空间层次聚类显著性判别的重排检验方法

同时顾及空间邻近与专题属性相似的空间层次聚类是挖掘空间分布模式的一种有效手段。空间层次聚类方法虽然可以获得多层次的聚集结构,但聚类结果显著性的统计判别依然是一个尚未解决的难题。为此,本文提出了一种空间层次聚类结果显著性的统计判别方法,用于确定空间层次聚类的停止准则,减少聚类过程对参数设置的依赖。通过试验分析与比较发现,该方法能够有效判别空间层次聚类结果的显著性和确定层次聚类合并过程的停止条件,同时具有很好的抗噪性,避免随机结构的干扰。     

Grid pattern recognition in road networks using the C4.5 algorithm

Pattern recognition in road networks can be used for different applications, including spatiotemporal data mining, automated map generalization, data matching of different levels of detail, and other important research topics. Grid patterns are a common pattern type. This paper proposes and implements a method for grid pattern recognition based on the idea of mesh classification through a supervised learning process. To train the classifier, training datasets are selected from worldwide city samples with different cultural, historical, and geographical environments. Meshes are subsequently labeled as composing or noncomposing grids by participants in an experiment, and the mesh measures are defined while accounting for the mesh’s individual characteristics and spatial context. The classifier is generated using the C4.5 algorithm. The accuracy of the classifier is evaluated using Kappa statistics and the overall rate of correctness. The average Kappa value is approximately 0.74, which corresponds to a total accuracy of 87.5%. Additionally, the rationality of the classifier is evaluated in an interpretation step. Two other existing grid pattern recognition methods were also tested on the datasets, and comparison results indicate that our approach is effective in identifying grid patterns in road networks.     

红层软岩边坡生态防护技术探讨

红层软岩边坡,土质贫瘠,浅层稳定性差,生态防护失效的现象比较突出。为提高西部红层软岩边坡生态防护的可靠性,在对西部红层软岩地区铁路、公路边坡生态防护状况进行调研和分析的基础上,总结红层软岩边坡生态防护失败的原因,吸取经验教训,提出适于红层软岩边坡的生态防护方法和适合该区栽植的草木品种及配置方法。     

基于克里格法刻画砂岩型铀矿U、Ra和U-Ra平衡系数垂向分布规律——以二连盆地芒来铀矿床为例

砂岩型铀矿是绿色经济可采的重要能源矿种,目前是世界上重要的铀矿勘探类型之一。二连盆地芒来铀矿床、鄂尔多斯盆地纳岭沟铀矿床铀矿体多呈板状产出,板状铀矿体成因备受关注。为研究砂岩型铀矿内部U、Ra和铀镭平衡系数（Kp）分布的垂向分布规律,本文以二连盆地芒来铀矿床为例,采用具有网格精度高优点的克里格插值法研究U、Ra和Kp垂向分布规律,分别利用放射性样品分析数据和定量伽马测井五点式反褶积法反演U含量数据,通过克里格法精细刻画砂岩型矿体中U、Ra和Kp分布的垂向分布规律。研究发现,该矿床板状矿体内部具有卷状的特征,Kp分布形态可以用来判断含氧含铀水的运移方向以及氧化强弱。该方法对研究铀矿体形态、铀矿成矿规律和后续地浸开采具有重要意义。     

A case study on Landscape Component Niche based on Landscape Pattern Indices: Yanchi,Ningxia Province,China

Yanchi County is located in the agro-pastoral ecotone and belongs to the ecologically fragile area of Northwest China.It is important to study the evolution of landscape pattern to curb its environmental degradation.In order to intuitively show how the landscape pattern of the study area changes over time,Landsat Thematic Mappers(TM)and Landsat Operational Land Imager(OLI)data of 1991,2000,2010 and 2017 were used.This paper attempts to apply niche theories and methods into landscape ecology,and constructs a niche model of landscape components by using"n-dimentional hypervolume niche theory"and landscape pattern indices.By evaluating the spatial and temporal evolution of niche from the perspective of two-dimensional space to reflect the changes of landscape pattern in the study area over the past 26 years,new theories and methods were introduced for the characterization of landscape pattern.The results indicate that:1)The larger the attribute and dominance value of landscape components,the higher the ecological niche and the stronger the control effect on the overall landscape.2)The ecological niche of each landscape component was significantly different,just as its control effect on the overall landscape.3)The dynamic change of the ecological niche of each landscape component was different,with grassland,unused land and arable land always in a high dominant position,although the ecological niche of construction land and water area was always low.In general,the introduction of niche theory into the landscape ecology provided a new method to study the changes in regional landscape pattern.     

