Fuzzy set approaches to classification of rock masses

Rock mass classification is analogous to multi-feature pattern recognition problem. The objective is to assign a rock mass to one of the pre-defined classes using a given set of criteria. This process involves a number of subjective uncertainties stemming from: (a) qualitative (linguistic) criteria; (b) sharp class boundaries; (c) fixed rating (or weight) scales; and (d) variable input reliability. Fuzzy set theory enables a soft approach to account for these uncertainties by allowing the expert to participate in this process in several ways. Hence, this study was designed to investigate the earlier fuzzy rock mass classification attempts and to devise improved methodologies to utilize the theory more accurately and efficiently. As in the earlier studies, the Rock Mass Rating (RMR) system was adopted as a reference conventional classification system because of its simple linear aggregation.

The proposed classification approach is based on the concept of partial fuzzy sets representing the variable importance or recognition power of each criterion in the universal domain of rock mass quality. The method enables one to evaluate rock mass quality using any set of criteria, and it is easy to implement. To reduce uncertainties due to project- and lithology-dependent variations, partial membership functions were formulated considering shallow (<200 m) tunneling in granitic rock masses. This facilitated a detailed expression of the variations in the classification power of each criterion along the corresponding universal domains. The binary relationship tables generated using these functions were processed not to derive a single class but rather to plot criterion contribution trends (stacked area graphs) and belief surface contours, which proved to be very satisfactory in difficult decision situations. Four input scenarios were selected to demonstrate the efficiency of the proposed approach in different situations and with reference to the earlier approaches.     

The crater-facies kimberlite system of Tokapal, Bastar District, Chhattisgarh, India

Discovery of diamondiferous kimberlites in the Mainpur Kimberlite Field, Raipur District, Chhattisgarh in central India, encouraged investigation of similar bodies in other parts of the Bastar craton. The earlier known Tokapal ultramafic intrusive body, located beyond the 19-km milestone in Tokapal village along the Jagdalpur–Geedam road, was reinterpreted as crater-facies kimberlite. Its stratigraphic position in the Meso-Neoproterozoic intracratonic sedimentary Indravati basin makes it one of the oldest preserved crater-facies kimberlite systems. Ground and limited subsurface data (dug-, tube-wells and exploratory boreholes) have outlined an extensive surface area (>550 ha) of the kimberlite. The morphological and surface color features of this body on enhanced satellite images suggest that there is a central feeder surrounded by a collar and wide pyroclastic apron. Exploration drilling indicates that the central zone probably corresponds to a vent overlain by resedimented volcaniclastic (epiclastic) rocks that are surrounded by a 2-km-wide spread of pyroclastic rocks (lapilli tuff, tuff/ash beds and volcaniclastic breccia). Drill-holes also reveal that kimberlitic lapilli tuffs and tuffs are sandwiched between the Kanger and Jagdalpur Formations and also form sills within the sedimentary sequence of the Indravati basin. The lapilli tuffs are commonly well stratified and display slumping. Base surges and lava flows occur in the southern part of the Tokapal system. The geochemistry and petrology of the rock correspond to average Group I kimberlite with a moderate degree of contamination. However, the exposed rock is intensely weathered and altered with strong leaching of mobile elements (Ba, Rb, Sr). Layers of vesicular fine-grained glassy material represent kimberlitic lava flows. Tuffs containing juvenile lapilli with pseudomorphed olivine macrocrysts are set in a talc–serpentine–carbonate matrix with locally abundant spinel and sphene. Garnet has not been observed, and phlogopite is very rare. Very limited microdiamond testing (two 18-kg samples) proved negative; however, the composition of chromite grains indicate crystallization in the diamond stability field.     

Découverte d'un diatrème de kimberlite diamantifère à Séguéla en Côte-d'Ivoire

The Séguéla area in Ivory Coast is known for its diamond-bearing field related to dykes of kimberlite and lamproite. These dykes, devoid of any deformation and metamorphism, crosscut the Birimian formations. Their N 170° orientation is controlled by the tectonized contact between the Archean and the Paleoproterozoic shields of the West-African craton. Discovery of a diatreme, with its pipe breccias and well-preserved maar sediments, below the present-day colluvia, attests for the probable recent geological age (Cretaceous?) of the kimberlitic activity. To cite this article: A. Pouclet et al., C. R. Geoscience 336 (2004).     

基于神经网络的区域生态环境分类方法研究

如何利用智能化信息提取技术,进行区域生态环境自动分类,一直是一种前沿性研究。该文在分析研究区自然景观特征的基础上,总结了影响区域生态环境的建模要素,基于神经网络技术,并根据生态环境的遥感探测机理,利用TM卫星遥感数据中的可见光、热红外、植被指数(NDVI)以及DEM数据,建立了基于BP神经网络的区域生态环境信息自动提取模型,形成了一种新的生态环境分类方法,其分类结果与实际情况完全一致。     

论新土地分类在1∶1000土地利用现状调查中的应用

根据新土地分类在南海区1∶1000土地利用现状调查中的应用,采用文献分析法和实例验证法,探讨其在大比例尺土地利用现状调查中的适用性。结果表明:新土地分类在使用中存在诸如分类层次数目少且略显粗糙以及界线不严谨等问题。提出建议:增加分类层次熏进一步细化分类;更清晰表达地类涵义以及统一分类标准等。     

概率神经网络与BP网络模型在遥感图像分类中的对比研究

通过分析概率神经网络(以下称PNN)的基本结构及其训练算法,建立了卫星图像分类的概率神经网络模型,并通过实例对比分析了概率神经网络与BP网络分类模型的分类效果。实验表明,PNN图像分类方法在分类精度上优于误差反向传播神经网络模型,且分类时间相当,是一种有效的图像分类方法。     

IMD法在多光谱图像分类中的应用

数学形态学着重于分析和处理图像的几何结构信息。根据这一原理，在图像分类预处理过程中，对各种地物区域的几何结构特点进行分析，构造相应的结构元素，然后对图像进行形态迭代分解法(IMD，Iterative Morphological Decompostion)变换。在变换结果中，地物区域的灰度信息进行了归一化处理，同时区域的几何结构特点和独立地物得到了有效保留。将多光谱图像的IMD变换结果进行分类实验的结果表明，该方法可以有效提高多光谱图像分类的精度和效率，具有较强的适用性。     

基于光谱空间密度分析的边缘提取

针对传统的边缘提取方法大部分不适应高光谱数据的特点，提出了基于光谱空间密度分析边缘提取的思想。在分组主分量变换提取第一主分量作为特征维的基础上，采用面向对象的二次判别边缘的方法，通过立体判决将光谱空间中低密度超椭球体集群视为真实边缘点集群。试验表明，此方法是合理可行的。     

利用案例推理（CBR）方法对雷达图像进行土地利用分类

提出了基于案例推理 (CBR)的遥感分类的新方法。基于规则的专家系统被用来提高遥感分类的效率。但所涉及的规则可能多达上百或上千条 ,有的问题根本无法用规则来表达。CBR只是根据以往的案例进行推理 ,克服了基于规则的推理方法的不足 ,可以用来解决一些复杂的资源环境问题。利用CBR和模糊数学结合 ,并通过分层随机采样来控制案例在空间上的分布 ,以反映复杂环境所造成的光谱变化 ,由此解决遥感分类中的“同物异谱”现象。实验表明 ,所建立的案例库可以被重复多次使用 ,分类的效果比监督分类和非监督分类要好。