The development of a regional geomagnetic daily variation model using neural networks

Global and regional geomagnetic field models give the components of the geo magnetic field as functions of position and epoch; most utilise a polynomia l or Fourier series to map the input variables to the geomagnetic field val ues. The only temporal variation generally catered for in these models is t he long term secular variation. However, there is an increasing need amongs t certain users for models able to provide shorter term temporal variations , such as the geomagnetic daily variation. In this study, for the first tim e, artificial neural networks (ANNs) are utilised to develop a geomagnetic daily variation model. The model developed is for the southern African regi on; however, the method used could be applied to any other region or even g lobally. Besides local time and latitude, input variables considered in the daily variation model are season, sunspot number, and degree of geomagneti c activity. The ANN modelling of the geomagnetic daily variation is found t o give results very similar to those obtained by the synthesis of harmonic coefficients which have been computed by the more traditional harmonic anal ysis of the daily variation.