A new decomposition model of sea level variability for the sea level anomaly time series prediction

Rising sea level is of great significance to coastal societies;predicting sea level extent in coastal regions is critical.When carrying out predictions,the subsequences obtained using decomposition methods may exhibit a certain regularity and therefore can provide multidimensional information that can be used to improve prediction models.Traditional decomposition methods such as seasonal and trend decomposition using Loess(STL)focus mostly on the fluctuating trend of time series and ignore its impact on prediction.Methods in the signal decomposition domain,such as variational mode decomposition(VMD),have no physical significance.In response to the above problems,a new decomposition method for sea level anomaly time series prediction(DMSLAP)is proposed.With this method,the trend term in a time series can be isolated and the effects of abnormal sea level change behaviors can be attenuated.We decompose multiperiod characteristics using this method while maintaining the smoothness of the analyzed series.Satellite altimetry data from 1993 to 2020 are used in experiments conducted in the study area.The results are then compared with predictions obtained using existing decomposition methods such as the STL and VMD methods and time varying filtering based on empirical mode decomposition(TVF-EMD).The performance of DMSLAP combined with a prediction method resulted in optimal sea level anomaly(SLA)predictions,with a minimum root mean square error(RMSE)of 1.40 cm and a maximum determination coefficient(R^(2))of 0.93 during 2020.The DMSLAP method was more accurate when predicting 1-year data and 3-year data.The TVF-EMD and DMSLAP methods had comparable accuracies,and the periodic term decomposed by the DMSLAP method was more in line with the actual law than that derived using the TVF-EMD method.Thus,DMSLAP can decompose SLA time series better than existing methods and is an effective tool for obtaining short-term SLA prediction.

STDNet: A Spatio-Temporal Decomposition Neural Network for Multivariate Time Series Forecasting

Long-term multivariate time series forecasting is an important task in engineering applications. It helps grasp the future development trend of data in real-time, which is of great significance for a wide variety of fields. Due to the non-linear and unstable characteristics of multivariate time series, the existing methods encounter difficulties in analyzing complex high-dimensional data and capturing latent relationships between multivariates in time series, thus affecting the performance of long-term prediction. In this paper, we propose a novel time series forecasting model based on multilayer perceptron that combines spatio-temporal decomposition and doubly residual stacking, namely Spatio-Temporal Decomposition Neural Network (STDNet). We decompose the originally complex and unstable time series into two parts, temporal term and spatial term. We design temporal module based on auto-correlation mechanism to discover temporal dependencies at the sub-series level, and spatial module based on convolutional neural network and self-attention mechanism to integrate multivariate information from two dimensions, global and local, respectively. Then we integrate the results obtained from the different modules to get the final forecast. Extensive experiments on four real-world datasets show that STDNet significantly outperforms other state-of-the-art methods, which provides an effective solution for long-term time series forecasting.

Analysis of temperature time series based on Hilbert-Huang Transform

In this paper, with consideration of the nonlinear and non-stationary properties of the temperature time series, we employ the Hilbert-Huang Transform, based on the empirical mode decomposition（EMD）, to analyze the temperature time series from 1959 to 2012 in the Fengxian district of Shanghai, obtained from a certain monitoring station. The oscillating mode is drawn from the data, and its characteristics of the time series are investigated. The results show that the intrinsic modes of 1, 2 and 6 represent the periodic properties of 1 year, 2.5 years, and 27 years. The mean temperature shows periodic variations, but the main trend of this fluctuation is the rising of the temperature in the recent 50 years. The analysis of the reconstructed modes with the wave pattern shows that the variations are quite large from 1963 to 1964, from 1977 to 1982 and from 2003 to 2006, which indicates that the temperature rises and falls dramatically in these periods. The volatility from 1993 to 1994 is far more dramatic than in other periods. And the volatility is the most remarkable in recent 50 years. The log-linear plots of the mean time scales T and M show that each mode associated with a time scale almost twice as large as the time scale of the preceding mode. The Hilbert spectrum shows that the energy is concentrated in the range of low frequency from 0.05 to 0.1 Hz, and a very small amount of energy is distributed in the range of higher frequency over 0.1 Hz. In conclusion, the HHT is better than other traditional signal analysis methods in processing the nonlinear signals to obtain the periodic variation and volatility＇s properties of different time scales.

