基坑工程支护选型多样性探讨

在建造深基坑工程支护选型专家系统ｔｙｐｅＥＳ过程中,通过对专家知识的分析后认为：支护选型要全面地考虑支护主类、复合型支护、支护亚类及地下水处理方案等才比较合理。最后举例用新的产生式规则形式表达出这些专家知识。     

多分类器实例协同训练遥感图像检索

提出一种基于多分类器协同训练的遥感图像检索方法,该方法在不同特征集上分别建立分类器,利用不同分类器的协同性自动标记未知样本,从而有效解决了小样本问题。通过与相关反馈方法进行实验比较分析,结果表明,这两种方法各有优劣,检索结果基本相当,然而多分类器协同训练方法避免了相关反馈过程中人工的多次反馈,自动化程度更高。     

基坑工程设计中的专家系统

介绍了基坑工程及专家系统技术, 提出用专家系统解决基坑工程中的问题的观点, 并介绍了一个实例, 证明了专家系统作为基坑工程设计的计算机辅助手段是争实可行的。     

西北地区主要农作物遥感估产信息系统设计

阐述了西北地区主要农作物遥感估产过程中背景数据的类型及获取,信息系统的基本内容和基本结构。介绍了资源环境(背景)信息系统、数据库系统、GIS空间信息提取、估产模型库系统、专家知识库系统和人工神经网络、基于INTERNET的数据发布等各个子模块的基本结构和功能。并描述了各个模块之间的相互关系。西北地区农作物遥感估产信息系统的建成,可及时、客观、准确地提供农作物的长势情况,粮食产量,为有关部门(如农业部门、政府决策部门)的相关决策提供科学数据和依据。     

A long-term volcanic hazard event tree for Teide-Pico Viejo stratovolcanoes (Tenerife,Canary Islands)

We propose a long-term volcanic hazards event tree for Teide-Pico Viejo stratovolcanoes, two complex alkaline composite volcanoes that have erupted 1.8–3 km³ of mafic and felsic magmas from different vent sites during the last 35 ka. This is the maximum period that can be investigated from surface geology and also represents an upper time limit for the appearance of the first phonolites on that volcano. The whole process of the event tree construction was divided into three stages. The first stage included the determination of the spatial probability of vent opening for basaltic and phonolitic eruptions, based on the available geological and geophysical data. The second, involved the analysis of the different eruption types that have characterised the volcanic activity from Teide during this period. The third stage focussed on the generation of the event tree from the information obtained in the two previous steps and from the application of a probabilistic analysis on the occurrence of each possible eruption type. As for other volcanoes, the structure of the Teide-Pico Viejo Event Tree was subdivided into several steps of eruptive progression from general to more specific events. The precursory phase was assumed as an unrest episode of any geologic origin (magmatic, hydrothermal or tectonic), which could be responsible for a clear increase of volcanic activity revealed by geophysical and geochemical monitoring. According to the present characteristics of Teide-Pico Viejo and their past history, we started by considering whether the unrest episode would lead to a sector collapse or not. If the sector collapse does not occur but an eruption is expected, this could be either from the central vents or from any of the volcanoes' flanks. In any of these cases, there are several possibilities according to what has been observed in the period considered in our study. In the case that a sector collapse occurs and is followed by an eruption we considered it as a flank eruption. We conducted an experts elicitation judgement to assign probabilities to the different possibilities indicated in the event tree. We assumed long term estimations based on existing geological and historical data for the last 35 Ka, which gave us a minimum estimate as the geological record for such a long period is incomplete. However, to estimate probabilities for a short term forecast, for example during an unrest episode, we would need to include in the event tree additional information from the monitoring networks, as any possible precursors that may be identified could tell us in which direction the system will evolve. Therefore, we propose to develop future versions of the event tree to include also the precursors that might be expected on each path during the initial stages of a new eruptive event.     

