道路网增量更新中拓扑冲突的检测方法

为提高空间数据增量更新中拓扑冲突的检测效率,针对道路网数据,首先分析了增量要素进行更新时可能产生的拓扑冲突的类型和特点,运用规则格网进行邻近区域的表达;然后使用5元组模型描述增量要素与邻近区域要素间的拓扑关系,与设定的拓扑冲突表达进行比较,判断是否存在拓扑冲突。实验结果表明,本方法对于道路网数据增量更新中的拓扑冲突的类型区分准确全面,检测效率较高,具有很好的实用性和可靠性。     

Using neural networks for the derivation of Runge-Kutta-Nyström pairs for integration of orbits

In this paper we present Runge-Kutta-Nyström (RKN) pairs of orders 4(3) and 6(4). We choose a test orbit from the Kepler problem to integrate for a specific tolerance. Then we train the free parameters of the above RKN4(3) and RKN6(4) families to perform optimally. For that we form a neural network approach and minimize its objective function using a differential evolution optimization technique. Finally we observe that the produced pairs outperform standard pairs from the literature for Pleiades orbits and Kepler problem over a wide range of eccentricities and tolerances.     

Automated Prediction of CMEs Using Machine Learning of CME – Flare Associations

Machine-learning algorithms are applied to explore the relation between significant flares and their associated CMEs. The NGDC flares catalogue and the SOHO/LASCO CME catalogue are processed to associate X and M-class flares with CMEs based on timing information. Automated systems are created to process and associate years of flare and CME data, which are later arranged in numerical-training vectors and fed to machine-learning algorithms to extract the embedded knowledge and provide learning rules that can be used for the automated prediction of CMEs. Properties representing the intensity, flare duration, and duration of decline and duration of growth are extracted from all the associated (A) and not-associated (NA) flares and converted to a numerical format that is suitable for machine-learning use. The machine-learning algorithms Cascade Correlation Neural Networks (CCNN) and Support Vector Machines (SVM) are used and compared in our work. The machine-learning systems predict, from the input of a flare’s properties, if the flare is likely to initiate a CME. Intensive experiments using Jack-knife techniques are carried out and the relationships between flare properties and CMEs are investigated using the results. The predictive performance of SVM and CCNN is analysed and recommendations for enhancing the performance are provided.     

Configurations of community in flood risk management

ABSTRACT

Despite a notable increase in the literature on community resilience, the notion of ‘community’ remains underproblematised. This is evident within flood risk management (FRM) literature, in which the understanding and roles of communities may be acknowledged but seldom discussed in any detail. The purpose of the article is to demonstrate how community networks are configured by different actors, whose roles and responsibilities span spatial scales within the context of FRM. Accordingly, the authors analyse findings from semi-structured interviews, policy documents, and household surveys from two flood prone areas in Finnish Lapland. The analysis reveals that the ways in which authorities, civil society, and informal actors take on multiple roles are intertwined and form different types of networks. By implication, the configuration of community is fuzzy, elusive and situated, and not confined to a fixed spatiality. The authors discuss the implications of the complex nature of community for FRM specifically, and for community resilience more broadly. They conclude that an analysis of different actors across scales contributes to an understanding of the configuration of community, including community resilience, and how the meaning of community takes shape according to the differing aims of FRM in combination with differing geographical settings.     

Chloride source delineation in an urban-agricultural watershed: Deicing agents versus agricultural contributions

Analyses (n = 525) of chloride (Cl⁻), bromide (Br⁻), nitrate as nitrogen (NO₃-N), sodium (Na⁺), calcium (Ca²⁺) and potassium (K⁺) in stream water, tile-drain water and groundwater were conducted in an urban-agricultural watershed (10% urban/impervious, 87% agriculture) to explore potential differences in the signature of Cl⁻ originating from an urban source as compared with an agricultural source. Only during winter recharge events did measured Cl⁻ concentrations exceed the 230 mg/L chronic threshold. At base flow, nearly all surface water and tile water samples had Cl⁻ concentrations above the calculated background threshold of 18 mg/L. Mann–Whitney U tests revealed ratios of Cl⁻ to Br⁻ (p = .045), to NO₃-N (p < .0001), to Ca²⁺ (p < .0001), and to Na⁺ (p < .0001) to be significantly different between urban and agricultural waters. While Cl⁻ ratios indicate that road salt was the dominant source of Cl⁻ in the watershed, potassium chloride fertilizer contributed as an important secondary source. Deicing in watersheds where urban land use is minimal had a profound impact on Cl⁻ dynamics; however, agricultural practices contributed Cl⁻ year-round, elevating stream base flow Cl⁻ concentrations above the background level.     