Computational Intelligence Prediction Model Integrating Empirical Mode Decomposition,Principal Component Analysis,and Weighted k-Nearest Neighbor

On the basis of machine leaning,suitable algorithms can make advanced time series analysis.This paper proposes a complex k-nearest neighbor(KNN)model for predicting financial time series.This model uses a complex feature extraction process integrating a forward rolling empirical mode decomposition(EMD)for financial time series signal analysis and principal component analysis(PCA)for the dimension reduction.The information-rich features are extracted then input to a weighted KNN classifier where the features are weighted with PCA loading.Finally,prediction is generated via regression on the selected nearest neighbors.The structure of the model as a whole is original.The test results on real historical data sets confirm the effectiveness of the models for predicting the Chinese stock index,an individual stock,and the EUR/USD exchange rate.

Hybrid Model Based on Wavelet Decomposition for Electricity Consumption Prediction

The effective supply of electricity is the basis of ensuring economic development and people's normal life. It is difficult to store electricity, as leading to the production and consumption must be completed simultaneously. Therefore, it is of great significance to accurately predict the demand for electricity consumption for the production planning of electricity and the normal operation of the society. In this paper, a hybrid model is constructed to predict the electricity consumption in China. The structural breaks test of monthly electricity consumption in China from January 2010 to December 2016 is carried out by using the structural breaks unit root test. Based on the existence of structura breaks, the electricity consumption data are decomposed into low-frequency and high-frequency components by wavelet model, and the separated low frequency signal and high frequency signal are predicted by autoregressive integrated moving average(ARIMA) and nonlinear autoregressive neural network(NAR), respectively. Therefore the wavelet-ARIMA-NAR hybrid model is constructed. In order to compare the effect of the hybrid model, the structural time series(STS) model is applied to predicting the electricity consumption. The results of prediction error test show that the hybrid model is more accurate for electricity consumption prediction.

基于改进EMD和ARMA的MEMS陀螺仪随机误差补偿方法

微机电系统(Micro-Electro-Mechanical System,MEMS)陀螺仪的随机误差限制了其测量精度。为了降低MEMS陀螺仪的随机误差,提出一种基于改进的经验模态分解(Empirical Mode Decomposition,EMD)和优化的自回归滑动平均(Autoregressive Moving Average,ARMA)模型的方法。该方法在传统EMD的基础上,结合Hausdorff距离和累积标准化模态均值以提取信号中的噪声和趋势项,对剩余信号进行ARMA建模和滤波。采用沙猫群优化算法优化建模的定阶过程,采用改进的自适应滤波补偿随机误差。试验结果表明:相较于传统EMD和传统ARMA方法,新方法在静态试验中得到的均方根误差分别降低52.5%和34.4%,在动态试验中得到的均方根误差分别降低50%和32.35%;新方法有效抑制了随机误差,提升了MEMS陀螺仪的使用精度。

基于VMD-TCN-GRU模型的水质预测研究

为充分挖掘水质数据在短时震荡中的变化特征,提升预测模型的精度,提出一种基于VMD(变分模态分解)、TCN(卷积时间神经网络)及GRU(门控循环单元)组成的混合水质预测模型,采用VMD-TCN-GRU模型对汾河水库出水口高锰酸盐指数进行预测,并与此类研究中常见的SVR(支持向量回归)、LSTM(长短期记忆神经网络)、TCN和CNN-LSTM(卷积神经网络-长短期记忆神经网络)这4种模型预测结果对比表明:VMD-TCN-GRU模型能更好挖掘水质数据在短时震荡过程中的特征信息,提升水质预测精度;VMD-TCN-GRU模型的MAE(平均绝对误差)、RMSE(均方根误差)下降,R^(2)(确定系数)提高,其MAE、RMSE、R^(2)分别为0.0553、0.0717、0.9351;其预测性能优越,预测精度更高且拥有更强的泛化能力,可以应用于汾河水质预测。

