基于小波长短期记忆网络的风电功率超短期概率预测

随着大规模的风电并网,风电所具有的间歇性与随机性对电力系统的稳定性产生了很大的影响,风电功率预测成为当前解决该问题重要的方式之一.本文利用长短期记忆（LSTM）网络良好的时序记忆特性,将小波分解技术与LSTM深度网络结合,提出基于小波长短期记忆网络的风电功率超短期概率预测模型.首先通过小波分解技术将原始时间序列进行平稳化处理,再建立各子序列样本的LSTM网络预测模型,借助最大似然估计法估计预测误差的高斯分布函数,最终实现对未来4 h时刻的风电功率概率区间预测.最后,采用中国东北某风电场数据对所提方法进行算例分析,结果表明,将小波分解与深度学习方法结合可以较好地提高预测的精度,提高概率预测的区间可靠性.     

三参数小波及其在地震资料分析中的应用

提出了一类含有三个可调参数的分析小波（称为三参数小波）,通过选择这三个参数,可使其最适合于所给定的问题．Morlet小波及改进的Morlet小波是其特例．通过对三参数小波中的参数加以约束,可以获得一类新的近似解析小波．论证了通过恰当的选择参数,三参数小波不仅适合于分析包含慢变频率和振幅分量的信号,而且也适合于包含快变分量的信号．以三参数小波为分析小波,提出了一种用于薄互层地震资料分析的方法．该方法能够刻画薄互层的沉积旋回,也能研究薄互层内部的局部结构,并采用模型资料验证了方法的有效性．     

小波分析在地震资料去噪中的应用

本文阐述了小波变换和去噪的基本原理,根据模拟信号和实际地震信号的频谱分析,讨论了如何选择小波基,及去噪中的阈值问题,从小波分解出发,利用多尺度分解对地震资进行分析,并基于MATLAB语言和小波工具箱,实现了对地震资料的去噪.     

位场小波变换研究进展

小波变换的具有多尺度分析的特点,在位场资料分析中得到了广泛应用.本文总结了位场小波变换的理论基础及应用现状,介绍了位场小波基函数的概念.小波分析可以应用于位场分离、去噪、反演及综合地质解释等分析.文中从小波的数学性质和物理意义等角度讨论了位场资料处理中小波基函数的选取问题.     

基于小波变换的射频干扰消除方法的研究

在射电天文观测中,射频干扰(Radio Frequency Interference, RFI)会以多种形式混入望远镜接收系统,给观测带来误判或者降低观测信噪比.近年来国内国际射电天文快速发展,国内国际大型射电望远镜和阵列先后建设,观测灵敏度大为提高,射频干扰的影响尤为突出.随着科技发展和人类活动的加剧,射频干扰日益严重且不可逆转.提出利用2维离散小波变换的方法分析射电天文观测的数据,对望远镜系统输出的时间频率序列进行小波变换,根据小波系数分离出原始信号中各分量,每个分量统计得到相应的阈值,将各分量与阈值相比较识别干扰成分并标记去除.利用该方法对实际观测数据进行了处理,结果表明该方法能够很好地标记并消减干扰信号,且提高了观测的信噪比.     

利用极化SAR数据进行土地覆盖分类研究

基于相关矩阵特征向量的目标分解将地物回波复杂的散射过程分解成相互独立的三种单一散射分量:单向散射、双向散射和交叉散射,分别对应各自的目标相关矩阵。目标分解技术降低了散射回波之间的相关性,有利于分析地物散射机理,有助于提高分类精度。对荷兰F levoland地区全极化数据进行分解,经过试验和相关性分析,选用7种数据形成多参数数据组合,对其进行最大似然监督分类,同时进行常规三种极化加相位差的分类和基于复W ishart分布的最大似然分类,逐像元计算混淆矩阵,分析对比三种分类结果的精度,试验表明:相对于常规数据组合分类,基于复W ishart分布的监督分类可以小幅度提高分类精度,而利用目标分解得到多参数组合数据进行分类则有大幅度的提高。     

