大坝沉降监测的时间序列与预报

基于平稳性时间序列分析理论,对大坝沉降监测数据时间序列进行模式识别、参数估计,建立变形监测分析与预报的ARMA模型。结合实例,运用该模型对变形监测数据进行动态分析和预报,将拟合和预报数据同原始数据进行比较分析,结果表明ARMA模型处理动态监测数据是十分可行和有效的,具有重要的应用价值。     

时序递阶组合模型在降水量预测中的应用

应用时间序列分析方法,将年降水量时间序列通过趋势项、周期项和平稳随机项的分析、识别与提取,建立了时序递阶组合模型,并应用该模型对潘家口水库年降水量进行了预测.结果表明,建立的时序递阶组合模型具有较高的精度.     

ARIMA模型在降水量预测中的应用

ARIMA模型是研究时间序列的重要方法,普遍应用于时间序列的分析与预测。利用SPSS软件的时间序列分析预测功能,对营口市降水量数据建立ARIMA模型,并在模型的基础上对营口市降水量趋势进行了分析和预测。     

基于BP神经网络时间序列模型的降水量预测

基于降水过程存在周期性、随机性的特点,应用时间序列典型分解法提取原降水量序列中的趋势成分和周期性成分,对于剩余平稳序列成分,采取BP神经网络模型对其进行模拟;最后建立降水量的BP神经网络时间序列预测模型。以宿迁市近14年的月平均降水资料为实例对该模型进行了具体的应用。结果表明:基于BP神经网络时间序列预测模型可以有效地预测降水量,并和传统的时间序列加法模型进行了比较,结果显示基于BP神经网络的时间序列预测优于传统的时间序列加法模型,模型具有较高的精度和稳定性。     

基于小波分析技术的中长期径流预测模型研究

针对中长期径流预测精度低的问题,提出了基于小波分析技术的时间序列预测模型。利用小波函数db(5)将年径流序列进行尺度为3的分解,得到相应的低频信号和高频信号,然后对各级分解信号利用ARMA(2,1)模型进行预报,最后将各预报结果叠加合成原始径流的预测值,并与ARMA模型直接预测的年径流值比较,通过实例得出前者预测模型要比后者预测的精度更高、稳定性更好,从而验证了该中长期径流预测模型的有效性。     

基于小波分析技术的中长期径流预测模型研究

针对中长期径流预测精度低的问题,提出了基于小波分析技术的时间序列预测模型。利用小波函数db(5)将年径流序列进行尺度为3的分解,得到相应的低频信号和高频信号,然后对各级分解信号利用ARMA(2,1)模型进行预报,最后将各预报结果叠加合成原始径流的预测值,并与ARMA模型直接预测的年径流值比较,通过实例得出前者预测模型要比后者预测的精度更高、稳定性更好,从而验证了该中长期径流预测模型的有效性。     

ARIMA模型在唐山市降水量趋势预测与分析中的应用

利用SPSS软件的时间序列预测功能,对唐山市降水量数据建立ARIMA模型。模型通过了显著性检验,在此基础上对唐山市降水量趋势进行了预测与分析。     

基于ARIMA模型在降水量趋势分析与预测中的应用

利用SPSS软件的时间序列预测功能,对唐山市降水量数据建立ARIMA模型。建立的模型通过了模型的显著性检验,并在此基础上对降水量趋势进行了预测与分析。     

半湿润地区旱涝灾害预测模型研究

简要介绍了对ARMA模型的识别、定阶、参数估计及检验等方法,并将该模型运用到半湿润地区的旱涝灾害预测中,用所建立的ARMA（2,2）模型对降水量进行预测。分析结果表明,预测效果较好,误差均在10%范围内,然后用降水距平百分率法对预测的降水量进行旱涝指标评定,可见,该地区2003~2005年无旱涝灾害发生,与实际情况相符。分析方法可以为半湿润地区旱涝预报和防治提供参考依据,对于其他地区旱涝灾害预测的研究也有一定的借鉴意义。     

基于ARMA模型的短期风功率预测研究

针对风功率预报中出现的资料获取困难、预报精度差等问题,提出采用基于时间序列数据的ARMA模型,并重点对ARMA模型进行识别和参数进行估计。在一定范围内,枚举输入AIC值,并采用大量数据进行模拟,同时采用MAE、NMAE和NRMSE三种指标对模拟结果进行评价,得到了适合于风功率预报的ARMA模型。同时将模型用于预报,发现预报结果精度比较高,表明ARMA模型有较好的实用性。     

