共查询到19条相似文献，搜索用时 171 毫秒
1.
针对极端学习机(Extreme Learning Machine,ELM)用于日长(Length-Of-Day,LOD)变化预报过程中,样本输入方式对预报结果的影响进行了研究。采用跨度、连续和迭代3种样本输入方式对日长变化进行预报。结果表明,不同的样本输入方式对预报结果有很大影响,样本按跨度输入的预报精度最低;样本采用连续输入方式在短期和中长期预报中预报精度较高,但计算速度较慢,较适合中长期预报;样本按迭代输入方式的短期预报精度稍优于连续输入方式,而中长期预报精度则不如连续输入方式,但具有较高的预报效率。这对于日长变化的实时快速预报有着较高的现实意义。 相似文献
2.
为研究最小二乘(least squares,LS)模型和自回归(autoregression,AR)模型的组合(LS+AR)方法用于地球自转参数(Earth rotation parameters,ERP)的预报时,不同的预报方式对预报结果的影响,我们采用递推、迭代和间隔这3种预报方式对ERP进行预报。结果表明,这3种方式对日长变化(length of day,LOD)所有跨度预报的精度相当,而递推方式在极移所有跨度的预报上表现出精度优势,间隔方式次之,迭代方式最差。在数据利用率和计算速度方面,递推和迭代方式的数据利用率高,但前者的计算量明显小于后者,而间隔方式的数据利用率低,但计算速度最快。 相似文献
3.
针对目前极移最小二乘(Least Square, LS)+自回归(AutoRegressive, AR)预报模型的单一数据选取方案, 提出分别考虑LS模型数据量和AR残差数据量的组合数据模式, 并对极移预报时单一数据和组合数据预报结果精度进行分析, 探讨模型输入数据量对极移预报精度的影响. 结果表明, 模型输入数据量的变化对极移预报结果影响较大. 采用组合数据预报的方式相比较于单一数据量预报方式精度更高, 特别是针对30--360 d跨度内的中长期预报, 组合数据量的极移预报精度可比单一数据量预报精度有较大改善. 结论证明组合数据在极移预报时具有一定的优势, 可为以后极移预报数据量选取提供一定的借鉴参考意义. 相似文献
4.
5.
6.
7.
针对极移复杂的时变特性, 根据混沌相空间坐标延迟重构理论, 提出一种基于Volterra自适应滤波的极移预报方法. 首先, 利用最小二乘拟合算法分离极移序列中的线性趋势项、钱德勒项和周年项, 获得线性极移、钱德勒极移和周年极移的外推值; 其次, 通过C-C关联积分法对最小二乘拟合残差序列进行相空间重构, 并利用小数据量法计算残差序列的最大Lyapunov指数验证其混沌特性, 在此基础上, 构建Volterra自适应滤波器对残差序列进行预测; 最后, 将线性极移、钱德勒极移和周年极移的外推值以及最小二乘拟合残差的预测值相加获得极移最终预报值. 利用国际地球自转服务局(International Earth Rotation and Reference Systems Service, IERS)提供的极移数据进行1--60d跨度预报, 并将预报结果分别与国际地球定向参数预报比较竞赛(Earth Orientation Parameters Prediction Comparison Campaign, EOP PCC)结果和IERS A公报发布的极移预报产品进行对比, 结果表明: 对于1--30d的短期预报, 该方法的预报精度与EOP PCC最优预报方法相当, 当预报跨度超过30d时, 该方法的预报精度低于EOP PCC最优预报方法, 优于参与EOP PCC的其他方法; 与IERS A公报相比, 该方法的短期预报效果较好, 当预报跨度增加时预报精度低于IERS A公报. 预报结果表明该方法更适合于极移短期预报. 相似文献
8.
《天文学报》2014,(4)
在低轨卫星的轨道计算中需要输入太阳辐射指数,它常用来描述太阳活动对高层大气密度的直接影响以及对轨道摄动的间接影响.因此太阳辐射指数的精度将影响轨道预报的精度.以太阳活动27 d短期震荡规律为基础,研究了一种利用135 d的辐射指数历史数据对F_(10.7)进行54 d中期预报的方法,能够预测太阳在未来2个自转周内辐射指数的变化.通过与其他预报方法的比较,表明:(1)该方法显著优于传统的三角函数长期预报法;(2)短期预报7 d时方法略优于美国空间天气预报中心(Space Weather Prediction Center,SWPC)的方法,RMS(Root Mean Square)下降约19%;(3)中期预报27 d时该方法与国内常用的54阶自回归模型精度基本相当,但方法的参数和需要的历史资料都明显减少,在轨道计算中使用更为简便,而且精度稳定,在54 d时预报值和实测值之间的相关系数仍然优于0.92.该方法的特点是只利用辐射指数较少的历史资料,不需要额外的太阳观测资料作支撑,能进行长达54 d的中期预报,为航天任务中的轨道中短期预报提供合理、可靠的辐射指数. 相似文献
9.
