排序方式： 共有30条查询结果，搜索用时 15 毫秒
11.
A hybrid neural network model for typhoon-rainfall forecasting 总被引：2，自引：0，他引：2
A hybrid neural network model is proposed in this paper to forecast the typhoon rainfall. Two different types of artificial neural networks, the self-organizing map (SOM) and the multilayer perceptron network (MLPN), are combined to develop the proposed model. In the proposed model, a data analysis technique is developed based on the SOM, which can perform cluster analysis and discrimination analysis in one step. The MLPN is used as the nonlinear regression technique to construct the relationship between the input and output data. First, the input data are analyzed using a SOM-based data analysis technique. Through the SOM-based data analysis technique, input data with different properties are first divided into distinct clusters, which can help the multivariate nonlinear regression of each cluster. Additionally, the topological relationships among data are discovered from which more insight into the typhoon-rainfall process can be revealed. Then, for each cluster, the individual relationship between the input and output data is constructed by a specific MLPN. For evaluating the forecasting performance of the proposed model, an application is conducted. The proposed model is applied to the Tanshui River Basin to forecast the typhoon rainfall. The results show that the proposed model can forecast more precisely than the model developed by the conventional neural network approach. 相似文献
12.
登陆台风的多层递阶预报 总被引：1，自引：0，他引：1
多层递阶预报是动态系统的新型统计预报理论。由于它把动态系统看成是一个时变参数系统,因而与客观实际较为符合,预报误差也相对较小,利用它来进行台风预报具有一定的实用价值。 相似文献
13.
A catastrophic earthquake with a Richter magnitude of 7.3 occurred in the Chi-Chi area of Nantou County on 21 September 1999.
Large-scale landslides were generated in the Chiufenershan area of Nantou County in central Taiwan. This study used a neural
network-based classifier and the proposed NDVI-based quantitative index coupled with multitemporal SPOT images and digital
elevation models (DEMs) for the assessment of long-term landscape changes and vegetation recovery conditions at the sites
of these landslides. The analyzed results indicate that high accuracy of landslide mapping can be extracted using a neural
network-based classifier, and the areas affected by these landslides have gradually been restored from 211.52 ha on 27 September
1999 to 113.71 ha on 11 March 2006, a reduction of 46.24%, after six and a half years of assessment. In accordance with topographic
analysis at the sites of the landslides, the collapsed and deposited areas of the landslide were 100.54 and 110.98 ha, with
corresponding debris volumes of 31,983,800 and 39,339,500 m3. Under natural vegetation succession, average vegetation recovery rate at the sites of the landslides reached 36.68% on 11
March 2006. The vegetation recovery conditions at the collapsed area (29.17%) are shown to be worse than at the deposited
area (57.13%) due to topsoil removal and the steep slope, which can be verified based on the field survey. From 1999 to 2006,
even though the landslide areas frequently suffered from the interference of typhoon strikes, the vegetation succession process
at the sites of the landslides was still ongoing, which indicates that nature, itself, has the capability for strong vegetation
recovery for the denudation sites. The analyzed results provide very useful information for decision-making and policy-planning
in the landslide area. 相似文献
14.
To be physically interpretable, sub-pixel land cover fractions or abundances should fulfill two constraints, the Abundance Non-negativity Constraint (ANC) and the Abundance Sum-to-one Constraint (ASC). This paper focuses on the effect of imposing these constraints onto the MultiLayer Perceptron (MLP) for a multi-class sub-pixel land cover classification of a time series of low resolution MODIS-images covering the northern part of Belgium. Two constraining modes were compared, (i) an in-training approach that uses ‘softmax’ as the transfer function in the MLP’s output layer and (ii) a post-training approach that linearly rescales the outputs of the unconstrained MLP. Our results demonstrate that the pixel-level prediction accuracy is markedly increased by the explicit enforcement, both in-training and post-training, of the ANC and the ASC. For aggregations of pixels (municipalities), the constrained perceptrons perform at least as well as their unconstrained counterparts. Although the difference in performance between the in-training and post-training approach is small, we recommend the former for integrating the fractional abundance constraints into MLPs meant for sub-pixel land cover estimation, regardless of the targeted level of spatial aggregation. 相似文献
15.
针对WebGIS多尺寸三维景观地图数据处理问题,提出了一种高速数据索引结构MSORQ-Tree。根据该索引的算法,得出移动WebGIS景观图,将该索引和其他索引进行性能比较。结果显示,基于金字塔分割规则的区域,进行分割四叉树所获取的MSORQ-Tree高速索引可有效处理WebGIS中海量景观地图数据。 相似文献
16.
