利用BP网络技术预测碳酸盐岩储层孔隙度

利用径向基函数(RadialBasisFunction,RBF)神经网络的原理对储层参数(孔隙度、渗透率)进行了预测,运用有效测井数据和岩心测试资料作为网络模型的学习样本,通过网络的学习、训练,建立了测井解释的RBF神经网络模型。应用此模型定量计算了鄂尔多斯盆地杭锦旗地区多口井的碎屑岩层的孔隙度和渗透率。与用传统的统计方法比较,神经网络的方法显示出了更好的精度和更强的实用性。     

Critiquing environmental management in indigenous Australia: two case studies

The notion of community participation in sustainable environmental management is well documented, but applications between environmental scientists and indigenous Australians are less known. Many indigenous Australians are socially and culturally marginalized, and agencies debate over appropriate designs for collaborative, cross-cultural environmental programmes that will alleviate marginalization. This paper presents two case studies from northern Australia, where indigenous people participated in an environmental project exploring the commercial potential of the local sea cucumber resource. A framework with principles of participation and knowledge exchange guided project implementation at both localities. Participant observation data that related to these principles suggests that abuse of power imbalances and exploitation (institutional racism) may be more easily disguised within formalized governance structures than in the informal networks and structures that can be supported through less formalized representation. Linking informal and formal governance structures and canvassing a range of governance modalities will ultimately connect the human behaviours and governance structures needed to progress indigenous environmental management in Australia.     

Self-organized complexity in geomorphology: Observations and models

The focus of this paper is to relate fundamental statistical properties of landforms and drainage networks to models that have been developed in statistical physics. Relevant properties and models are reviewed and a general overview is presented. Landforms and drainage networks are clearly complex, but well-defined scaling laws are found. Coastlines, topography contours, and lakes are classic self-similar fractals. The height of topography along a linear track is well approximated as a Brownian walk, a self-affine fractal. This type of behavior has also been found in surface physics, for example the surface roughness of a fracture. An applicable model is the Langevin equation, the heat equation with a stochastic white-noise driver. This model also reproduces the statistics of sediment deposition. Drainage networks were one of the original examples of self-similar fractal trees. An important advance in quantifying the structure of drainage networks is the application of the Tokunaga fractal side-branching statistics. A classic problem in statistical physics is the diffusion-limited aggregation. The resulting tree like structures have been shown to also satisfy the Tokunaga statistics. A modified version of the diffusion-limited aggregation model reproduces the statistics of drainage networks. It is concluded that the models developed in statistical physics have direct applicability to the fundamental problems in geomorphology.     

Application of Radial Basis Functional Link Networks to Exploration for Proterozoic Mineral Deposits in Central Iran

The metallogeny of Central Iran is characterized mainly by the presence of several iron, apatite, and uranium deposits of Proterozoic age. Radial Basis Function Link Networks (RBFLN) were used as a data-driven method for GIS-based predictive mapping of Proterozoic mineralization in this area. To generate the input data for RBFLN, the evidential maps comprising stratigraphic, structural, geophysical, and geochemical data were used. Fifty-eight deposits and 58 ‘nondeposits’ were used to train the network. The operations for the application of neural networks employed in this study involve both multiclass and binary representation of evidential maps. Running RBFLN on different input data showed that an increase in the number of evidential maps and classes leads to a larger classification sum of squared error (SSE). As a whole, an increase in the number of iterations resulted in the improvement of training SSE. The results of applying RBFLN showed that a successful classification depends on the existence of spatially well distributed deposits and nondeposits throughout the study area. An erratum to this article can be found at     

Ground subsidence,Quaternary faults and vulnerability of utilities and transportation networks in Thessaly,Greece

Ground fissures and subsidence have caused extensive damage in structures and the utility networks (roads, railroad line, Larisa NATO airport, telecommunication network) in the plain of Thessaly, central Greece, in the last 20 years. The fact that these fissures are parallel to Quaternary faults controlling the structural evolution of the Thessaly basin, marked by intense recent seismic activity, led some scientists to regard them as manifestation of tectonic creep, even premonitory phenomena of major future seismic events. A careful study of the geometric characteristics and of the kinematics of these ground fissures, however, revealed that they only reflect shear failure of the ground due to compaction of loose sediments following significant decline of the groundwater level due to over-pumping; i.e. a geotechnical and not a tectonic process. Furthermore, theoretical considerations and modeling predict surface fissuring along zones of anomalous basement, normal-fault controlled topography. This explains the correlation between ground fissures and active Quaternary normal faults.     

