基于小波分析AR(P)-SVR组合模型在大坝变形预测中的应用

监测序列经小波分解后,得到低频分量和高频分量。对低频分量采用自回归AR(P)模型预测,对高频分量采用支持向量回归机SVR模型预测,最后将各分量进行小波重构,得到监测序列的预测值。结果表明,此种预测方法比直接使用SVR模型或经小波分解后再采用SVR模型预测精度高。     

Estimation of winter wheat crop growth parameters using time series Sentinel-1A SAR data

In the present study, Sentinel-1A Synthetic Aperture Radar analysis of time series data at C-band was carried out to estimate the winter wheat crop growth parameters. Five different date images were acquired during January 2015–April 2015 at different growth stages from tillering to ripening in Varanasi district, India. The winter wheat crop parameters, i.e. leaf area index, vegetation water content (VWC), fresh biomass (FB), dry biomass (DB) and plant height (PH) were estimated using random forest regression (RFR), support vector regression (SVR), artificial neural network regression (ANNR) and linear regression (LR) algorithms. The Ground Range Detected products of Interferometric Wide (IW) Swath were used at VV polarization. The three different subplots of 1 m² area were taken for the measurement of crop parameters at every growth stage. In total, 73 samples were taken as the training data-sets and 39 samples were taken as testing data-sets. The highest sensitivity (adj. R^2?=?0.95579) of backscattering with VWC was found using RFR algorithm, whereas the lowest sensitivity (adj. R^2?=?0.66201) was found for the PH using LR algorithm. Overall results indicate more accurate estimation of winter wheat parameters by the RFR algorithm followed by SVR, ANNR and LR algorithms.     

昆仑山地区冻融土导热系数试验测试与预测模型研究

为探究青藏高原工程走廊带昆仑山地区冻融土导热系数基本特征,采用瞬态平面热源法对钻取的349组冻土试样和245组融土试样导热系数进行了测试,分析了五类土导热系数分布特征及天然含水率、干密度与导热系数的偏相关性,并以两者为变量因素建立了经验公式拟合、支持向量回归（SVR）和径向基（RBF）神经网络导热系数预测模型。结果表明:冻融土导热系数整体均呈粗颗粒土大于细颗粒土特征,且冻土和融土导热系数随土性分布规律存在差异;天然含水率、干密度与导热系数均呈正相关性,不同土类偏相关性结果差异明显,典型土导热系数二元经验回归方程表现为非线性拟合结果。对比三种预测模型下各典型土冻融土导热系数预测结果,全风化千枚岩、角砾及砾砂三种预测模型效果整体较佳,粉土的SVR及RBF神经网络预测精度较好;融土导热系数预测效果整体略优于冻土,SVR及RBF神经网络模型下角砾、粉土及全风化千枚岩融土导热系数预测精度较高。综合导热系数模型预测效果和误差结果分析可得,SVR和RBF神经网络模型预测效果显著优于经验方程拟合,后者针对部分土性拟合效果相对较好,可满足一般工程估算需求;SVR和RBF神经网络预测模型针对不同土性导热系数预测效果呈差异性变化,整体预测效果相当,且预测精度更高、应用土性范围更广。     

Potential of support vector regression for prediction of monthly streamflow using endogenous property

In the recent past, a variety of statistical and other modelling approaches have been developed to capture the properties of hydrological time series for their reliable prediction. However, the extent of complexity hinders the applicability of such traditional models in many cases. Kernel‐based machine learning approaches have been found to be more popular due to their inherent advantages over traditional modelling techniques including artificial neural networks(ANNs ). In this paper, a kernel‐based learning approach is investigated for its suitability to capture the monthly variation of streamflow time series. Its performance is compared with that of the traditional approaches. Support vector machines (SVMs) are one such kernel‐based algorithm that has given promising results in hydrology and associated areas. In this paper, the application of SVMs to regression problems, known as support vector regression (SVR), is presented to predict the monthly streamflow of the Mahanadi River in the state of Orissa, India. The results obtained are compared against the results derived from the traditional Box–Jenkins approach. While the correlation coefficient between the observed and predicted streamflows was found to be 0·77 in case of SVR, the same for different auto‐regressive integrated moving average (ARIMA) models ranges between 0·67 and 0·69. The superiority of SVR as compared to traditional Box‐Jenkins approach is also explained through the feature space representation. Copyright © 2009 John Wiley & Sons, Ltd.     

Forecasting of chlorophyll-a concentrations in South San Francisco Bay using five different models

Accurate and reliable eutrophication level forecasting models are necessary for characterizing complicated water quality processes in bays. In this study, the ability of coupled discrete wavelet transform (DWT) with artificial neural network (ANN) and multi linear regression (MLR) (WANN and WMLR), ANN, MLR and genetic algorithm-support vector regression (GA-SVR) models for chlorophyll-a level forecasting applications were considered. The data used to develop and validate the models were monthly chlorophyll-a (Chl-a) data recorded from January 1994 to December 2013 were obtained from the NO.36 station located in the South San Francisco bay, USA. In the proposed WANN and WMLR models, the observed time series of Chl-a were decomposed to sub time series at different scales by DWT. Afterwards, the sub time series were used as input data to the ANN and MLR systems to predict the 1 month ahead Chl-a. Also the genetic algorithm was linked to SVR models to search for the optimal SVR parameters. The relative performance of the proposed models was compared together and the results showed that the WANN models were found to provide more accurate monthly Chl-a forecasts compared to the other models. The determination coefficient was 0.87, −0.04, 0.31, −2.36 and 0.24 for the WANN, WMLR, ANN, MLR and GA-SVR models, respectively. In addition, the WANN model predicted extreme Chl-a values precisely. The results indicate that the WANN models are a promising new method for eutrophication level forecasting in bays such as those found in South San Francisco Bay.     

SVR在平均海面高格网化中研究

研究了利用SVR进行平均海面高格网化的方法,并结合平均海面高数据的特点,确定了格网化半径;利用Surfer11软件中几种数据插值方法,对平均海面高进行了格网化处理,并对结果进行交叉验证;将SVR格网化方法所得平均海面高与surfer11格网化所得平均海面高进行了对比,结果表明利用SVR进行平均海面高格网化是切实可行的。