由太阳活动引发的磁暴事件会导致地球磁场产生剧烈变化,进而影响通信、导航、电力等工程应用系统的服务性能.在空间物理领域通常利用Dst指数表征磁暴强度的变化,本文提出一种基于卷积神经网络(CNN)、门控循环单元(GRU)和长短时记忆网络(...由太阳活动引发的磁暴事件会导致地球磁场产生剧烈变化,进而影响通信、导航、电力等工程应用系统的服务性能.在空间物理领域通常利用Dst指数表征磁暴强度的变化,本文提出一种基于卷积神经网络(CNN)、门控循环单元(GRU)和长短时记忆网络(LSTM)的磁暴预测模型(C-G-LSTM),能够提前1~6 h预测Dst指数.进一步利用美国航空航天局(National Aeronautics and Space Administration,NASA)提供的2010-2019年Dst指数评估混合深度学习预测模型的性能.结果显示最大均方根误差不超过7.29 nT;最大平均绝对误差不超过5.03 nT,磁暴期间误差有所增大.与已有研究结果相比,本文所提出的模型具有较高精度,且无须提供太阳风温度、太阳风动压以及行星际磁场分量等输入参数,适用于业务预报.展开更多
The Dst index has been commonly used to measure the geomagnetic effectiveness of magnetic storm events for several decades.Based on Burton’s empirical Dst model and the global magneto-hydrodynamic(MHD)simulation of E...The Dst index has been commonly used to measure the geomagnetic effectiveness of magnetic storm events for several decades.Based on Burton’s empirical Dst model and the global magneto-hydrodynamic(MHD)simulation of Earth’s magnetosphere,here we proposed a semi-empirical model to forecast the Dst index during geomagnetic storms.In this model,the ring current contribution to the Dst index is derived from Burton’s model,while the contributions from other current systems are obtained from the global MHD simulation.In order to verify the model accuracy,a number of recent magnetic storm events are tested and the simulated Dst index is compared with the observation through the correlation coefficient(CC),prediction efficiency(PE),root mean square error(RMSE)and central root mean square error(CRMSE).The results indicate that,in the context of moderate and intense geomagnetic storm events,the semi-empirical model performs well in global MHD simulations,showing relatively higher CC and PE,and lower RMSE and CRMSE compared to those from the empirical model.Compared with the physics-based ring current models,this model inherits the advantage of fast processing from the empirical model,and easy implementation in a global MHD model of Earth’s magnetosphere.Therefore,it is suitable for the Dst estimation under a context of a global MHD simulation.展开更多
文摘由太阳活动引发的磁暴事件会导致地球磁场产生剧烈变化,进而影响通信、导航、电力等工程应用系统的服务性能.在空间物理领域通常利用Dst指数表征磁暴强度的变化,本文提出一种基于卷积神经网络(CNN)、门控循环单元(GRU)和长短时记忆网络(LSTM)的磁暴预测模型(C-G-LSTM),能够提前1~6 h预测Dst指数.进一步利用美国航空航天局(National Aeronautics and Space Administration,NASA)提供的2010-2019年Dst指数评估混合深度学习预测模型的性能.结果显示最大均方根误差不超过7.29 nT;最大平均绝对误差不超过5.03 nT,磁暴期间误差有所增大.与已有研究结果相比,本文所提出的模型具有较高精度,且无须提供太阳风温度、太阳风动压以及行星际磁场分量等输入参数,适用于业务预报.
基金supported by NNSFC grants 42150101,42188105,42304189National Key R&D program of China No.2021YFA-0718600the Pandeng Program of National Space Science Center,Chinese Academy of Sciences.
文摘The Dst index has been commonly used to measure the geomagnetic effectiveness of magnetic storm events for several decades.Based on Burton’s empirical Dst model and the global magneto-hydrodynamic(MHD)simulation of Earth’s magnetosphere,here we proposed a semi-empirical model to forecast the Dst index during geomagnetic storms.In this model,the ring current contribution to the Dst index is derived from Burton’s model,while the contributions from other current systems are obtained from the global MHD simulation.In order to verify the model accuracy,a number of recent magnetic storm events are tested and the simulated Dst index is compared with the observation through the correlation coefficient(CC),prediction efficiency(PE),root mean square error(RMSE)and central root mean square error(CRMSE).The results indicate that,in the context of moderate and intense geomagnetic storm events,the semi-empirical model performs well in global MHD simulations,showing relatively higher CC and PE,and lower RMSE and CRMSE compared to those from the empirical model.Compared with the physics-based ring current models,this model inherits the advantage of fast processing from the empirical model,and easy implementation in a global MHD model of Earth’s magnetosphere.Therefore,it is suitable for the Dst estimation under a context of a global MHD simulation.
