17:15 〜 18:45
[PEM11-P21] Forecast of CIR-driven geomagnetic storms using the deep neural networks
The geomagnetic field disturbance, known as the indicator of the magnetospheric disturbance on the Earth, is one of the essential indicators for the space weather forecast. The magnetospheric condition strongly depends on the solar wind variation associated with, for example, coronal mass ejection (CME) and/or co-rotating interaction region (CIR). Here, we focus on CIR-driven geomagnetic storms, which are originated from high-speed plasma flow from coronal holes. It is known that the solar wind variation depends on the location and scale of coronal holes. In particular, the solar wind emitted from coronal holes near the solar equatorial region are likely to cause a drastic change of ring current, resulting a geomagnetic storm that can be detected as a global change of magnetic field both in space and on the ground. One of the difficulties for the geomagnetic storm forecast is that the interaction between solar wind and magnetosphere includes nonlinear processes. In addition, different characteristics for each storm event make it difficult to predict geomagnetic storms only using physically based simulations. In this study, we aim to develop the machine learning model for the prediction of CIR-driven geomagnetic storms.
We have developed the regression prediction model of solar wind that have applied from the solar flare prediction model using deep neural networks (DeFN). First, the database of coronal holes (location coordinates, area) and solar wind (speed, plasma density, IMF Bz) is made from the observation data in 2017-2022 for learning. The parameters for coronal holes are derived from by SDO spacecraft data, while solar wind parameters are derived from DSCOVR spacecraft. The time intervals when CME-driven geomagnetic storms are likely to occur are excluded from the database. We find that the model can tentatively estimate the solar wind speed with an accuracy of about 100 km/s. As a next step, geomagnetic indices (i.e., Dst, AE, and Kp indices) are included in the database to predict the scale of geomagnetic storm intensity in the Earth's magnetosphere. We are now improving the model and analyzing the correlation among input feature parameters.
We have developed the regression prediction model of solar wind that have applied from the solar flare prediction model using deep neural networks (DeFN). First, the database of coronal holes (location coordinates, area) and solar wind (speed, plasma density, IMF Bz) is made from the observation data in 2017-2022 for learning. The parameters for coronal holes are derived from by SDO spacecraft data, while solar wind parameters are derived from DSCOVR spacecraft. The time intervals when CME-driven geomagnetic storms are likely to occur are excluded from the database. We find that the model can tentatively estimate the solar wind speed with an accuracy of about 100 km/s. As a next step, geomagnetic indices (i.e., Dst, AE, and Kp indices) are included in the database to predict the scale of geomagnetic storm intensity in the Earth's magnetosphere. We are now improving the model and analyzing the correlation among input feature parameters.