Region-based classification of PolSAR data using radial basis kernel functions with stochastic distances

Region-based classification of PolSAR data can be effectively performed by seeking for the assignment that minimizes a distance between prototypes and segments. Silva et al. [“Classification of segments in PolSAR imagery by minimum stochastic distances between wishart distributions.” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 6 (3): 1263–1273] used stochastic distances between complex multivariate Wishart models which, differently from other measures, are computationally tractable. In this work we assess the robustness of such approach with respect to errors in the training stage, and propose an extension that alleviates such problems. We introduce robustness in the process by incorporating a combination of radial basis kernel functions and stochastic distances with Support Vector Machines (SVM). We consider several stochastic distances between Wishart: Bhatacharyya, Kullback-Leibler, Chi-Square, Rényi, and Hellinger. We perform two case studies with PolSAR images, both simulated and from actual sensors, and different classification scenarios to compare the performance of Minimum Distance and SVM classification frameworks. With this, we model the situation of imperfect training samples. We show that SVM with the proposed kernel functions achieves better performance with respect to Minimum Distance, at the expense of more computational resources and the need of parameter tuning. Code and data are provided for reproducibility.     

Object-based image analysis of suburban landscapes using Landsat-8 imagery

Many experiments of object-based image analysis have been conducted in remote sensing classification. However, they commonly used high-resolution imagery and rarely focused on suburban area. In this research, with the Landsat-8 imagery, classification of a suburban area via the object-based approach is achieved using four classifiers, including decision tree (DT), support vector machine (SVM), random trees (RT), and naive Bayes (NB). We performed feature selection at different sizes of segmentation scale and evaluated the effects of segmentation and tuning parameters within each classifier on classification accuracy. The results showed that the influence of shape on overall accuracy was greater than that of compactness, and a relatively low value of shape should be set with increasing scale size. For DT, the optimal maximum depth usually varied from 5 to 8. For SVM, the optimal gamma was less than or equal to 10^?2, and its optimal C was greater than or equal to 10². For RT, the optimal active variables was less than or equal to 4, and the optimal maximum tree number was greater than or equal to 30. Furthermore, although there was no statistically significant difference between some classification results produced using different classifiers, SVM has a slightly better performance.     

基于ANN-FES的石漠化综合治理智能决策支持系统设计及应用研究

对人工智能技术的两个分支神经网络(ANN)与模糊专家系统(FES)各自的基本工作原理进行了阐述,分析了基于神经网络和模糊专家系统集成的混合系统功能框架,并介绍了系统结构及知识表示、知识获取、知识简化和推理机制等方面的基本方法.在此基础上,以都安石漠化综合治理智能决策为例,提出了基于神经网络和专家系统集成的石漠化智能决策系统的结构.人工神经网络实现石漠化预警分析,预测得到的石漠化危险性指数,最后得出专家系统所需的预警度(无警、轻警、中警和重警).模糊专家系统的推理机通过对神经网络得到的初步数据和其他测量的数据处理,实现系统的综合诊断,最后由治理模式系统确定采用哪种综合治理模式.该方法融合了神经网络自适应学习能力强和模糊专家系统知识表达明确的优点,简化了神经网络学习数据获取及模糊推理规则建立的过程.     

Discrimination of agricultural crops in a tropical semi-arid region of Brazil based on L-band polarimetric airborne SAR data

Recent articles are indicating that polarimetric data provide significantly more information than conventional or multi-polarized images, particularly due to the additional phase information. The objective of this paper is to evaluate the multi-polarized and fully polarimetric L-band airborne SAR-R99B data, in terms of their capability to distinguish among different agricultural crops in the western part of Bahia State, Brazil. Emphasis was given to coffee, cotton and pasture crops which were at well developed growing stages. Discrimination among crops was carried out using graphical analysis of mean backscatter values. Crop classification was performed for single and multiple polarizations, and fully polarimetric images with a classifier that uses the contextual Iterated Conditional Modes–ICM algorithm. The investigation confirmed the potential of L-band multi-polarized and polarimetric airborne SAR-R99B data to distinguish and classify agricultural crops in the tropical condition of the test-site. In addition, it clearly indicated the gradual and considerable improvement that was achieved going from single to three polarizations and from multi-polarized to fully polarimetric images.     

上海强风暴潮预警报系统设计总体框架

随着信息化程度的提高,可以利用计算机技术建立强风暴潮预警报系统。上海强风暴潮预警报系统包括三个层面:a)强风暴潮延时与实时资料数据库;b)强风暴潮数值预报和专家系统工作站;c)强风暴潮预警报服务网络系统。在风暴潮预报上可以通过数值计算结果,最后能够直接、自动、快速地将预报结果发布到各个相关单位和媒体,同时也能作为预报员在预报风暴潮时的辅助决策系统。