基于长短期记忆神经网络的太阳耀斑短期预报

提出了一个基于长短期记忆神经网络的耀斑预报模型,利用过去24 h太阳活动区的磁场变化时序构建样本,通过长短期记忆神经网络对磁场特征时序演化进行分析,预报未来48 h内是否发生≥M级别耀斑事件。使用的数据集为2010年5月到2017年5月所有活动区样本,选取了SDO/HMI SHARP的10个磁场特征参量。在建模过程中通过XGBoost方法选取权重、增益率和覆盖率均较高的6个特征参量作为输入参数。通过测试对比,模型的虚报率和准确率与传统机器学习模型相近,报准率和临界成功指数分别为0.7483和0.7402,优于传统机器学习模型。模型总体效果优于传统机器学习模型。      

基于集成学习的太阳质子事件短期预报方法

太阳质子事件是一种由太阳活动爆发时喷射并传播到近地空间的高能粒子引起的空间天气现象。这些高能粒子会对航天器和宇航员产生严重危害,对太阳质子事件进行准确的短期预报是航天活动灾害预防的重要内容。针对当前主要预报模型中普遍存在的高虚报率问题,提出了一种基于集成学习的太阳质子事件短期预报方法,利用第23个太阳活动周数据,建立了一种集成8种机器学习模型的太阳质子事件短期预报系统。实验结果表明,本文方法在取得了80.95%的报准率的同时,将虚报率降低至19.05%,相比现有的预报系统具有较为明显的优势。      

Using Back Propagation Neural Network Method to Forecast Daily Indices of Solar Activity F10.7

The solar 10.7 cm radio flux，F_10.7，a measure of the solar radio flux per unit frequency at a wavelength of 10.7 cm，is a key and serviceable index for monitoring solar activities.The accurate prediction of F_10.7 is of significant importance for short-term or long-term space weather forecasting. In this study，we apply Back Propagation （BP） neural network technique to forecast the daily F_10.7 based on the trial data set of F_10.7 from 1980 to 2001.Results show that this technique is better than the other prediction techniques for short-term forecasting，such as Support Vector Regression method.      

Research Progress of Interplanetary Physics in Mainland China

Significant progress has been made by Chinese scientists in research of interplanetary physics during the recent two years (2018-2020). These achievements are reflected at least in the following aspects:Activities in solar corona and lower solar atmosphere; solar wind and turbulence; filament/prominence, jets, flares, and radio bursts; active regions and solar eruptions; coronal mass ejections and their interplanetary counterparts; other interplanetary structures; space weather prediction methods; magnetic reconnection; Magnetohydrodynamic (MHD) numerical modeling; solar energetic particles, cosmic rays, and Forbush decreases; machine learning methods in space weather and other aspects. More than one hundred and forty papers in the academic journals have been published in these research directions. These fruitful achievements are obtained by Chinese scholars in solar physics and space physics either independently or through international collaborations. They greatly improve people's understanding of solar activities, solar eruptions, the corresponding space weather effects, and the Sun-Earth relations. Here we will give a very brief review on the research progress. However, it must be pointed out that this paper may not completely cover all achievements in this field due to our limited knowledge.      

太阳活动区EUV图像的生成式模型耀斑分级与预报

近年来,不断发射的空基观测台持续传送回海量日面图像及日地间气象数据,为采用人工智能技术对太阳活动进行预报预警提供了数据基础。但是,极端天气爆发少,样本量较少;中等程度爆发稍多,样本量较多;常规无爆发天气常见,样本较为集中,样本不均衡状况严重影响机器学习方法在空间天气领域的广泛应用。本文面向多源多通道多尺度日面图像信息,构建了来自SOHO和SDO的1996-2015年日面活动区图像数据集;针对数据分布的不平衡,对太阳活动区图像作耀斑分级与预报。在对比分析元学习算法的基础上,设计了结合分类头设计和卷积核初始化的生成式模型;在使网络轻量化的基础上,能够将M和X级耀斑预报的检测率指标相较于普通的深度学习模型和无监督度量式模型分别提升10%和7%。     

Development of Operational Space Weather Prediction Models

In this report, we summarize the needs of space weather models, and recommend that developing operational prediction models, rather than transitioning from research to operation, is a more feasible and critical way for space weather services in the near future. Operational models for solar wind speed, geomagnetic indices, magnetopause, plasma sheet energetic electrons, inner boundary of ion plasma sheet, energetic electrons in outer radiation belt, and thermospheric density at low Earth orbit, have been developed and will be introduced briefly here. Their applications made a big progress in space weather services during the past two years in China.      