大坝渗压混合预测的STL分解-集成学习模型

针对目前大坝渗压预测研究大多未区分影响因素对渗压不同特征成分贡献的差异,降低了模型的可解释性,且现有的预测模型大多采用单一算法,存在难以区分具有高度非线性和非稳态混合特征的渗流压力序列模式等问题,本文提出一种基于STL分解和集成学习策略的渗压可解释混合预测模型。该模型首先通过时间序列分解(STL)将原始渗压时间序列分解为季节项、趋势项和余项,以避免现有模型在渗流压力预测中模式混淆的不足;然后,不同成分的变化特征可采用多策略改进麻雀搜索算法(MSISSA)优化的核极限学习机(KELM)和卷积神经网络组合门控递归单元(CNN-GRU)组成的集成学习模型来识别;此外,还采用单次单因子法(OFAT)分析影响因素对渗流压力不同特征成分的贡献,从而改变输入因素的权重,以提高模型的可解释性。案例分析结果表明,在确保模型可解释性的同时,所提出的混合模型与基于单一算法的模型相比,预测精度平均提高了48.44%;与其他集成预测模型相比,预测精度平均提高了11.42%,验证了所提模型的有效性,为大坝渗流安全监控提供了新的建模方法。

Phenology of different types of vegetation and their response to climate change in the Qilian Mountains,China

The Qilian Mountains(QM)possess a delicate vegetation ecosystem,amplifying the evident response of vegetation phenology to climate change.The relationship between changes in vegetation growth and climate remains complex.To this end,we used MODIS NDVI data to extract the phenological parameters of the vegetation including meadow(MDW),grassland(GSD),and alpine vegetation(ALV))in the QM from 2002 to 2021.Then,we employed path analysis to reveal the direct and indirect impacts of seasonal climate change on vegetation phenology.Additionally,we decomposed the vegetation phenology in a time series using the trigonometric seasonality,Box-Cox transformation,ARMA errors,and Trend Seasonal components model(TBATS).The findings showed a distinct pattern in the vegetation phenology of the QM,characterized by a progressive shift towards an earlier start of the growing season(SOS),a delayed end of the growing season(EOS),and an extended length of the growing season(LOS).The growth cycle of MDW,GSD,and ALV in the QM species is clearly defined.The SOS for MDW and GSD occurred earlier,mainly between late April and August,while the SOS for ALVs occurred between mid-May and mid-August,a one-month delay compared to the other vegetation.The EOS in MDW and GSD were concentrated between late August and April and early September and early January,respectively.Vegetation phenology exhibits distinct responses to seasonal temperature and precipitation patterns.The advancement and delay of SOS were mainly influenced by the direct effect of spring temperatures and precipitation,which affected 19.59%and 22.17%of the study area,respectively.The advancement and delay of EOS were mainly influenced by the direct effect of fall temperatures and precipitation,which affected 30.18%and 21.17%of the area,respectively.On the contrary,the direct effects of temperature and precipitation in summer and winter on vegetation phenology seem less noticeable and were mainly influenced by indirect effects.The indirect effect of winter precipitation is the main factor affecting the advance or delay of SOS,and the area proportions were 16.29%and 23.42%,respectively.The indirect effects of fall temperatures and precipitation were the main factors affecting the delay and advancement of EOS,respectively,with an area share of 15.80%and 21.60%.This study provides valuable insight into the relationship between vegetation phenology and climate change,which can be of great practical value for the ecological protection of the Qinghai-Tibetan Plateau as well as for the development of GSD ecological animal husbandry in the QM alpine pastoral area.