当某一问题很难甚至无法用数学方法建立精确模型时,人工神经网络的方法则显示了优势。对于一个具体问题,采用何种网络结构是至关重要的。本文以美国内华达州Cuprite矿区成像光谱数据特征矿物识别为例,采用6种不同结构的多层前馈网络模型,从其训练难度、运算效率及识别效果等方面进行了综合对比分析。 相似文献
17.
The Canyon Range syncline, Central Utah, is composed of an alternating sequence of competent quartzite and incompetent argillite layers and is used here as a natural case study of multilayer folding processes. Geometric details of this fold are evaluated in terms of energy consumption in order to determine which kinematic components of folding are dominant at various stages of fold tightening. In addition, this paper attempts to evaluate what mechanism(s) (e.g. kink folding, fracture formation and sliding along surfaces) are involved in each kinematic component.In general, the patterns preserved in the Canyon Range syncline are comparable to multilayer folding models. In more detail, the following is concluded from this case study. (1) The competent and incompetent members deformed primarily by cataclastic flow and consumed approximately equal amounts of energy. (2) The roles of original competent and incompetent layers reversed during folding. (3) As the syncline tightened, less energy was consumed with increasing hinge fractions. (4) The least amount of energy was consumed with 40° limb dips (i.e., 100° interlimb angle). (5) With an open fold geometry (interlimb angle ≥140°), the hinge region consumed 70% of the fold's total energy. (6) Once the fold reached an interlimb angle of 60°, the limbs consume close to 70% of the total energy. (7) When the fold reached an interlimb angle of ≤60°, the incompetent layer(s) consumed 90% of the fold's energy. 相似文献
18.
综合考虑农田生态系统中水、热、CO2输送所涉及的大气、水文、生物等生物物理过程,以Farquhar等提出的叶片尺度光合作用生物化学过程机理模型为理论基础,对其进行空间尺度扩展,并改进冠层分层方法,建立了均匀农田与大气之间物质输送和能量交换的多层模式,在模式中运用双叶模型,同时考虑叶片氮素水平垂直差异,对2008年4—5月华北平原冬小麦生长旺季农田生态系统中冠层CO2通量进行了模拟研究,并利用涡度相关观测的通量数据对模型的有效性加以验证,结果表明:在冠层多层空间,小麦拔节至孕穗期和开花至乳熟期叶片氮含量随冠层高度的衰减系数分别为0.793(R2=0.698)和1.374(R2=0.728),冠层内叶片氮含量的空间分布可以用以相对累积叶面积指数为自变量的函数来描述;模型分别计算各层阴、阳叶的光截取、气孔传导、光合作用等,最终计算冠层上方CO2通量,冬小麦农田净生态系统生产力模拟值与实测值相关显著(R2=0.78),模拟的CO2通量日变化特征晴天昼间比阴雨天和夜间的效果好;在考虑丛聚影响的叶片非随机分布的密集农田中,阴叶对总初始生产力的贡献率在35.7%左右,对生产力贡献很重要。分层统计显示,作物最终产量的形成主要... 相似文献
19.
A numerical method is proposed for solving the two layer shallow water equations with variable bathymetry in one dimension based on high-resolution f-wave-propagation finite volume methods. The method splits the jump in the fluxes and source terms into waves propagating away from each grid cell interface. It addresses the required determination of the system’s eigenstructure and a scheme for evaluating the flux and source terms. It also handles dry states in the system where the bottom layer depth becomes zero, utilizing existing methods for the single layer solution and handling single layer dry states that can exist independently. Sample results are shown illustrating the method and its handling of dry states including an idealized ocean setting. 相似文献
20.
The fundamental solutions of axisymmetric elastodynamic problem for the multilayered half-space due to an impulsive ring source acting within a layered elastic media are derived in time domain with the aid of Laplace–Hankel mixed transform and transfer matrix techniques. In addition, an effective numerical procedure, which utilizes the fast Hankel transform algorithm, is also proposed to calculate these solutions. Illustrative examples have been given to demonstrate that the fundamental solutions can be readily evaluated and the numerical results are of high accuracy. The present solutions can be directly applied to determine the transient wave fields caused by a seismic source and show the potential application to the elastodynamic problems solved by the boundary element method. 相似文献