Abstract

Early detection of interplanetary activity is important when attempting to associate, with better accuracy, interplanetary phenomena with solar activity and geomagnetic disturbances. However, for a large number of interplanetary observations to be done every day, extensive data analysis is required, leading to a delay in the detection of transient interplanetary activity. In particular, the interplanetary scintillation (IPS) observations done with Ooty Radio Telescope (ORT) need extensive human effort to reduce the data and to model, often subjectively, the scintillation power spectra. We have implemented an artificial neural network (ANN) to detect interplanetary activity using the power spectrum scintillation. The ANN was trained to detect the disturbed power spectra, used as an indicator of the interplanetary activity, and to recognize normal and strong scattering spectra from a large data base of IPS spectra. The coincidence efficiency of classification by the network compared with the experts’ judgement to detect the normal, disturbed and strong scattering spectra was found to be greater than 80 per cent. The neural network, when applied during the IPS mapping programme to provide early indication of interplanetary activity, would significantly help the ongoing efforts to predict geomagnetic disturbances.