一种基于时间序列分解和时空信息提取的云服务器异常检测模型

异常检测是维护云数据中心性能的一项重要任务。云数据中心中运行着大量的云服务器以实现各种云计算功能。由于云数据中心的性能取决于云服务的正常运行,因此检测和分析云服务器中的异常至关重要。为此,该文提出一种基于时间序列分解和时空信息提取的云服务器异常检测模型。首先,提出带时空信息提取模块的双向Wasserstein生成对抗网络算法(BiWGAN-GTN),该算法在具有梯度惩罚的双向Wasserstein生成对抗网络(BiWGAN-GP)算法的基础上,将生成器与编码器替换为由图卷积网络(GCN)与时间卷积网络(TCN)组成的时空信息提取模块(GTN),实现对数据空时信息的提取;其次,提出半监督BiWGAN-GTN算法来识别多维时间序列中的异常,以在训练过程中避免异常数据侵入的风险并增强模型鲁棒性。最后设计多通道BiWGAN-GTN算法-MCBiWGAN-GTN以实现降低数据复杂度并提升模型学习效率的目标。利用带有自适应噪声完全集合经验模态分解(CEEMDAN)算法将时序数据分解,然后将不同的分量送入对应通道下的BiWGAN-GTN算法中训练。在真实世界云数据中心数据集Clearwater和MBD上采用精确率、召回率和F1分数这3个性能指标验证了该文所提模型的有效性。实验结果表明,MCBiWGAN-GTN在这两个数据集上的性能稳定并优于所比较的方法。

基于VMD-GA-BiLSTM的月降水量预测方法

利用辽宁省气象局提供的地面观测降水资料,构建了具有多元时间特征的降水数据,采用变分模态分解方法(variational mode decomposition,VMD)组合遗传算法(genetic algorithm,GA)对双向长短时记忆神经网络(bidirectional long short-term memory,BiLSTM)进行优化,建立基于VMD-GA-BiLSTM的月降水量预测模型,并与BiLSTM、VMD-BiLSTM和GA-BiLSTM进行实验对比,应用均方根误差(root mean square error,RMSE)、平均绝对误差(mean absolute error,MAE)和R 2决定系数作为模型评价指标。实验结果表明:VMD-GA-BiLSTM模型的R 2决定系数达到0.98,RMSE和MAE表现更低,验证了VMD-GA-BiLSTM模型在时间序列预测方面的优势。

基于张量表示的间歇性序列自适应区间预测

在实际业务中,配件需求发生随机、需求量波动大,配件序列数据呈现明显的间歇性分布,同时由于人工报单失误或特殊事件等因素的影响,实际配件需求易发生异常变化,导致传统的时间序列预测方法难以捕捉配件需求量的演化规律,预测结果不确定性高、可靠性不足。为解决上述问题,提出了一种基于张量表示的间歇性序列自适应区间预测方法。首先,利用层次聚类,基于间歇性序列的平均需求间隔和平方变异系数指标筛选相似序列形成序列簇,用于提取簇内公共需求演化信息,增加可预测性;其次,通过张量分解重构原始需求序列,在最大限度保留序列核心信息的前提下平滑序列中的异常值;最后,构建一种自适应预测区间算法,通过动态更新机制得到配件需求量的预测值和预测区间,以确保结果的可靠性。利用某大型轨道交通制造企业实际售后数据进行验证,与现有典型时间序列预测方法相比,所提方法可有效挖掘不同特点间歇性序列的演化趋势,提高小样本间歇性序列的预测精度。实验结果表明:所提方法在间歇性特有指标均方根标准误差(RMSSE)上,相较于需求预测主流的深度学习方法平均降低了0.32,且当预测结果出现失真时,可提供一个可靠的弹性预测区间,为实际应用中企业智能备件计划决策提供了一种新的解决方案。

