Recent news
Method of geomagnetic data analysis based on the combination of wavelet transform with radial basis neural networks
- Institute of Cosmophysical Researches and Radio Wave Propagation FEB RAS
- Kamchatka State Technical University, Russia
The present report is devoted to the development of tools intended for the
analysis of the Earth's magnetic field parameters, the extraction of
geomagnetic disturbances and estimation of field properties applying
artificial intelligence and wavelet analysis according to the data
obtained from ground-based observatories. In this report a method for the
analysis of the Earth's magnetic field variations (on the example of
H-vector), based on the combination of wavelet analysis with radial basis
neural networks, is suggested. This method allows to determine the
components of field variations, which characterize degree of disturbance
of field, to study their structure, to classify features of the data and
to estimate condition of field. On the basis of the data feature
separation in wavelet space, statistical properties of the process are
analyzed and informative features are extracted. Extracted features
determine the radial layer of the network, which specifies belonging of
the feature to a class.
The method makes it possible to study the subtle features of geomagnetic
data structure, and it can be implemented as an automatic tool for rapid
estimation of the Earth's magnetic field condition. The method has been
successfully tested on the Earth's magnetic field data obtained from
Paratunka observatory (Paratunka, Kamchatka region, Far East of Russia).
The approbation of the method confirmed its effectiveness and allowed to
extract classification features in the field variations which characterize
the field disturbance degree.