Variation characteristics of evaporation in the Gulang River Basin during 1959-2013

Based on monthly evaporation of two meteorological stations in the Gulang River Basin of China, the inter-annual variation of evaporation during 1959-2013 were analyzed using Mann-Kendall and wavelet analysis. The results demonstrated that the annual evaporation show a fluctuating increase over the past 50 years approximately, with an average increase rate of 4.26 mm per decade. The overall trend was decrease-increase-decrease. According to the cumulative anomaly curve,the turning point of the annual evaporation occurred in 1979, in which the evaporation increased in the early stage and decreased in the later stage. Meanwhile, the seasonal variation of the evaporation shows that it decreased in Spring and Autumn, and increased in Summer and Winter, especially obvious for the later. The evaporation abruptly changed in Spring and Summer in 2008 and in Winter in 1994. In addition, all evaporation increased after the changes. However,the evaporation in Autumn abruptly changed in 1986 and 1999, which show a trend of increase-decrease-increase.Wavelet analysis shows that evaporation in Summer and wet season would decrease in the next few years, and in the other seasons would increase. Based on the aforementioned analysis, it can be concluded that increased evaporation is mainly induced by increase of evaporation in dry season, especially in Winter, and this trend to be continued in the future for the Gulang River Basin.     

Regional soil organic carbon prediction model based on a discrete wavelet analysis of hyperspectral satellite data

Most studies have the achieved rapid and accurate determination of soil organic carbon (SOC) using laboratory spectroscopy; however, it remains difficult to map the spatial distribution of SOC. To predict and map SOC at a regional scale, we obtained fourteen hyperspectral images from the Gaofen-5 (GF-5) satellite and decomposed and reconstructed the original reflectance (OR) and the first derivative reflectance (FDR) using discrete wavelet transform (DWT) at different scales. At these different scales, as inputs, we selected the 3 optimal bands with the highest weight coefficient using principal component analysis and chose the normalized difference index (NDI), ratio index (RI) and difference index (DI) with the strongest correlation with the SOC content using a contour map method. These inputs were then used to build regional-scale SOC prediction models using random forest (RF), support vector machine (SVM) and back-propagation neural network (BPNN) algorithms. The results indicated that: 1) at a low decomposition scale, DWT can effectively eliminate the noise in satellite hyperspectral data, and the FDR combined with DWT can improve the SOC prediction accuracy significantly; 2) the method of selecting inputs using principal component analysis and a contour map can eliminate the redundancy of hyperspectral data while retaining the physical meaning of the inputs. For the model with the highest prediction accuracy, the inputs were all derived from the wavelength range of SOC variations; 3) the differences in prediction accuracy among the different prediction models are small; and 4) the SOC prediction accuracy using hyperspectral satellite data is greatly improved compared with that of previous SOC prediction studies using multispectral satellite data. This study provides a highly robust and accurate method for predicting and mapping regional SOC contents.     

球面小波模型在GPS高程拟合中的应用

本文利用某地共99个GPS水准点的大地高和正常高求取高程异常,使用DOG球面小波模型和多面函数,分别对高程异常进行拟合。拟合时剔除模型残差大于2倍中误差的点,并在剔除粗差后重新进行拟合。通过比较外部检核点的已知高程异常值和球面小波模型值、多面函数拟合值之间的均方差评价模型的精度。数据结果表明,以外部检核均方差最小为准则,球面小波模型拟合精度较优,其拟合精度为1.65 cm,多面函数拟合精度为2.35 cm。     

极点对称模态分解下陕西气候变化特征及影响因素

全球变暖背景下,受人类活动和气候系统波动共同影响,气候要素响应具有非线性、非平稳特征,如何识别气候变化多时间尺度信息,是当前研究的热点话题.基于1970—2017年气温和降水逐日数据,辅以滑动平均、趋势分析和极点对称模态分解(ESMD)等方法,对陕西3大地理单元气候时空特征进行分析,进而探讨不同海区厄尔尼诺指数与气温、...