基于模态分解与SRU网络的时间序列预测

时间序列预测在工业、农业、金融及军事等领域中具有重要的应用价值。为了进一步提高预测的可靠性和准确性,构建一种基于模态分解与SRU网络的杂交预测模型。首先,针对模态个数难以确定的问题,构建基于平均样本熵来确定模态个数的自适应变分模态分解(AVMD)模型,以减少不同频率上的混叠及降低随机噪声的干扰。通过在Adam算法中引入了随机调整参数,来提高SRU网络的训练速度及增强网络跳出局部最优解的能力。最后,发展一种基于AVMD与SRU网络的杂交模型。为评估提出的预测模型的可靠性和准确性,将之与一些最新预测方法做比较。电力负荷序列的实验结果表明,所提出的杂交预测模型具有较高的准确性和可靠性。

彬长大佛寺矿井涌水量时序预测

为提高矿井涌水量预测精度,解决矿井涌水量预测无法及时响应动态变化的问题,构建一种基于模态分解和深度学习的矿井涌水量多因素时间序列组合预测模型。使用变分模态分解和灰色关联分析筛选主控因素,通过双向长短期记忆网络和卷积长短期记忆网络对高、低频模态分量进行预测。结果表明:对比不同时序预测模型,变分模态分解可以有效捕捉时序数据中的长期依赖关系,提供了更加准确的长期时序数据预测能力;经过鲸鱼优化、贝叶斯优化算法对不同频率模态分量的处理,有效降低了高频部分的无序性、复杂性并优化了较为线性、缓慢的低频部分;验证了矿井涌水量时序预测中的变分模态深度学习组合模型的有效性和适用性,预测精度满足生产需求。该理论丰富了矿井涌水量时序预测方法,对煤矿水害预防具有一定的理论意义。

改进多变量时序模型的露天涌水量预测

露天矿坑涌水量变化影响着边坡的稳定性、工程进度和设备使用寿命,在矿山汛期,涌水量的突增给矿山带来巨大的安全隐患。为了做好涌水量突增安全防范,对于汛期涌水量的精准预测成为矿山安全生产的一大难题。针对这一问题,提出了一种基于改进蜣螂优化算法(Sparrow Initialization Dung Beetle Optimizer,SIDBO)优化变分模态分解(Variational Mode Decomposition,VMD)-双向长短周期神经网络(Bi-directional Long Short-Term Memory,BiLSTM)时序模型预测露天矿坑涌水量的方法。对于难以确定VMD参数的问题,利用改进蜣螂优化算法寻找最优VMD核心参数组合。SIDBO算法首先基于t分布的差分策略优化勘探阶段,使用最优解和第二解中位搜寻策略增强全局最优解搜索能力,最后采用麻雀优化算法优化开发阶段。结果表明,与VMD-SIDBO-LSTM等模型相比较,SIDBO-VMD-SIDBO-BiLSTM模型预测精度更高,均方根误差(R_(MSE))、平均绝对误差(M_(AE))、平均绝对百分比误差(M_(APE))、R^(2)分别为5.96、4.96、0.41%、0.98,并将该模型与传统地质方法——水均衡法在实际工程实例中进行对比,该时序模型相对于水均衡法对于矿坑汛期涌水量预测精度提升了3.8%,为露天矿汛期涌水量预测提供了新的技术方法与思路。

配电网负荷预测中信号分解和预测模型组合的双层优化策略

负荷时间序列的波动性和非线性特征的加剧对负荷预测方法提出了更高的要求,而常规组合预测方法针对海量负荷数据存在应用局限性问题。为此,提出了配电网负荷预测中时序分解方法和预测模型组合的双层优化策略。首先针对某一负荷预测数据,在时序信号分解层配置权重,以负荷均方根误差最小寻优各分解方法的权重系数,进而获得各时序信号分解方法的最优组合;在此基础上,在预测模型层进行组合方案寻优,通过配置权重系数以获得各预测模型的最优组合,进一步提升负荷预测的精度。仿真结果表明,所提策略可根据预测对象的特征优化组合各信号分解方法和预测模型,降低了配电网负荷序列的非平稳性对预测精度的影响。

