ends. A collection of extended databases relating scintillation to ionospheric variables for Sao Luis is employed to perform the training of an artificial neural network with a new architecture. Two classes are considered, not strong (null/weak/moderate) and strong scintillation. An innovative scheme preprocesses the data taking into account similarities of the values of the variables for the same class. A formerly proposed resampling heuristic is employed to provide a balanced number of tuples of each class in the training set. Tests were performed showing that the proposed neural network is able to predict the level of scintillation over the station on the evening ahead of the data sample considered between 17:30 and 19:00 LT.

[1]  S. Stephany,et al.  Survey and prediction of the ionospheric scintillation using data mining techniques , 2010 .

[2]  Terence Bullett,et al.  A Forecasting Ionospheric Real‐time Scintillation Tool (FIRST) , 2010 .

[3]  Srdjan S. Stankovic,et al.  Ionospheric forecasting technique by artificial neural network , 1998 .

[4]  David N. Anderson,et al.  Daytime vertical E × B drift velocities inferred from ground‐based magnetometer observations at low latitudes , 2004 .

[5]  Stephan Stephany,et al.  Training a Neural Network to Detect Patterns Associated with Severe Weather , 2013 .

[6]  P. J. Sultan,et al.  Linear theory and modeling of the Rayleigh‐Taylor instability leading to the occurrence of equatorial spread F , 1996 .

[7]  David N. Anderson,et al.  Forecasting the occurrence of ionospheric scintillation activity in the equatorial ionosphere on a day-to-day basis , 2004 .

[8]  Paul M. Kintner,et al.  Equatorial anomaly effects on GPS scintillations in brazil , 2003 .

[9]  Bernard Widrow,et al.  Neural nets for adaptive filtering and adaptive pattern recognition , 1988, Computer.

[10]  J. S. Hey,et al.  Fluctuations in Cosmic Radiation at Radio-Frequencies , 1946, Nature.

[11]  E. R. de Paula,et al.  Correlation analysis between the occurrence of ionospheric scintillation at the magnetic equator and at the southern peak of the Equatorial Ionization Anomaly , 2014 .

[12]  E. Appleton.  The anomalous equatorial belt in the F2-layer , 1954 .

[13]  Brent M. Ledvina,et al.  Characteristics of the ionospheric F-region plasma irregularities over brazilian longitudinal sector , 2007 .

[14]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[15]  M. A. Abdu,et al.  Outstanding problems in the equatorial ionosphere–thermosphere electrodynamics relevant to spread F , 2001 .

[16]  Stephan Stephany,et al.  A new classification approach for detecting severe weather patterns , 2013, Comput. Geosci..

[17]  Abhijeet Dasgupta,et al.  Equatorial scintillations in relation to the development of ionization anomaly , 2006 .