基于深度学习的SuperDARN雷达极区电离层对流电势模型构建及预测

来源 :地球物理学报 | 被引量 : 0次 | 上传用户:a8058058
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
电离层等离子体对流是表征电离层电动力学的重要现象,对空间天气有着重要的指示作用.SuperDARN雷达网是研究中高纬电离层对流的重要手段,也是获得对流电势数据的重要来源.本文基于SuperDARN雷达12月份的对流电势数据,采用BP模型、FC-LSTM模型以及ED-ConvLSTM时空序列模型构建了高纬电离层等离子体对流电势30min预测模型,然后采用独立的数据集,基于预测值与实测值的结构相似度(SSIM)、均方根误差(RMSE)以及线性相关系数(LC)三个统计指标对模型的性能进行了评估,同时分析对比了三种模型预测的越极盖电势(CPCP)和越极盖电场(CPEF)与实测值的统计分布情况.结果 表明,BP模型和FC-LSTM模型由于没有充分挖掘到空间上的信息,因此整体误差较大,前者SSIM、LC以及RMSE分别为0.80、0.89、4.38 kV,后者为0.76、0.86、4.96 kV,而ED-ConvLSTM模型则分别为0.83、0.91、3.96 kV,因其能充分捕捉到空间上的信息,三个指标明显优于前两种模型,同时在CPCP分布和CPEF分布的相似度上,EI-ConvLSTM模型性能也表现得最好.本文结果证明了时空序列模型ED-ConvLSTM在对流电势预测上的有效性.
其他文献
Compact torus(CT)injection is one of the most promising methods for the central fuelling of next-generation reactor-grade fusion devices due to its high density,high velocity,and self-contained magnetised structure.A newly compact torus injector(CTI)devic
The flashover performance of insulating materials plays an important role in the development of high-voltage insulation systems.In this paper,silicone rubber(SIR)is modified by CF4 radio frequency capacitively coupled plasma(CCP)for the improvement of sur
With the undergoing and planned implementations of mega constellations of thousands of Low Earth Orbiting (LEO) satellites, space will become even more congested for satellite operations. The enduring effects on the long-term space environment have been i
In the present work,a complete 2D chemical and thermal non-equilibrium numerical model coupled with a relatively simple sheath model is developed for hydrogen arcjet thruster.Conduction heat transfer in the anode wall is also included in the model.The ope
In this article,plasma-assisted NH3 synthesis directly from N2 and H2 over packing materials with different dielectric constants(BaTiO3,TiO2 and SiO2)and thermal conductivities(BeO,AlN and Al2O3)at room temperature and atmospheric pressure is reported.The
Low Earth Orbit (LEO) satellite navigation signal can be used as an opportunity signal in the case of a Global Navigation Satellite System (GNSS) outage, or as an enhancement by means of traditional GNSS positioning algorithms. No matter which service mod
The Local Monte Carlo(LMC)method is used to solve the problems of deep penetration and long time in the neutronics calculation of the radial neutron camera(RNC)diagnostic system on the experimental advanced superconducting tokamak(EAST),and the radiation
Precise control of the discharge in space and time is of great significance for better applications of discharge plasma.Here,we used a femtosecond laser filament to trigger and guide a high-voltage DC pulse discharge to achieve spatiotemporal control of t
脑功能网络的信息流向能反映不同脑区之间的因果关系,通过研究不同情绪状态下脑区间的因果关系,不仅对揭示情绪产生的机理至关重要,而且可以对情绪的产生进行有效的分析、识别和监控.在人工智能领域,有效的情绪识别将直接影响人机交互过程.本研究使用DEAP情绪数据集,基于传递熵的方法构建有向功能网络,探讨了在不同情绪状态下信息流的流向及强弱变化规律,以及不同脑区间存在的信息传递相互影响模式.研究发现,不同的情绪状态下各脑区的信息流量强度不同,唤醒度越高,信息流强度越大.信息流向和脑区各节点局部连接方式也存在显著差异.
本文利用秘鲁和印度地磁台站的观测数据,结合全球电离层-热层模型的模拟结果,研究了地磁场强度的减弱对赤道电激流的地方时和经度分布的影响.这对理解地球空间天气和行星演化具有重要的科学意义.结果 表明,当地磁场强度减弱一半时,东向电激流和风发电机电场的峰值时间均提前1h,而低层大气潮汐使峰值时间延后了1h.其主要原因是,随着地磁场减弱,E层当地激发和来自低层大气迁移潮汐的上传过程均发生了变化.当磁场减弱50%时,电离层Cowling电导率增加为真实地磁场条件下的3倍,而峰值电激流增加为真实地磁场条件下的1.3倍