厦门下潭尾红树林修复区景观类型与鸟类群落动态

2018年10月—2019年9月调查厦门下潭尾红树林修复区鸟类群落变化,利用遥感图像解译红树林修复区景观格局,为修复区后续景观格局优化与鸟类保护提供技术支持。结果显示:修复区鸟类共有26科62种,鹭类(8种2047只)与鸻鹬类(16种786只)种类及数量较多。春季鸟类种数及数量最多,其中3月鸟类种数最多25种,5月数量最多828只。下潭尾修复区景观格局在低潮位与高潮位存在周期性变化,不同景观鸟类种类及数量有较大差异;鸻鹬类在低潮位时的种类较多但数量较少,高潮位时仅分布于高潮裸露湿地和建设用地。建议修复区增加鸻鹬类高潮停息的滩涂湿地及游禽类生活需要的生态塘区,进一步提高水鸟多样性。     

自组织竞争神经网络在江苏油田有杆抽油系统故障诊断中的应用

有杆抽油系统的故障诊断技术是国内外采油工程技术中的一个重要研究课题。通过示功图的不同形状特征可以反映抽油机的不同工作状态。将自组织竞争神经网络应用于示功图的识别与分类,建立了一个自组织竞争神经网络模型对示功图进行自动聚类,从而实现故障诊断的自动化。应用江苏油田的实测示功图数据进行实验,可以看出自组织竞争神经网络具有良好的分类能力和泛化性能,是实现油田抽油系统故障诊断的有效技术,具有很强的实用价值和广泛的应用前景。     

辽宁省城市人居环境系统耦合协调度时空格局演变及驱动力研究

人居环境系统内部的耦合协调是保证人居环境均衡发展的基础。基于“人类-居住-支撑-自然-社会”5个子系统,构建人居环境系统耦合协调发展评价指标体系,将2个系统间的容量耦合模型扩展运用到人居环境5个子系统中,综合熵值法、GIS空间分析以及地理探测器对辽宁省2005~2016年人居环境系统耦合协调度的时空演化特征与驱动力进行探讨,阐述人居环境系统内部协调性。研究表明:①2005~2016年辽宁省人居环境系统内部的耦合度与耦合协调度整体呈缓慢浮动上升趋势;②辽宁省人居环境耦合协调度呈分散格局,并且呈现从中间向两侧递减的“屋脊”式格局和“双核结构”;东西方向上,空间演变趋势由倒U型逐渐向一字型演变,南北方向上由斜线型向“L”型演变。③全省出现了中耦合低协调区、中耦合过渡协调区、高耦合低协调区、高耦合过渡协调区、高耦合高协调区5种类型区。④空间分异驱动力主要包括人的需求、经济发展、住房、互联网发展等。     

苹果手机零部件全球价值链的价值分配与中国角色演变

产品内分工已成为支配当代企业分工与产品生产的重要模式。研究智能手机生产网络价值分配格局,对辨析中国大陆企业在移动通讯产业价值链中所处地位与演进具有重要意义。论文利用2012—2017年苹果公司供应商数据,以其零部件价值含量与技术要求为测度标准,分析了苹果手机零部件全球价值链的分配特征以及中国大陆企业在其中的地位变化。发现：高价值环节的供应商主要以美国、日本、韩国为主,而中低价值环节则以中国台湾、日本和中国大陆供应商为主,且中国大陆与中国台湾在中间环节占据重要地位。处于价值链高端的供应商分支数量在中国大陆和美国缩减明显,日本、韩国较为稳定,中国台湾增加明显。在价值链的中低端环节,供应商分支趋向中国大陆集中。印度、巴西以及越南等地成为新的中低端价值环节转移承接地。近年来,中国大陆在苹果手机价值链的高端环节得到了提升,长三角、珠三角、京津冀、成渝、中原地区等地逐渐形成了苹果供应商分支的集聚区域,呈现出零部件生产的区域分工特征。长三角(上海-苏州为核心)与珠三角(深圳-东莞为核心),承接了价值链多个生产环节,是中国大陆嵌入苹果手机生产网络的主要阵地。成渝地区既承接了芯片类企业布局,也承接了价值链低端的组装代工和包装服务环节,呈现出在价值链两端双向承接的特征。环渤海、福建及湖南等地主要承接苹果手机价值链的中间环节,而中原地区主要以苹果手机组装与包装服务为主,承接价值链的低端环节。最后,论文从创新驱动、政府作用与外资等方面探讨了影响中国大陆地位提升的因素。     

A high-precision heuristic model to detect home and work locations from smart card data

Smart card-automated fare collection systems now routinely record large volumes of data comprising the origins and destinations of travelers. Processing and analyzing these data open new opportunities in urban modeling and travel behavior research. This study seeks to develop an accurate framework for the study of urban mobility from smart card data by developing a heuristic primary location model to identify the home and work locations. The model uses journey counts as an indicator of usage regularity, visit-frequency to identify activity locations for regular commuters, and stay-time for the classification of work and home locations and activities. London is taken as a case study, and the model results were validated against survey data from the London Travel Demand Survey and volunteer survey. Results demonstrate that the proposed model is able to detect meaningful home and work places with high precision. This study offers a new and cost-effective approach to travel behavior and demand research.