考虑块段效应的RBF神经网络在土壤空间插值中的应用

定义了土壤变异中的块段效应,提出了考虑块段效应的RBF神经网络空间插值模型(RBFBE法),以期提高土壤水分和养分的插值精度;并以江苏省扬州市区北部某试区为例,通过A、B两种训练方案,将RBFBE法对土壤含水率与有机质含量的插值结果与常规的RBF神经网络(RBFANN法)空间插值结果及普通克里金法(OK法)插值结果进行了对比分析。结果表明:与OK法相比,RBFBE法能使土壤特性的均方误差M_se缩小19.0%~62.2%,预测吻合度G提高8.9%~28.8%;与输入信息相同的RBFANN法相比,RBFBE法亦能使土壤特性的均方误差M_se缩小10.0%~48.8%,预测吻合度G提高3.4%~22.0%;此外,研究也表明RBFBE法具有较强的泛化能力。考虑块段效应的RBF神经网络方法有利于拓展人工神经网络方法在土壤特性空间插值中的应用范围,具有一定的应用前景。     

Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data

Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R² = 0.81, root mean square error (RMSE) = 0.08, and R² = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.     

基于混合阶矢量基函数的海洋可控源电磁三维谱元法数值模拟

在前人工作的基础上,本文推导了电导率任意各向异性介质的海洋可控源电磁三维谱元法正演方程.采用一次场/二次场分离算法结合混合阶矢量基函数,可以有效避免源点的奇异性的影响,从而提高数值解的精度.采用任意六面体单元离散研究区域,有利于模拟复杂地形和地电结构.利用不完全LU分解的Induced Dimension Reduction（IDR（s））迭代算法求解线性方程组,有效地提高了求解的效率.设计典型的地电模型进行正演计算,并将计算结果与有限元解进行对比,对比结果表明本文提出的基于混合阶矢量基函数的海洋可控源电磁三维谱元数值模拟算法是正确的、有效的.本文算法具有良好的通用性,可推广用于电导率呈任意各向异性的陆地电磁、井中电磁等数值模拟研究.

     

基于紧支径向基函数的点插值无网格方法

紧支径向基函数能使支配方程中的刚度矩阵具有稀疏性,很适合应用于无网格方法中,其缺点是在插值计算时精度不高.点插值方法的插值函数具有Delta函数性质,可以很方便的施加本质边界条件,但在计算插值函数时矩阵易出现奇异.为了提高计算精度并避免点插值法的局限性,首先对紧支径向基函数进行完备性修正,然后用完备性修正的紧支径向基函数代替多项式来形成插值函数,建立了紧支径向基函数点插值方法.由于该方法中的形函数满足Delta函数性质,因此本质边界条件可以像传统的有限元方法一样很容易施加.然后将该方法用于二维弹性静力问题的求解,导出了其相应的离散方程.最后将该方法应用于一个悬臂梁的分析中,初步验证了该方法的有效性与合理性.     

东准噶尔蛇绿混杂岩带填图等级体制划分意见讨论

当洋盆闭合洋壳残片构造侵位于陆壳之上时 ,共同组成蛇绿混杂岩带。由于构造破坏 ,蛇绿岩及伴生的深海沉积物 (放射虫硅质岩、粘土等 )往往呈构造包体形式赋存在古大陆边缘沉积的陆源碎屑物基质中 ,基质是混杂岩带的主体。它们属构造无序岩层 ,不服从层序律。在造山带 1∶ 2 5万区域填图中 ,首先考虑蛇绿混杂岩的产出特点 ,划分出构造包体和基质两大类 ,分别建立“岩群”;其次根据填图精度的要求 ,按照它们各自组成的地质单元分别建立“岩组”、“岩段”,对于基质中不同时代的地层单元能够恢复原始层序的可以建立“组”、“段”。为达到蛇绿混杂岩带的研究目的 ,测制大比例尺地质图作为补充图件     

Determining the Gravitational Gradient Tensor Using Satellite-Altimetry Observations over the Persian Gulf

