F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM...F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.展开更多
In this study, the relationship between the neutral components （N2 and 02） in the E-region of the ionosphere （at 110 km altitude） for the Singapore （01.23 N; 103.55 E） station in the equatorial region and the FI...In this study, the relationship between the neutral components （N2 and 02） in the E-region of the ionosphere （at 110 km altitude） for the Singapore （01.23 N; 103.55 E） station in the equatorial region and the FI0.7 solar flux and z-component of Interplanetary Magnetic Field （IMF-Bz） was investigated. This relationship was determined by means of statistical multiple regression model. As a result, it was observed that the changes in F10.7 solar flux and IMF-Bz were inversely proportional to the changes in N2 and 02. 92% and 83% of changes in N2 and O2 were found to be explained by F10.7 solar flux and IMF-Bz, respectively. When the F10.7 solar flux is changed by 1 s.f.u., it causes a decrease of 2.61×10TM m-3 in N2 and 2.96×1014 m-3 in O2. Change of I nT in IMF-Bz causes a decrease of 9.95× 1015 m-3 in N2 and 1.69× 1015 m-3 in O2.展开更多
文摘F_(10.7)指数是太阳活动的重要指标,准确预测F_(10.7)指数有助于预防和缓解太阳活动对无线电通信、导航和卫星通信等领域的影响.基于F_(10.7)射电流量的特性,在双向长短时记忆网络(Bidirectional Long Short-Term Memory Network,BiLSTM)基础上融入注意力机制(Attention),提出了一种基于BiLSTM-Attention的F_(10.7)预报模型.在加拿大DRAO数据集上其平均绝对误差(MAE)为5.38,平均绝对百分比误差(MAPE)控制在5%以内,相关系数(R)高达0.987,与其他RNN模型相比拥有优越的预测性能.针对中国廊坊L&S望远镜观测的F_(10.7)数据集,提出了一种转换平均校准(Conversion Average Calibration,CAC)方法进行数据预处理,处理后的数据与DRAO数据集具有较高的相关性.基于该数据集对比分析了RNN系列模型的预报效果,实验结果表明,BiLSTM-Attention和BiLSTM两种模型在预测F_(10.7)指数方面具有较好的优势,表现出较好的预测性能和稳定性.
文摘In this study, the relationship between the neutral components （N2 and 02） in the E-region of the ionosphere （at 110 km altitude） for the Singapore （01.23 N; 103.55 E） station in the equatorial region and the FI0.7 solar flux and z-component of Interplanetary Magnetic Field （IMF-Bz） was investigated. This relationship was determined by means of statistical multiple regression model. As a result, it was observed that the changes in F10.7 solar flux and IMF-Bz were inversely proportional to the changes in N2 and 02. 92% and 83% of changes in N2 and O2 were found to be explained by F10.7 solar flux and IMF-Bz, respectively. When the F10.7 solar flux is changed by 1 s.f.u., it causes a decrease of 2.61×10TM m-3 in N2 and 2.96×1014 m-3 in O2. Change of I nT in IMF-Bz causes a decrease of 9.95× 1015 m-3 in N2 and 1.69× 1015 m-3 in O2.
