基于多参量的模拟退火全局优化傅里叶有限差分算子

傅里叶有限差分法(FFD)能够处理复杂地质构造中的波传播问题,但对陡倾角成像仍有明显的误差.优化参数的方法能够在保持计算效率的前提下进一步提高陡倾角的成像精度.本文在有理近似的基础上,将FFD算子展开式中的常系数由两个拓展为四个,然后采用模拟退火算法对这四个参数进行全局优化.本方法除了考虑速度对比度以外,还考虑了频率和延拓步长等参量的影响.理论误差分析和脉冲响应测试均表明该方法能极大地提高FFD算子的精确传播角度.二维SEG/EAGE盐丘模型实验表明本文方法对陡倾角以及盐下构造的成像精度明显高于未优化的FFD法.将本文的方法与交替方向加插值的方法结合应用于三维脉冲响应测试更进一步证实了本文方法的有效性.     

FLU-net：用于表征页岩储层微观孔隙的深度全卷积网络

页岩孔隙是页岩气储集的主要空间,孔隙的形状、大小、连通性与发育程度很大程度上决定了页岩储集层的储集性能,因此,页岩气开采首先需要对其孔隙有充分的认识。基于阈值分割法获取页岩孔隙结构参数是目前页岩微观结构表征的一种重要手段,但是受扫描电镜图像灰度分布差异的影响,该方法需要逐一修改图像的最佳分割阈值以达到最好的孔隙分割效果,且阈值分割方法无法直接划分孔隙类别,这给后续的页岩微观结构定量表征带来了麻烦。为了实现页岩孔隙的智能识别和分类,笔者设计基于像素级语义分割的深度全卷积神经网络FLU-net,对页岩孔隙识别并分类为有机孔、无机孔（粒内孔、粒间孔）及裂缝,并结合孔隙尺度分类统计方法,分析不同类型孔隙发育数量、孔径大小、孔隙度等参数,实现页岩储层微观孔隙结构的自动化定量表征。以重庆渝西区块足201井区和四川盆地威远地区威204井区的页岩扫描电镜图像为研究对象,在对1 600幅页岩扫描电镜图像原始数据进行人工标注并划分数据集后,使用FLU-net进行孔隙识别,结果表明,本方法具有较高的准确率,同时自动化程度和泛化能力均高于传统预测方法。因此,扫描电镜与基于深度学习的语义分割模型结合是定量研究页岩微观结构表征的有效手段。     

Estimation of suspended sediment concentration in the Saint John River using rating curves and a machine learning approach

ABSTRACT

Sedimentation in navigable waterways and harbours is of concern for many water and port managers. One potential source of variability in sedimentation is the annual sediment load of the river that empties in the harbour. The main objective of this study was to use some of the regularly monitored hydro-meteorological variables to compare estimates of hourly suspended sediment concentration in the Saint John River using a sediment rating curve and a model tree (M5?) with different combinations of predictors. Estimated suspended sediment concentrations were multiplied by measured flows to estimate suspended sediment loads. Best results were obtained using M5? with four predictors, returning an R² of 0.72 on calibration data and an R² of 0.46 on validation data. Total load was underestimated by 1.41% for the calibration period and overestimated by 2.38% for the validation period. Overall, the model tree approach is suggested for its relative ease of implementation and constant performance.

EDITOR M.C. Acreman; ASSOCIATE EDITOR B. Touaibia     

A brief catalogue of failures: Framing evaluation and learning in fisheries resource management

We propose a framework for enabling a systematic evaluation of a fisheries resource management system, which we define as a feed-back mechanism coupled to a fishery. The resource management system includes four basic functions: diagnostics, intervention, goal setting, and decision making. This model allows for the development of an evaluation framework for fisheries resource management by facilitating a typology of failures. We suggest that the potential for systemic and interdisciplinary learning will be significantly enhanced through the process of developing such a framework.     

基于光谱—空间特征的ASTER影像岩性分类研究——以甘肃北山白峡尼山地区为例

遥感岩性制图是地质填图中的重要工作,基于光谱特征的岩性分类易受到色调、纹理等因素影响导致精度不佳。前人进行岩性自动分类研究多关注影像的光谱特征,而忽略空间特征,笔者等基于甘肃北山白峡尼山地区ASTER影像,将支持向量机、极限学习机两种机器学习分类方法与基于空间特征的快速漂移算法相结合进行岩性分类。结果表明支持向量机分类总体精度为89.17%;极限学习机不但具有需调节参数少的优势,且分类精度和速度均优于支持向量机,分类总体精度达96.70%;利用快速漂移算法提取的影像空间特征可有效减少错分区,提升岩性分类效果。研究证实将基于光谱特征的极限学习机和基于空间特征的快速漂移算法结合的岩性分类方法具有客观、高效、高精度等优势,可为后续地质填图和找矿勘查工作提供可靠数据支撑,在遥感岩性分类领域具有较高的推广价值。     