《天文学报》2017,(3)
卫星钟差预报精度的不断提升是精密导航的关键问题.为了进一步提高钟差的预报精度和更好地反映钟差的变化特性,提出一种基于Takagi-Sugeno模糊神经网络(Fuzzy Neural Network,FNN)的钟差预报方法.该方法首先根据钟差数据的特点对钟差进行预处理,然后以预处理后的数据建立一种高精度预报钟差的Takagi-Sugeno模糊神经网络算法.采用IGS(International Global Navigation Satellite System Service)不同采样间隔的精密钟差数据进行了短期预报试验,并与ARIMA(Auto-Regressive Integrated Moving Average)模型、GM(1,1)模型及QP(Quadratic Polynomial)模型进行了对比试验,分析结果表明:对不同类型原子钟,该方法用于钟差短期预报是可行的、有效的,其获得的卫星钟差预报结果明显优于常规方法. 相似文献
10.
北斗卫星导航系统(BDS)地面跟踪站都配置有高精度的氢原子钟,并基于精密定轨数据处理与主站的时间基准进行同步.在卫星轨道机动以及机动恢复期间,通常采用几何法定轨以及单星定轨确定卫星的轨道.而在这两种定轨模式中,需要提供精确的测站钟差作为输入.为提高定轨的实时性,需要对测站钟差进行预报处理.分析了2次多项式模型、附加周期项模型、灰色模型3种模型对北斗地面跟踪站钟差短期拟合和预报的性能,并将钟差预报结果应用于单星定轨,同时还分析了不同预报钟差用于定轨的精度.试验发现,以上3种模型对6个测站钟差的平均拟合精度分别为0.14 ns、0.05 ns、0.27 ns,预报1 h的平均精度分别为1.17 ns、0.88 ns、1.28 ns,预报2 h的平均精度分别为2.72 ns、2.09 ns、2.53 ns.采用3种模型对测站钟差进行预报并用于单星定轨,采用附加周期项的钟差预报模型轨道3维误差最小,不同模型轨道径向精度差异在3 cm以内.以上结果表明,附加周期项的站钟拟合及预报模型在北斗系统机动期间的轨道恢复数据处理具有最好的效果. 相似文献
11.
《Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science》1999,24(4):343-347
To test the ability and efficacy of neural networks in short-term prediction of ionospheric parameters, this study used the time series of the ionospheric foF2 data from Slough station during solar cycles 21 and 22. It describes different neural network architectures that led to similar conclusions on one-hour- ahead foF2 prediction. This prediction is compared with observations and results from linear and persistence models considered here as two special cases of the neural networks. 相似文献
12.
Via the three physical quantities (i.e., the maximal horizontal gradient of longitudinal magnetic field |ΔhBz|m, the length of neutral line with a large gradient L, and the number of isolated singular points η), which are used to represent the characteristics of the complexity and non-potentiality of the photospheric magnetic fields in solar active regions, a model of the shortterm forecast of proton events is built. The effectivity of the short-term forecast of proton events by means of the characteristic physical quantities of magnetic fields is verified. In the nowadays commonly used models of short-term forecast of solar proton events, until present the characteristic physical quantituieas of magnetic fields are not formally taken to be the factors of forecast. Because the solar proton events are low probability events, the physical mechanism of their occurrence is still not well understood. In the models of their prediction, the problems of high rates of false alarm or low rates of right alarm often exist. In this paper the traditional factors used in the existing models of forecast of proton events and the characteristic physical quantities of magnetic fields are combined together. By using the method of neural network, a more effective method of the short-term prediction of proton events is established. With the 1871 sample data in 1997-2001, we have set up Model A with the traditional forecast factors as the input layer, and also Model B with the traditional forecast factors plus the characteristic physical quantities of magnetic fields as the input layer. Via the set of 973 sample data of the years 2002 and 2003, we have carried out a simulative forecast, and found that under the condition that these two models possess the same rate of accuracy in the forecast of proton events, the rate of false alarm of Model B becomes evidently lower. This has further verified the effectiveness of the characteristic physical quantities of magnetic fields in shortterm prediction. Furthermore, this may improve the actual ability of forecast of solar proton events. 相似文献
13.