Sunspot cycle prediction using Warped Gaussian process regression

Solar cycle prediction is a key activity in space weather research. Several techniques have been employed in recent decades in order to try to forecast the next sunspot-cycle maxima and time. In this work, the Gaussian process, a machine-learning technique, is used to make a prediction for the solar cycle 25 based on the annual sunspot number 2.0 data from 1700 to 2018. A variation known as Warped Gaussian process is employed in order to deal with the non-negativity constraint and asymmetrical data distribution. Tests using holdout data yielded a root mean square error of 10.0 within 5 years and 25.0–35.0 within 10 years. Simulations using the predictive distribution were performed to account for the uncertainty in the prediction. Cycle 25 is expected to last from 2019 to 2029, with a peak sunspot number about 117 (110 by the median) occurring most likely in 2024. Thus our method predicts that solar Cycle 25 will be weaker than previous ones, implying a continuing trend of declining solar activity as observed in the past two cycles.     

天基X射线掠入射式成像望远镜发展现状

阐述了太阳X射线成像观测在空间天气预报中的地位和作用，叙述了掠入射式X射线聚焦成像的基本原理，简要介绍了在轨成功运行的天体X射线成像望远镜和太阳X射线成像望远镜的基本设计和技术指标，并介绍了国内正开发研制的专门服务于空间天气预报的太阳X射线成像望远镜基本设计和主要特点．     

太阳质子事件预报和射电Ⅰ型噪暴

太阳是一个异常活跃的天体,其爆发过程会对地球周围空间环境产生重要影响. 通常,单个高能质子即足以引起飞行器中微电子器件出现异常,因此太阳质子事件预报是空间天气预报的重要内容. 关于预报模型的参数选择尚有值得改进之处. 研究认为,Ⅰ型噪暴与日冕加热磁重联具有密切关系,可以作为预报参数. 通过两个典型太阳爆发事件的详细资料分析,说明了Ⅰ型噪暴与质子事件及CME的相关性.      

Research Progress of Solar Corona and Interplanetary Physics in China: 2010-2012

The scientific objective of solar corona and interplanetary research is the understanding of the various phenomena related to solar activities and their effects on the space environments of the Earth. Great progress has been made in the study of solar corona and interplanetary physics by the Chinese space physics community during the past years. This paper will give a brief report about the latest progress of the corona and interplanetary research in China during the years of 2010?2012. The paper can be divided into the following parts: solar corona and solar wind, CMEICME, magnetic reconnection, energetic particles, space plasma, space weather numerical modeling by 3D SIP-CESE MHD model, space weather prediction methods, and proposed missions. They constitute the abundant content of study for the complicated phenomena that originate from the solar corona, propagate in interplanetary space, and produce geomagnetic disturbances. All these progresses are acquired by the Chinese space physicists, either independently or through international collaborations.      

A Review of the Ionospheric Investigations in China: Progress During 2008—2010

In the ionospheric research, various progresses have been made during the last two years. This paper reviews the recent works of Chinese scientists. For convenience, the contents include: ionospheric storms and space weather; ionospheric irregularities and scintillation; ionospheric variability; ionospheric disturbances; ionospheric response to solar eclipses; ionospheric coupling with atmosphere and lithosphere; ionospheric climatology; ionospheric modeling; and ionospheric prediction and application.      

冕洞特征参数与地磁暴强度及发生时间统计

地磁暴是空间天气预报的重要对象.在太阳活动周下降年和低年,冕洞发出的高速流经过三天左右行星际传输到达地球并引发的地磁暴占主导地位.目前地磁暴的预报通常依赖于1AU处卫星就位监测的太阳风参数,预报提前量只有1h左右.为了增加地磁暴预报提前量,需要从高速流和地磁暴的源头即太阳出发,建立冕洞特征参数与地磁暴的定量关系.分析了2010年5月到2016年12月的152个冕洞-地磁暴事件,利用SDO/AIA太阳极紫外图像提取了两类冕洞特征参数,分析了其与地磁暴期间ap,Dst和AE三种地磁指数的统计关系,给出冕洞特征参数与地磁暴强度以及发生时间的统计特征,为基于冕洞成像观测提前1～3天预报地磁暴提供了依据.      

Data storage and real time observations at the Mexican Array Radio Telescope

The tracking of large-scale interplanetary (IP) disturbances traveling from the Sun to the Earth is a key issue in space weather studies. The Mexican Array Radio Telescope (MEXART) applies the Interplanetary Scintillation (IPS) technique to detect these solar wind disturbances and it will participate in a global warning network of space weather forecasting. We describe the data storage and computational processes carried out to manage the instrument’s real time data. These procedures are important for the MEXART calibration, operation and the scientific data reduction.     

Advance of interplanetary physics study in China: 2008—2010

Interplanetary physics study is an important ingredient in space weather research. Considerable progress this aspect has been achieved by the space physics community of China in recent years. This brief report summarizes the latest advances of the interplanetary physics research in China during the period of 2008--2010. This report includes solar corona and solar wind, interplanetary transients, energetic particles, MHD simulation, space plasma, and prediction methods for physical phenomena originating from both solar corona and interplanetary space.      