集聚经济影响城市经济增长的理论基础与实证研究:文献述评与展望

集聚经济理论自诞生之日起便与城市经济增长存在着本源联系。论文系统梳理集聚经济理论的起源与发展,归纳集聚经济阐释城市空间形成与发展的核心思想,明确集聚经济与城市经济增长之间是具有本源联系的。进一步回顾集聚经济影响城市经济增长的程度与机制,发现以人口密度等指标为代表的集聚经济能够显著促进城市经济的增长,可从“宏观过程”与“微观过程”两大视角探寻城市集聚经济影响城市经济增长的解释机制。这一工作不仅是以往集聚经济与城市经济增长相关文献回顾的一个延续,也为后续集聚经济影响中国城市经济增长的实证研究提供了一个参照。     

A Review of: “Applications of Spatial Data Structures: Computer Graphics,Image Processing,and GIS”. By H. SAMET. (Addison-Wesley Publishing Company,Inc, 1989.) [Pp. xv + 507; figures,tables, appendix,references, name and credit index,subject index.] Price US $49.95. ISBN 020150300 X (hardback).

The introduction of automated generalisation procedures in map production systems requires that generalisation systems are capable of processing large amounts of map data in acceptable time and that cartographic quality is similar to traditional map products. With respect to these requirements, we examine two complementary approaches that should improve generalisation systems currently in use by national topographic mapping agencies. Our focus is particularly on self‐evaluating systems, taking as an example those systems that build on the multi‐agent paradigm. The first approach aims to improve the cartographic quality by utilising cartographic expert knowledge relating to spatial context. More specifically, we introduce expert rules for the selection of generalisation operations based on a classification of buildings into five urban structure types, including inner city, urban, suburban, rural, and industrial and commercial areas. The second approach aims to utilise machine learning techniques to extract heuristics that allow us to reduce the search space and hence the time in which a good cartographical solution is reached. Both approaches are tested individually and in combination for the generalisation of buildings from map scale 1:5000 to the target map scale of 1:25 000. Our experiments show improvements in terms of efficiency and effectiveness. We provide evidence that both approaches complement each other and that a combination of expert and machine learnt rules give better results than the individual approaches. Both approaches are sufficiently general to be applicable to other forms of self‐evaluating, constraint‐based systems than multi‐agent systems, and to other feature classes than buildings. Problems have been identified resulting from difficulties to formalise cartographic quality by means of constraints for the control of the generalisation process.     

Co-management and the co-production of knowledge: Learning to adapt in Canada's Arctic

Co-management institutional arrangements have an important role in creating conditions for social learning and adaptation in a rapidly changing Arctic environment, although how that works in practice has not been clearly articulated. This paper draws on three co-management cases from the Canadian Arctic to examine the role of knowledge co-production as an institutional trigger or mechanism to enable learning and adapting. Experience with knowledge co-production across the three cases is variable but outcomes illustrate how co-management actors are learning to learn through uncertainty and environmental change, or learning to be adaptive. Policy implications of this analysis are highlighted and include the importance of a long-term commitment to institution building, an enabling policy environment to sustain difficult social processes associated with knowledge co-production, and the value of diverse modes of communication, deliberation and social interaction.     

Assessing the performance of two unsupervised dimensionality reduction techniques on hyperspectral APEX data for high resolution urban land-cover mapping

Despite the high richness of information content provided by airborne hyperspectral data, detailed urban land-cover mapping is still a challenging task. An important topic in hyperspectral remote sensing is the issue of high dimensionality, which is commonly addressed by dimensionality reduction techniques. While many studies focus on methodological developments in data reduction, less attention is paid to the assessment of the proposed methods in detailed urban hyperspectral land-cover mapping, using state-of-the-art image classification approaches. In this study we evaluate the potential of two unsupervised data reduction techniques, the Autoassociative Neural Network (AANN) and the BandClust method – the first a transformation based approach, the second a feature-selection based approach – for mapping of urban land cover at a high level of thematic detail, using an APEX 288-band hyperspectral dataset. Both methods were tested in combination with four state-of-the-art machine learning classifiers: Random Forest (RF), AdaBoost (ADB), the multiple layer perceptron (MLP), and support vector machines (SVM). When used in combination with a strong learner (MLP, SVM) BandClust produces classification accuracies similar to or higher than obtained with the full dataset, demonstrating the method’s capability of preserving critical spectral information, required for the classifier to successfully distinguish between the 22 urban land-cover classes defined in this study. In the AANN data reduction process, on the other hand, important spectral information seems to be compromised or lost, resulting in lower accuracies for three of the four classifiers tested. Detailed analysis of accuracies at class level confirms the superiority of the SVM/Bandclust combination for accurate urban land-cover mapping using a reduced hyperspectral dataset. This study also demonstrates the potential of the new APEX sensor data for detailed mapping of land cover in spatially and spectrally complex urban areas.