With the advent of satellite altimetry in 1973, new scientific applications became available in oceanography, climatology, and marine geosciences. Moreover, satellite altimetry provides a significant source of information facilitated in the geoid determination with a high accuracy and spatial resolution. The information from this approach is a sufficient alternate for marine gravity data in the high-frequency modeling of the marine gravity field quantities. The gravity gradient tensor, consisting of the second-order partial derivatives of the gravity potential, provides more localized information than gravity measurements. Marine gravity observations always carry a high noise level due to environmental effects. Moreover, it is not possible to model the high frequencies of the Earth's gravity field in a global scale using these observations. In this article, we introduce a novel approach for a determination of the gravity gradient tensor at sea level using satellite altimetry. Two numerical techniques are applied and compared for this purpose. In particular, we facilitate the radial basis functions (RBFs) and the harmonic splines. As a case study, the gravitational gradient tensor is determined and results presented in the Persian Gulf. Validation of results reveals that the solution of the harmonic spline approach has a better agreement with a theoretical zero-value of the trace of the Marussi gravitational gradient tensor. However, the data-adaptive technique in the RBF approach allows more efficient selection of the parameters and 3-D configuration of RBFs compared to a fixed parameterization by the harmonic splines.     

杂交边界点方法求解动态断裂力学问题

结合杂交边界点法和双互易法则,推导出求解动力问题的纯边界类型无网格方法--双互易杂交边界点方法,并将该方法用于求解含中心裂纹的方板受瞬态载荷作用的问题。该方法将问题的解分为通解和特解两部分,通解使用杂交边界点法求解,特解则利用局部径向基函数近似,域内布点仅仅为了径向基插值,因此仍然是一种纯边界类型的无网格方法。同时,将移动最小二乘近似中的基函数扩充,使该方法能更好地模拟裂纹尖端应力场的奇异性,具有后处理简单、精度高的优点。数值算例表明了该方法的稳定性和有效性。     

径向基神经网络在沉降预测中的应用

针对大型建筑物的沉降监测存在较多的不等时间间隔沉降监测数据,现有模型需要对此类数据进行等间隔处理后建立沉降预测模型的现状,该文采用无需对监测数据进行等间隔预处理的径向基神经网络对沉降监测数据建立沉降预测。通过对西安某大厦基坑开挖对地表和周围建筑物影响的沉降监测数据进行实例分析,并与非等间隔灰色GM(1,1)预测模型进行对比,利用模型评价指标评价预测模型精度。结果表明:采用径向基神经网络建立预测模型处理过程简便,其预测精度优于非等间隔灰色GM(1,1)预测模型。     

基于RBF神经网络的遥感影像分类器设计

设计了一种运用径向基函数神经网络进行遥感影像分类的监督分类器,以实际的遥感光谱影像分类为例,将分类效果同传统的最小欧氏距离法分类进行比较,探讨了RBF分类的优越性,结果表明RBF神经网络是一种更为有效的图像分类器。     

Monitoring nitrogen concentration of oilseed rape from hyperspectral data using radial basis function

Remote sensing technology is the important tool of digital earth, it can facilitate nutrient management in sustainable cropping systems. In the study, two types of radial basis function (RBF) neural network approaches, the standard radial basis function (SRBF) neural networks and the modified type of RBF, generalized regression neural networks (GRNN), were investigated in estimating the nitrogen concentrations of oilseed rape canopy using vegetation indices (VIs) and hyperspectral reflectance. Comparison analyses were performed to the spectral variables and the approaches. The Root Mean Square Error (RMSE) and determination coefficients (R²) were used to assess their predictability of nitrogen concentrations. For all spectral variables (VIs and hyperspectral reflectance), the GRNN method produced more accurate estimates of nitrogen concentrations than did the SRBF method at all ranges of nitrogen concentrations, and the better agreements between the measured and the predicted nitrogen concentration were obtained with the GRNN method. This indicated that the GRNN method is prior to the SRBF method in estimation of nitrogen concentrations. Among the VIs, the Modified Chlorophyll Absorption in Reflectance Index (MCARI), MCARI₁₅₁₀, and Transformed Chlorophyll Absorption in Reflectance Index are better than the others in estimating oilseed rape canopy nitrogen concentrations. Compared to the results from VIs, the hyperspectral reflectance data also gave an acceptable estimation. The study showed that nitrogen concentrations of oilseed rape canopy could be monitored using remotely sensed data and the RBF method, especially the GRNN method, is a useful explorative tool for oilseed rape nitrogen concentration monitoring when applied on hyperspectral data.