Spatial predictions of geological rock mass properties based on in-situ interpretations of multi-dimensional seismic data

The article presents a statistical approach to characterize and predict engineering geological conditions in the up to 2000 m deep Faido tunnel and Gotthard base tunnel in Switzerland. Seismic investigations were conducted to improve the technology of interpreting seismic tomographic images. Overall, the goal of this study was to predict spacial maps of geological rock mass properties, such as, uniaxial compressive strength or total fracture spacing, by using up to six seismic features in combination, e.g., compression-wave and shear-wave velocities and dynamic Poisson's ratio. Self-Organizing Mapping (SOM), an artificial intelligent method, was used for the purposes of interpreting multi-dimensional geophysical attributes derived from seismic profiles of tomographic images along tunnel sidewalls. The SOM-method was applied in the Faido tunnel to delineate complex physical relations between the geological and seismic parameters. Then, the method was applied to predict geological properties around a segment of the Gotthard base tunnel with unknown geological–geotechnical conditions. The results illuminate that correlation analyses (pairwise parameter classification) are substantially less powerful than the SOM-method (multi-parameter classification) in order to interpret geological features from seismic in-situ data. Moreover, predicted spatial distributions of the total fracture spacing and the uniaxial compressive strength, for example, corresponded well with drill core and tunnel mapping results. The SOM-approach was a helpful tool for practitioners in predicting zones of instabilities and geological complexity during underground excavation processes of the Gotthard base tunnel. It is suggested to use such an interpretation method as decision support for purposes of sub/surface exploration and long-term geophysical monitoring of large-scale geoengineering projects, such as, disposals of nuclear waste and greenhouse gases or geopower plants for renewable energy (geothermal, biosoils).     

Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams

In longwall development mining of coal seams, planning, optimizing and providing adequate ventilation are very important steps to eliminate the accumulation of explosive methane–air mixtures in the working environment. Mine operators usually try to supply maximum ventilation air based on the capacity of the system and the predicted need underground. This approach is neither economical nor safer as ventilation capacity may decrease in time depending on various mining and coalbed parameters. Thus, it is important to develop better engineered approaches to optimize mine ventilation effectiveness and, therefore, to ensure a safer work environment.This study presents an approach using coalbed methane reservoir modeling and an artificial neural network (ANN) design for prediction and optimization of methane inflows and ventilation air requirements to maintain methane concentrations below statutory limits. A coalbed reservoir model of a three-entry development section, which is typical of Pittsburgh Coalbed mines in the Southwestern Pennsylvania section of Northern Appalachian Basin, was developed taking into account the presence and absence of shielding boreholes around the entries against methane inflow. In the model, grids were dynamically controlled to simulate the advance of mining for parametric simulations.Development and application of artificial neural networks as an optimization tool for ventilation requirements are introduced. Model predictions are used to develop, train, and test artificial neural networks to optimize ventilation requirements. The sensitivity and applications of proposed networks for predicting simulator data are presented and discussed. Results show that reservoir simulations and integrated ANN models can be practical and powerful tools for predicting methane emissions and optimization of ventilation air requirements.     

预测工后软土地基沉降

本文简要叙述沉降观测在软土地基施工中的重要性,并提出了基于神经网络的高速公路工后沉降预测方法。结合工程实例运用MATLAB工具箱函数建立网络模型,选择合适的训练函数,使其训练精度和速度达到最优化。     

Social Network Approach to Understand the Ethnic Economy: A Theoretical Discourse<Superscript>1</Superscript>

In this paper we suggest how social network analysis, in contrast to looking at physical space, can be used to trace the social and economic location of ethnic enclaves. Taking skilled workers immigrating to Canada from China as an example, we analyze critically how split labor market theories describe materialist and structural factors that determine immigrants’ limited options. Cultural theories play up immigrants’ interest in using their cultural resources to pull themselves ahead. We propose that social network analysis as a single framework can bring together elements from materialist–structural and cultural theories. The position of people and firms in these networks gives us a view of the kinds of jobs immigrants get and the businesses they set up. To understand the ethnic economy, we discuss how networks of social and economic relations intersect each other. By seeing the ethnic economy embedded in social networks, we can provide a more general explanation of the social space of the ethnic economy in contrast to its physical location. We use three cases of ethnic entrepreneurs to illustrate how the social and economic relations locate their businesses in the enclave and how they are also linked to the mainstream economy. ¹This paper has benefitted from the critical clarifications of Chiu Luk and an anonymous reviewer, and the talented editing of Allen Sutterfield. Lynn Xu Liping helped on an earlier draft.     

Tenseurs de perméabilité équivalente d'un domaine hétérogène fini

In an earlier paper, it has been shown that for a heterogeneous block of finite size, under linear boundary pressure conditions, a symmetric and positive definite tensor, denoted here by ${\mathbf{K}}^{\mathrm{p}}$, exists, which relates the mean flux to the mean gradient of pressure in the block. In this paper, the conditions of constant boundary flux are first defined. Then it is shown that, under these conditions also, a symmetric and positive definite tensor, denoted ${\mathbf{K}}^{\mathrm{q}}$, exists, which relates the mean flux to the mean pressure gradient. It is then shown that ${\mathbf{K}}^{\mathrm{q}}$ and ${\mathbf{K}}^{\mathrm{p}}$ respectively give the equivalent permeability in the direction of mean gradient and of mean flux. The directional permeability values given by ${\mathbf{K}}^{\mathrm{q}}$ are shown to be smaller than ${\mathbf{K}}^{\mathrm{p}}$. To cite this article: A. Pouya, C. R. Geoscience 337 (2005).