Traditional methods for predicting the change in length of day (LOD change) are mainly based on some linear models, such as the least square model and autoregression model, etc. However, the LOD change comprises complicated non-linear factors and the prediction effect of the linear models is always not so ideal. Thus, a kind of non-linear neural network — general regression neural network (GRNN) model is tried to make the prediction of the LOD change and the result is compared with the predicted results obtained by taking advantage of the BP (back propagation) neural network model and other models. The comparison result shows that the application of the GRNN to the prediction of the LOD change is highly effective and feasible. 相似文献
14.
《天文和天体物理学研究(英文版)》2021,(5)
The continuous observation of the magnetic field by the Solar Dynamics Observatory(SDO)/Helioseismic and Magnetic Imager(HMI) produces numerous image sequences in time and space.These sequences provide data support for predicting the evolution of photospheric magnetic field. Based on the spatiotemporal long short-term memory(LSTM) network, we use the preprocessed data of photospheric magnetic field in active regions to build a prediction model for magnetic field evolution. Because of the elaborate learning and memory mechanism, the trained model can characterize the inherent relationships contained in spatiotemporal features. The testing results of the prediction model indicate that(1) the prediction pattern learned by the model can be applied to predict the evolution of new magnetic field in the next 6 hours that have not been trained, and predicted results are roughly consistent with real observed magnetic field evolution in terms of large-scale structure and movement speed;(2) the performance of the model is related to the prediction time; the shorter the prediction time, the higher the accuracy of the predicted results;(3) the performance of the model is stable not only for active regions in the north and south but also for data in positive and negative regions. Detailed experimental results and discussions on magnetic flux emergence and magnetic neutral lines finally show that the proposed model could effectively predict the large-scale and short-term evolution of the photospheric magnetic field in active regions. Moreover, our study may provide a reference for the spatiotemporal prediction of other solar activities. 相似文献
15.
We investigate two training-set methods: support vector machines (SVMs) and Kernel Regression (KR) for photometric redshift estimation with the data from the databases of Sloan Digital Sky Survey Data Release 5 and Two Micron All Sky Survey. We probe the performances of SVMs and KR for different input patterns. Our experiments show that with more parameters considered, the accuracy does not always increase, and only when appropriate parameters are chosen, the accuracy can improve. For different approaches, the best input pattern is different. With different parameters as input, the optimal bandwidth is dissimilar for KR. The rms errors of photometric redshifts based on SVM and KR methods are less than 0.03 and 0.02, respectively. Strengths and weaknesses of the two approaches are summarized. Compared to other methods of estimating photometric redshifts, they show their superiorities, especially KR, in terms of accuracy. 相似文献
16.
17.
18.
针对BP (Back Propagation)神经网络模型预测卫星钟差中权值和阈值的最优化问题, 提出了基于遗传算法优化的BP神经网络卫星钟差短期预报模型, 给出了遗传算法优化BP神经网络的基本思想、具体方法和实施步骤. 为验证该优化模型的有效性和可行性, 利用北斗卫星导航系统(BeiDou navigation satellite system, BDS)卫星钟差数据进行钟差预报精度分析, 并将其与灰色模型(GM(1,1))和BP神经网络模型预报的结果比较分析. 结果表明: 该模型在短期钟差预报中具有较好的精度, 优于GM(1,1)模型和BP神经网络模型. 相似文献
19.
Short-Term Solar Flare Prediction Using Predictor Teams 总被引：1，自引：0，他引：1
A short-term solar flare prediction model is built using predictor teams rather than an individual set of predictors. The information provided by the set of predictors could be redundant. So it is necessary to generate subsets of predictors which can keep the information constant. These subsets are called predictor teams. In the framework of rough set theory, predictor teams are constructed from sequences of the maximum horizontal gradient, the length of neutral line and the number of singular points extracted from SOHO/MDI longitudinal magnetograms. Because of the instability of the decision tree algorithm, prediction models generated by the C4.5 decision tree for different predictor teams are diverse. The flaring sample, which is incorrectly predicted by one model, can be correctly forecasted by another one. So these base prediction models are used to construct an ensemble prediction model of solar flares by the majority voting rule. The experimental results show that the predictor team can keep the distinguishability of the original set, and the ensemble prediction model can obtain better performance than the model based on the individual set of predictors. 相似文献