ARMA模型在兰州5～9月降水预报中的初步应用

本文试用动态数据处理中时间序列ＡＲＭＡ过程的概念来作长期降水预报,经过对降水历史资料平稳化处理后,对其建立ＡＲＭＡ模型,从预报趋势上看,此方法是有一定价值的。     

Functional series TARMA modelling and simulation of earthquake ground motion

The non‐stationary Functional Series time‐dependent autoregressive moving average (TARMA) modelling and simulation of earthquake ground motion is considered. Full Functional Series TARMA models, capable of modelling both resonances and antiresonances, are examined for the first time via a novel mixed parametric/non‐parametric estimation scheme, and critical comparisons with pure TAR and recursive ARMA (RARMA)‐recursive maximum likelihood (RML) adaptive filtering type modelling are made. The study is based upon two California ground motion signals: a 1979 El Centro accelerogram and a 1994 Pacoima Dam accelerogram. A systematic analysis, employing various functional subspaces and model orders, leads to two Haar function based models: a TARMA(2,4)₈ model for the El Centro case and a TARMA(6,2)₁₀ model for the Pacoima Dam case. Both models are formally validated and their simulation (synthesis) capabilities are demonstrated via Monte Carlo experiments focusing on important time domain signal characteristics. The Functional Series TAR/TARMA models are shown to achieve parsimony, as well as superior accuracy and simulation capabilities, over their RARMA counterparts. Copyright © 2001 John Wiley & Sons Ltd.     

基于CMONOC GPS数据的SSA电离层预测模型研究

利用基于CMONOC的GPS观测数据反演中国大陆区域高精度的RIM,并将奇异谱分析(SSA)方法应用于TEC预报,判断不同序列长度对预测结果的影响,并根据w-correlation选取合适的RC迭代阶数和窗口长度。结果发现,当TEC时间序列长度为27 d,窗口长度为序列长度的1/3、迭代SSA分解的前5项时,预测效果最好。提取RIM中心网格点的TEC数据,分别以年积日1~27、101~127、201~227、301~327等4个时段的TEC序列为原始数据,基于SSA进行7 d的预测,同时建立ARMA预测模型。结果显示,相较于ARMA预测,SSA方法总体预测精度提高约10%,预测时段更长。进一步对4个时段RIM中2 911个网格点处的TEC进行预测,发现RMSE随着纬度减小而增大,预测相对精度呈现中纬度比高、低纬度略高的特点,但无论哪种精度指标,SSA预测模型均优于ARMA预测模型。     

MEEMD-ARMA残差修正电离层TEC预测模型

提出一种改进的集总平均经验模态分解与自回归移动平均模型组合的残差修正模型,并利用2015年不同经纬度同一时段以及相同经纬度不同时段IGS提供的电离层电子总量数据,用3种模型对5 d内的数据进行预测。结果表明,改进模型5 d 内的平均相对精度为96%,而EMD-ARMA模型及ARMA模型分别为94.5%、93%。     

Stream nitrate levels in a small catchment in south west England over a period of 35 years (1970–2005)

This study considers a 35‐year record of streamwater nitrate concentration in a small agricultural catchment in south west England (Slapton Wood). The study revisits earlier work to assess whether upward trends have been maintained and how the controls upon streamwater concentration have been altered. The study has shown that (1) the catchment has reached a new position of equilibrium and increases in nitrate concentration have lessened; (2) the occurrence of severe drought in the record means that records of less than a decade are misleading and only long‐term records can illustrate changes of state; (3) the change of state observed in the catchment is illustrated in the switching of long‐term memory effects from a negative to a positive annual memory and (4) several significant long‐term impulsivity relationships with rainfall that become insignificant over the course of the study period. The study shows the importance of long‐term records in understanding changes in state in catchments and understanding the time constants of a range of driving processes. Copyright © 2009 John Wiley & Sons, Ltd.     

���SSA��ARMAģ��Ԥ�������TEC

???????????TEC????????????????????SSA????????TEC????У???SSA??????????????????ARMA???????????????????????????????IGS????2010??????TEC?????????飬???????????????????????5 d??TEC????????????92%???????ARMA??????4%??     

GPS测站坐标非线性变化研究方法的比较与分析

以GPS测站残差时间序列为研究对象,采用自回归滑动平均模型（ARMA）的两种建模方法（Box-Jenkins方法和Pandit-Wu方法）和三角函数法对其进行建模拟合与分析比较。通过实验发现Pandit-Wu方法拟合效果最好,Box-Jenkins方法次之,三角函数法最差,但是通过不同的测站残差数据实验比较也发现三角函数法能更加直观地体现出非线性变化的规律,有利于进一步分析非线性变化规律的性质与机制,因此,同样具有深入研究的价值。     

一种基于抗差自校正Kalman滤波的GPS导航算法

为减弱异常观测值对自校正Kalman滤波精度的影响,引入抗差M估计的等价权函数,建立了抗差自校正Kalman滤波算法,并用实例进行了验证。计算表明,该自适应滤波算法在完全未知噪声统计的情况下,不仅能够自适应地求解状态参数,而且还能在一定程度上有效地抵制观测异常对导航解的影响。     

顾及一次差分数据结构特征的钟差预报模型

星载原子钟在运行过程中会受到恶劣空间环境与设备老化等因素的影响, 使得卫星钟差数据中经常存在异常值, 其中AO(additive outlier)类异常值是钟差序列中常见的一类异常值。结合最大期望算法与自回归滑动平均(autoregressive moving average, ARMA)模型, 提出一种AO类异常值探测算法。该算法可以准确探测孤立AO类异常值与成片AO类异常值, 有效克服了其他算法经常出现的淹没与掩盖现象。在成功探测钟差序列AO类异常值的同时, 该算法可以估计得到精确的ARMA模型, 进而能准确地进行卫星钟差预报。利用仿真数据与北斗卫星钟差实测数据进行计算分析, 结果表明, 所提算法可以精确探测出钟差序列AO类异常值, 并且具有很好的卫星钟差预报效果。     

英镑兑美元汇率分析及预测

根据外汇汇率数据的特点，尤其是数据之间的依赖关系这一重要特性，并结合汇率预测要求快且准的原则，以数理统计学为基础，采用时间序列分析中的ARMA方法。通过数据的平稳性分析、模型的识别、参数估计、模型诊断以及最后预测精度的分析，建立了英镑兑美元汇率的ARMA预测模型并验证了其有效性。