The Research of Monthly Discharge Predictor-corrector Model Based on Wavelet Decomposition

Based on wavelet analysis theory, a wavelet predictor-corrector model is developed for the simulation and prediction of monthly discharge time series. In this model, the non-stationary time series of monthly discharge is decomposed into an approximated time series and several stationary detail time series according to the principle of wavelet decomposition. Each one of the decomposed time series is predicted, respectively, through the ARMA model for stationary time series. Then the correction procedure is conducted for the sum of the prediction results. Taking the monthly discharge at Yichang station of Yangtse River as an example, the monthly discharge is simulated by using ARMA model, seasonal ARIMA model, BP artificial neural network model and the wavelet predictor-corrector model proposed in this article, respectively. And the effect of decomposition scale for the wavelet predictor-corrector model is also discussed. It is shown that the wavelet predictor-corrector model has higher prediction accuracy than the some other models and the decomposition scale has no obvious effect on the prediction for monthly discharge time series in the example.     

Exploring the Regional Variance using ARMA-GARCH Models

Recently some generalized autoregressive conditional heteroskedasticity (GARCH) models are proposed and applied to various hydrologic variables to capture and remove the ARCH effect, which has been observed frequently in the residuals from linear autoregressive moving average (ARMA) models fitted to hydrologic time series. As a nonlinear phenomenon of variance behavior, the ARCH effect reveals partially nonstationarity and nonlinearity of hydrological processes. This paper deals with the variation of a river basin using the ARMA-GARCH error model, which combines an ARMA model for modelling the mean behavior and a GARCH model for modelling the variance behavior of the residuals from the ARMA model. Based on the heteroscedasticity of hydrological variable series, the time-varying regional variance is proposed to check the variation of a river basin for the first time. As a study case, the method is applied to four deseasonalized daily discharge series from the middle reach of Yangtze River, China. Through the analyses of the conditional variance in different streamflow series, it is concluded that: (1) The ARCH effect exists in all the studied series which means the stream processes is nonstationary in terms of the variance; (2) The variations of time-varying variances are similar for the series from adjacent hydrological stations, and the similarity degree increases from upstream to downstream; (3) The regional variance is time-varying and can be used for further regional research.     

ARMA模型在实时水文预报中的应用探讨

本文从水文预报的角度分析讨论了ARMA模型的特点,模型识别方法,实时预报中如何利用系列的周期性成份,消除不平稳因素的影响,参数递推估计以及卡尔曼滤波等问题。同时还给出了一个实例。分析和应用结果表明ARMA模型在水文预报中是一类很有潜力的模型,今后实时水文预报研究应重视这类模型,找出其在各种情况下的最佳实时预报途径。     

改进的时间序列模型在非汛期水沙预报中的应用

从ARMA模型出发，对传统的误差实时修正方法进行改进，用服从正态分布的纯随机序列代替，延长了时间序列预测时域．用这两种方法对黄河潼关水文站水沙序列进行了预测，经计算表明，改进的时间序列方法有效地提高了预测精度。     

几种AR和ARMA模型对城市用水量预测的比较

利用时间序列法中的自回归模型（AR）和自回归移动平均模型（ARMA）,对城市某区域的用水量进行预测。模型参数采用最小二乘法进行估计,并将预测值与实测值进行了比较。结果显示,预测值的相对误差均在±10%之内,且仅有个别点的相对误差在±5%之外,预测结果与实测值基本一致。对预测结果的进一步分析表明,高阶AR模型预测结果的均方差（MSE）低于低阶AR模型,而从平均绝对百分比误差（MAPE）来看,ARMA模型的预测结果并不优于AR模型。     

Evidence of Climate Change in the Senegal River Basin

International development policy makers are recognizing climate change and desertification as fundamental obstacles to the social and economic development of the Third World. Sub-Saharan Africa, particularly the Sahel region, has been severely impacted by the compounding effects of drought, deforestation and desertification. The Senegal River Basin in the West Africa is a prime example of a region where development objectives are seriously undermined by the drought-induced desertification process. The basic hydrologic constraint on development is revealed in a time series decompositionof Senegal River annual flow volumes, which strongly suggests that water resources availability has been substantially curtailed since 1960. Two alternative time series mechanisms are hypothesized to account for the decreased flow volumes in recent decades. The first time series model suggests the presence of a long-term periodicity, while the second model hypothesizes an ARMA(1,1,) process. The second hypothesis provides a superior model fit. The stationary ARMA(1,1) model can be fitted successfully, however, only after explicitly removing a non-stationary component by linearly detrending after 1960. The implication of non-stationarity in Senegal River hydrology provides additional analytic evidence that the landscape degradation and desertification processes observed in Sahelian Africa can be in part attributed to climate change effects. Efforts to redress desertification should be at once conscious of complex socioeconomic forces exacerbating the desertification process and fundamental hydrologic constraints to river basin development.     