基于MapReduce的CME参数识别模型并行计算技术

日冕物质抛射（Coronal Mass Ejection,CME）参数识别模型是太阳风预报过程的重要组成部分.在空间环境预报业务中,为提高太阳风预报的准确率,需要提高CME参数识别的精度.模型以计算任务串行的方式运行,运算效率低导致模型运算时间长,不能满足这种需求.CME参数识别模型的物理运算过程相互不独立,其在单节点上的运行方式不能满足并行化要求.基于MapReduce的并行计算框架,改进了CME参数识别模型的计算流程,提出CDMR（CME detection under MapReduce）方法,实现了CME参数识别模型的并行计算,并对比分析CME参数识别模型在串行计算和MapReduce并行计算下的运行时间,提高了模型的识别精度和计算效率.      

Predicting indices of the ionosphere response to solar activity for the ascending phase of the 25th solar cycle

The international reference ionosphere, IRI, and its extension to plasmasphere, IRI-Plas, models require reliable prediction of solar and ionospheric proxy indices of solar activity for nowcasting and forecasting of the ionosphere parameters. It is shown that IRI prediction errors could increase for the F2 layer critical frequency foF2 and the peak height hmF2 due to erroneous predictions of the ionospheric global IG index and the international sunspot number SSN1 index on which IRI and IRI-Plas models are built. Regression relation is introduced to produce daily SSN1 proxy index from new time series SSN2 index provided from June 2015, after recalibration of sunspots data. To avoid extra errors of the ionosphere model a new solar activity prediction (SAP) model for the ascending part of the solar cycle SC25 is proposed which expresses analytically the SSN1 proxy index and the 10.7-cm radio flux F10.7 index in terms of the phase of the solar cycle, Φ. SAP model is based on monthly indices observed during the descending part of SC24 complemented with forecast of time and amplitude for SC25 peak. The strength of SC25 is predicted to be less than that of SC24 as shown with their amplitudes for eight types of indices driving IRI-Plas model.     

冕洞相关地磁Ap指数中短期预报方法研究

地磁Ap指数是描述全球地磁活动水平的重要指数, 过去许多参考大气模式中都用Ap指数来表述地磁活动状态, 大气模式的运行需要输入地磁Ap指数, 因此, 地磁Ap指数的预报一直是空间环境预报中一个非常重要的内容. 针对太阳活动低年冕洞引起的地磁扰动具有明显27天重现的特性, 利用修正的自回归方法, 对地磁Ap指数进行了提前27天的预报; 采用从SOHO/EIT观测资料发展出来的描述冕洞特性的Pch因子, 进行了提前三天的地磁Ap指数预报. 结果显示, 将统计方法与物理分析相结合, 进行地磁Ap指数的中短期数值预报, 可以得到较好的预报效果.      

利用BP神经网络预测AE指数

采用的预报模式是一种全连接的BP网络模型,利用太阳风及行星际磁场的观测数据预报AE指数.神经网络输入选用ACE卫星数据,取5 min平均值,通过比较,选用4个预报参量.构造了预报参量时续为20 min,40 min和60 min依次递增的三个网络,分别进行训练和预测,并对行星际参量对AE指数影响的时续性进行了探讨.预报结果表明,全连接BP神经网络在AE指数的短期预报中是比较有效的,同时还提出了需要进一步改进的环节.      

利用人工神经网络预报大磁暴

本文采用阈值预报的策略和人工神经网络BP模型,以13个太阳风参量和地磁AE,Dst指数作为输入,以0或1作为输出,提前4h预报大磁暴主相发生的时刻．结果表明,采用神经网络方法的阈值预报可以对灾害性磁暴的发生提前数小时做出比较准确的预报．     

Prediction of expected global climate change by forecasting of galactic cosmic ray intensity time variation in near future based on solar magnetic field data

A method of prediction of expected part of global climate change caused by cosmic ray (CR) by forecasting of galactic cosmic ray intensity time variation in near future based on solar activity data prediction and determined parameters of convection-diffusion and drift mechanisms is presented. This gave possibility to make prediction of expected part of global climate change, caused by long-term cosmic ray intensity variation. In this paper, we use the model of cosmic ray modulation in the Heliosphere, which considers a relation between long-term cosmic ray variations with parameters of the solar magnetic field. The later now can be predicted with good accuracy. By using this prediction, the expected cosmic ray variations in the near Earth space also can be estimated with a good accuracy. It is shown that there are two possibilities: (1) to predict cosmic ray intensity for 1–6 months by using a delay of long-term cosmic ray variations relatively to effects of the solar activity and (2) to predict cosmic ray intensity for the next solar cycle. For the second case, the prediction of the global solar magnetic field characteristics is crucial. For both cases, reliable long-term cosmic ray and solar activity data as well as solar magnetic field are necessary. For solar magnetic field, we used results of two magnetographs (from Stanford and Kitt Peak Observatories). The obtained forecasting of long-term cosmic ray intensity variation we use for estimation of the part of global climate change caused by cosmic ray intensity changing (influenced on global cloudiness covering).