The Dst index is hourly calculated using magnetic measurements from four ground-based low-latitude observatories which are Hermanus, Kakioka, Honolulu, and San Juan observatories (Masahito et al., 2015). The original formula for the Dst index calculation was described in Sugiura ( 1964, 1969), and Sugiura and Kamei ( 1991). Later on, Sugiura ( 1964) published the hourly average value of the low-latitude horizontal ( H) component of the Earth's magnetic field. The basic idea to the Dst index was first introduced by Sugiura and Chapman ( 1960). The Dst index measures the intensity of the globally symmetrical equatorial electrojet (ring current) that is caused by solar wind plasma ejecta and/or high-speed streams. ( 2012) represent a comparison of different Dst models. However, several authors focus their work on the prediction of the disturbance storm time ( Dst) index (Caswell, 2014 Gonzalez et al., 2004 Kim et al., 2014 Mays et al., 2009 Qin & Nishii, 2015 Temerin & Li, 2002). Numerous efforts have been made during the last decades to find a relationship between solar and interplanetary phenomena and geomagnetic indices (Li et al., 2007 MacDonald & Ward, 1963 Uwamahoro & Habarulema, 2014). Nowadays, geomagnetic storm forecasting is one of the main subjects of the space weather studies. The space weather and the solar-terrestrial relationship have been under investigation for a long time. In addition, the results show a strong dependence on the solar wind electric current. The results are outstanding in term of accuracy when considering a medium-term prediction of 12 hr in advance and in term of timing of the Dst minimum occurrence. Generally, the duration and number of the input parameters significantly affect the training and prediction performance of the applied ANN. The results indicate an adequate accuracy of R = 0.876 for prediction 2 hr in advance and R = 0.857 for prediction 12 hr in advance. Several ANN structures were tested and the best results were determined using the correlation coefficient ( R) during the training and prediction phases. The input parameters are the solar wind interplanetary magnetic field, southward component of interplanetary magnetic field, temperature, density, speed, pressure, and electric field. The ANN uses 24 past hourly solar wind parameters values to forecast the Dst index. We propose an artificial neural network for the prediction of disturbance storm time ( Dst) index 1 to 12 hr ahead. The results are outstanding in term of accuracy when considering a medium-term prediction of 12 hr in advance and in terms of timing of the Dst minimum occurrence. The power of the proposed ANN was illustrated using the strongest six storms recorded during the prediction period. While the period from 1 January 2016 to was used to test the prediction capabilities of the ANN. The ANN was trained on the data period from 1 January 2007 to 31 December 2015, which contains 78,888 hourly data samples. The input parameters are the solar wind interplanetary magnetic field, north-south component of interplanetary magnetic field, temperature, density, speed, pressure, and electric field. The ANN uses past near-Earth solar wind parameter values to forecast the Dst. In this work, we propose an artificial neural network (ANN) with seven input parameters for the prediction of disturbance storm time ( Dst) index 1 to 12 hr ahead.
0 kommentar(er)