大坝变形的小波分析与ARMA预测模型

大坝变形观测资料可视为非平稳时间序列,从影响大坝变形规律的因素出发,可将其分解为主值函数项、周期函数项和改进后的平稳时间序列。其中主值函数项采用逐步回归法拟合,针对时效因子采用半经验公式无法准确拟合实际变化情况,采用小波分析法将序列分解为低频和高频两部分信号,其中低频部分代表时效等因素影响的变形趋势;高频部分代表水位、温度等影响的变化规律,应用时间序列原理分别建立变形预测ARMA（p,q）模型,从而在现有水位、温度观测资料下预测坝体未来的变形趋势。实例计算结果表明,结合小波分析的时间序列法建立的预测模型,预测精度高于统计回归分析,预测效果良好,可作为一种有效方法应用于大坝变形预测中。     

黄河干流水库联合调度径流预报模型研究

在简述线性水文系统中总径流线性响应模型ＴＬＲ与线性扰动模型ＬＰＭ以及时间序列的自回归ＡＲ模型、滑动平均ＭＡ模型和自回归滑动平均ＡＲＭＡ模型基础上，结合黄河干流水库联合调度研究阐明了黄河干流径流预报的构想及组合模型、并讨论了径流预报模型实时校正方法，同时分析了各模型的特点及其对水库优化调度的影响，这对黄河干流水库联合调度研究以及水库优化调度在实际中的应用具有重要意义．     

Temporal Variability and Potential Predictability of the Streamflow Regimes in the North‐Eastern Iberian Peninsula

This paper investigates the temporal variability and potential predictability of streamflow regimes in the north‐eastern Spain for the 1970–2010 period. Two different regimes are found, those characterized for having peak flows in the winter and those where this maximum appears in the spring. The main characteristic time scales of streamflows in each area are studied by singular spectral analysis (SSA). While winter streamflow regime only shows interannual variability (quasi‐oscillatory modes around 5.5 and 2.3 years), spring streamflow (2.6 and 6.6 years) also presents a decadal variability component. Based on this result, a modelling process is conducted using autoregressive moving average (ARMA) models, for interannual variability modelling, and stable teleconnections between global oceanic sea surface temperature (SST) anomalies and river flow, for decadal variability modelling. Finally, a one‐step‐ahead prediction experiment is computed to obtain forecasted streamflows. The results for winter streamflow regime modelling show a phase concordance between the raw and the forecasted streamflow time series of around 70% and a correlation around 0.7, for the validation period (2001–2010). For spring streamflow, additionally to the ARMA modelling for the interannual component, a model based on the SST has been established that involves some oceanic regions from previous seasons located, fundamentally, not only in the North Atlantic but also in the Indian Ocean. The combined model (SST + ARMA) significantly improves the prediction based on the ARMA model alone, showing a phase concordance and a correlation around 90% and 0.7 respectively. This modelling scheme provides predictability skills of the rivers from the Inland Catalan Basins at different time scales, representing an added value for water planning. Copyright © 2014 John Wiley & Sons, Ltd.     

基于ARMA模型的水文序列相依变异分级方法及验证

受自然和人为等因素的影响,水文情势和地理环境不断发生显著变化,不同水文要素形成的水文时间序列常呈现出一定的相依性。为定量研究水文序列中的这种相依现象,本文以自回归滑动平均模型ARMA为例,选取原始水文序列与其相依成分间的相关系数为衡量标准,提出对相依变异强弱程度分级的一种方法。先用公式推导的方式从原理上阐明相关系数与序列的自回归系数和滑动平均系数存在的关系,从而建立相关系数与序列自相关系数的联系,再选择合理阈值作为分级界限,把相关系数划分为5段区间,对应描述5种不同强弱的相依变异程度。分别以较低阶数的ARMA模型为例,通过统计试验验证了以相关系数作为分级指标的合理性。将所提方法分别应用于模拟时间序列和实测水文序列,并结合物理成因从气候变化和人类活动两个方面对实测径流序列的相依变异分级结果进行了分析与验证,结果表明该方法合理可靠。