基于周期特征提取的DLnet预测模型研究

现有的预测方法很少独立分析能源消耗的周期性特征。本文提出了一个短期办公建筑能耗预测模型(DLnet),以解决周期性能耗数据利用效率低下的问题。首先,利用STL对能耗数据的周期成分进行分解,通过网格搜索算法寻找能耗数据的最优周期;然后,根据最优周期构建周期块;再根据周期块的数据形状构建时间序列块数据;之后,利用长短期记忆(LSTM)对时间序列块数据和周期块数据进行训练和学习;最后,通过线性回归将时间序列块数据和周期块数据的预测结果进行融合。事实证明,所提出的模型的4个预测精度指标分别比LSTM模型高7%,21%,25%和26%。

基于测点聚类的POD-BPNN风压重构方法

文章提出本征正交分解(POD)与聚类分析结合的结构表面风压测点分类与关键测点布置方法,基于少量测点的风压数据,通过POD与误差反向传播神经网络(BPNN)方法实现方柱结构表面风压时程的重构。机器学习数据集为多风向角均匀来流下单方柱测压风洞试验得到的测点风压时程。将44个测点的风压时程数据POD降维,并采用K-means++聚类分析得到方柱周向轮廓系数分布,并基于轮廓系数的多风向角平均值,得到12、16、20和24个关键测点的轴对称布置方案。以关键测点的风压时程数据为训练集,采用POD-BPNN方法重构方柱表面其余测点所在位置的风压时程,并将风压时程及其统计值同试验结果对比。从12~20测点方案,风压重构精度逐步提升;20测点和24测点方案的重构风压差异较小,二者都能较好地重构方柱表面风压分布,仅在0°风向角方柱脉动风压误差偏大。

基于改进灰狼优化与支持向量回归的滑坡位移预测

针对滑坡位移难以预测、影响因素难以选择等问题,提出一种结合了二次移动平均(DMA)法、变分模态分解(VMD)、改进灰狼优化(IGWO)算法与支持向量回归(SVR)的模型进行滑坡位移预测。首先,利用DMA提取滑坡位移趋势项和周期项,采用多项式拟合对趋势项进行预测;其次,对滑坡周期项的影响因素进行分类,采用VMD对原始影响因子序列进行分解获得最优序列;再次,提出一种结合SVR与基于改进Circle多策略的灰狼优化算法CTGWO-SVR(Circle Tactics Grey Wolf Optimizer with SVR)对滑坡周期项进行预测;最后采用时间序列加法模型求出累计位移预测序列,并采用灰色预测的后验证差校验和小概率误差对模型进行评价。实验结果表明,与GA-SVR和GWO-SVR模型相比,CTGWO-SVR的预测精度更高,拟合度达到0.979,均方根误差分别减小了51.47%与59.25%,预测精度等级为一级,可满足滑坡预测的实时性和准确性要求。

基于时序分解和SARIMA⁃DSR的台区可开放容量计算方法

合理地分析并准确计算台区可开放容量,能够优化配电系统的运行,提高线路利用率,保证台区配电变压器安全、经济、稳定运行。传统的可开放容量计算方法主要基于线路输电能力经验公式进行计算,未考虑高负荷运行台区的短时性及季节性,存在计算准确率和普适性低的问题。因此,提出一种基于局部加权周期趋势分解算法(STL)和季节性自回归滑动平均模型(SARIMA)与动态同时率(DSR)的台区可开放容量计算方法。该方法首先利用STL将历史台区负荷数据分解为趋势项、季节项和余项;其次,根据调整的历史台区负荷数据建立SARIMA台区负荷预测模型,预测未来台区负荷的变化及负荷峰值;同时,根据台区历史负荷数据建立台区DSR准则;最后,构建SARIMA‐DSR模型,合理调整可开放容量计算方法中的配置系数,实现台区的可开放容量的准确计算。