多尺度视角下中国新能源汽车产业创新空间格局及网络特征

创新活动与创新网络的多尺度空间模式是创新经济地理学关注的焦点。论文选择在知识分类上兼具隐性和显性知识特征的新能源汽车产业作为研究对象,利用来自国家知识产权局的相关专利数据,分析了2001—2015年中国新能源汽车产业独立创新活动和合作创新网络在“区域—省域—市域”的多尺度空间特征,并对其进行空间分类。结果显示：① 创新活动在城市层面最具解释力度,中国新能源汽车产业技术创新活动主要集中在东部和北部沿海地区,市域尺度上的创新活动存在较大差异;② 内部创新网络和外部创新网络在区域层面最具解释力度,创新网络集中在东部和北部沿海地区,市域尺度上的创新网络变异明显;③ 在不同尺度上,创新网络与创新活动之间存在不同程度的差异。地方创新环境与创新主体性质是造成上述格局差异的重要原因。仅停留在空间上的分析很难深入解释创新网络格局,应从更微观的创新主体层面探究创新结网的过程和机理。此外,创新活动和创新网络分别具有“多尺度结构性嵌套”和“多尺度能动性交换”特征,未来研究应对两者之间的差别给予更多关注。     

基于粒子滤波的行车轨迹路网匹配方法

行车轨迹是一种时间序列的地理空间位置采样数据,而传统的轨迹—路网匹配方法主要以全局或局部寻优的方式建立轨迹—路网匹配关系,影响了时空场景中数据的匹配计算过程的相对独立性。针对这个问题,本文基于粒子滤波（Particle Filter,PF）原理建立行车轨迹与道路网络之间的匹配关系。首先,沿轨迹中车辆运动方向在道路网络中搜索邻近道路节点,在与道路节点拓扑邻接的道路弧段上初始化随机生成粒子,根据轨迹中车辆运动模型将粒子沿所在道路弧段移动;然后,基于PF原理计算各时刻粒子运动状态及与行车轨迹采样点之间的距离误差,根据高斯概率密度函数计算粒子权重并利用随机重采样方法进行粒子重采样,迭代更新粒子运动状态;最后,计算与搜索到的道路节点拓扑邻接的每条道路弧段中累计粒子权重,通过各道路弧段累计权重计算轨迹—路网匹配关系。以行车轨迹进行实验表明,利用本文方法可以通过粒子时空变化反映采样点的移动,行车轨迹—路网匹配结果的正确率大于85%,能够实现行车轨迹和路网的准确匹配。     

基于语义规则的高分辨率影像道路交叉口提取方法

为了准确提取遥感影像上道路交叉口目标,提出一种利用特征语义规则从高分辨率影像上提取道路交叉口的方法。该算法构建交叉口模型时将其视为由同质区域像素集合及区域轮廓边界构成的面对象,提取过程分为两步:1)利用辐射、纹理特征语义匹配提取交叉口候选区域;2)通过几何特征语义匹配筛选候选区域、识别交叉口属性。利用多源遥感影像对算法正确性及合理性进行验证,结果表明:算法能准确、完整地提取道路交叉口,可为影像道路网构建提供辅助信息。     

A Comparative Study of Various Supervised Learning Approaches to Selective Omission in a Road Network

Selective omission is necessary for road network generalisation. This study investigates the use of supervised learning approaches for selective omission in a road network. To be specific, at first, the properties to measure the importance of a road in the network are viewed as input attributes, and the decision of such a road is retained or not at a specific scale is viewed as an output class; then, a number of samples with known input and output are used to train a classifier; finally, this classifier can be used to determine whether other roads to be retained or not. In this study, a total of nine supervised learning approaches, i.e., ID3, C4·5, CRT, Random Tree, support vector machine (SVM), naive Bayes (NB), K-nearest neighbour (KNN), multilayer perception (MP) and binary logistic regression (BLR), are applied to three road networks for selective omission. The performances of these approaches are evaluated by both quantitative assessment and visual inception. Results show that: (1) in most cases, these approaches are effective and their classification accuracy is between 70% and 90%; (2) most of these approaches have similar performances, and they do not have any statistically significant difference; (3) but sometimes, ID3 and BLR performs significantly better than NB and SVM; NB and KNN perform significantly worse than MP, SVM and BLR.     

基于蚁群算法的道路选取模型研究

在制图综合中,道路选取是非常重要的内容之一,研究道路选取的智能化方法是非常必要的。文中在研究道路语义、几何特征、拓扑关系和结构特征的基础上,充分考虑居民点对道路选取过程的影响,建立道路选取的蚁群算法模型。通过实验证明该模型算法的可行性和有效性。