顾及排序差异的对象群邻近关系相似性计算

提出一种实用性较强的地理信息语义表达及相似性度量模型,实现从地理信息语义建模到相似性度量的完整技术链条。在对地理信息语义表达的内容与尺度分析的基础上,提出地理信息语义描述的基本结构,并将其进一步细化为具有不同大小的语义粒度项,以构建出地理信息语义的细节层次（level of detail,LOD）表达模型,最后依据地理信息概念间相关语义粒度项的匹配关系实现地理信息语义相似程度的定量化计算,在实例分析中则以土地利用类型为例进行相似度计算的实验,通过实验结果与实际经验判断比较验证出该模型具有较强的实用性。     

PCA-RBF网络预测模型在水质信息预测中的应用

在分析RBF神经网络预测算法和主成分分析方法的基础上,本文针对地理空间数据的复杂相关性和较强非线性,深入研究了主成分分析与RBF神经网络结合原理,构建了PCA-RBF网络预测模型,最后将预测模型应用于水质信息预测中。实验结果表明:该模型对海量的高维异构数据可进行有效降维,从而优化RBF神经网络结构,有效地提高了地理空间数据预测时的精度,并为GIS领域地理空间数据的预测提供了一种新思路。     

Temporal data mining using genetic algorithm and neural network —A case study of air pollutant forecasts

This paper integrates genetic algorithm and neural network techniques to build new temporal predicting analysis tools for geographic information system (GIS). These new GIS tools can be readily applied in a practical and appropriate manner in spatial and temporal research to patch the gaps in GIS data mining and knowledge discovery functions. The specific achievement here is the integration of related artificial intelligent technologies into GIS software to establish a conceptual spatial and temporal analysis framework. And, by using this framework to develop an artificial intelligent spatial and temporal information analyst (ASIA) system which then is fully utilized in the existing GIS package. This study of air pollutants forecasting provides a geographical practical case to prove the rationalization and justness of the conceptual temporal analysis framework.     

Temporal Data Mining Using Genetic Algorithm and Neural Network--A Case Study of Air Pollutant Forecasts

This paper integrates genetic algorithm and neural network techniques to build new temporal predicting analysis tools for geographic information system (GIS). These new GIS tools can be readily applied in a practical and appropriate manner in spatial and temporal research to patch the gaps in GIS data mining and knowledge discovery functions. The specific achievement here is the integration of related artificial intelligent technologies into GIS software to establish a conceptual spatial and temporal analysis framework. And, by using this framework to develop an artificial intelligent spatial and temporal information analyst (ASIA) system which then is fully utilized in the existing GIS package. This study of air pollutants forecasting provides a geographical practical case to prove the rationalization and justness of the conceptual temporal analysis framework.     

关于美中基础地理信息产品及其分发模式的思考

作为当今经济和科技最发达的国家,美国在基础地理信息产品建设和分发服务方面是代表世界最先进水平的国家之一,其丰富的基础地理信息系列产品、优秀的网络分发服务系统、完善的数据共享和更新策略等都值得我们学习和借鉴。本文介绍了美国基础地理信息产品的种类、发展及其分发服务模式,并根据我国的实际情况,在相关方面提出了几点建议。     

Exploring the link between urban form and work related transportation using combined satellite image and census information: Case of the Great lakes region

Aspects of urban transportation have significant implications for resource consumption and environmental quality. The level of travel activity, the viability of various modes of transportation and hence the level of transportation-related emissions are influenced by the structure of cities, i.e., their urban forms. While it is widely recognized that satellite remote sensing can provide spatial information on urban land cover and land use, its effective use for understanding impacts of urban form on issues such as transportation requires that this information be integrated with relevant demographic information. A comprehensive bi-national urban database, the Great Lakes Urban Survey (GLUS), comprising all cities with populations in excess of 200,000 has been created from Landsat imagery and national census and transportation survey information from Canada and the United States. A suite of analysis tools are proposed to utilize information sets such as GLUS to investigate the link between urban form and work-related travel. A new indicator, the Employment Deficit Measure (EDM), is proposed to quantify the balance between employment and worker availability at different transit horizons and hence to assess the viability of alternate modes of transportation. It is argued that the high degree of residential and commercial/industrial land uses greatly impact travel to work mode options as well as commute distance. A spatial interaction model is developed and found to accurately predict travel distance aggregated at the census tract level. We argue that this model could also be used to explore the relative levels of travel activity associated with different urban forms.     

Seasonal warm-water refuge and sanctuary usage by the Florida manatee (Trichechus manatus latirostris) in Kings Bay,Citrus County,Florida

The largest Florida manatee (Trichechus manatus latirostris) aggregation at a natural warm-water site occurs in Kings Bay, Crystal River, FL. In accordance with the Manatee Recovery Plan, manatee protection areas within Kings Bay have been created by the United States Fish and Wildlife Service (USFWS) and the State of Florida including a year-round refuge designation and seven Federal manatee sanctuaries during the winter manatee season (15 November–31 March). Over the last 30 years, an increase in manatee counts has been observed in Kings Bay which has prompted the need to review existing manatee protection measures. Aerial survey data collected between 1983 and 2012 were used to examine the seasonal change in manatee distribution within Kings Bay to assess the effectiveness of current sanctuary sizes and locations. Regression analysis suggested a significant change in manatee abundance among the winter seasons (p < 0.05). The average winter manatee counts increased by 4.81 animals per year over the 30-year period. Spatially explicit maps using geographic information system (GIS) analysis revealed a strong correlation between high manatee density and artesian springs in Kings Bay during the winter seasons. Highest abundances were identified at three locations: King Spring, Three Sisters Springs, and Magnolia Springs, which coincide with preexisting sanctuary designations. Additional coverage is advocated to support the overflow of manatees outside of sanctuary boundaries. As density patterns were not uniform across summer periods, a consideration of additional boat speed regulations is recommended.     

Measures of spatio-temporal accuracy for time series land cover data

Remote sensing is a useful tool for monitoring changes in land cover over time. The accuracy of such time-series analyses has hitherto only been assessed using confusion matrices. The matrix allows global measures of user, producer and overall accuracies to be generated, but lacks consideration of any spatial aspects of accuracy. It is well known that land cover errors are typically spatially auto-correlated and can have a distinct spatial distribution. As yet little work has considered the temporal dimension and investigated the persistence or errors in both geographic and temporal dimensions. Spatio-temporal errors can have a profound impact on both change detection and on environmental monitoring and modelling activities using land cover data. This study investigated methods for describing the spatio-temporal characteristics of classification accuracy. Annual thematic maps were created using a random forest classification of MODIS data over the Jakarta metropolitan areas for the period of 2001–2013. A logistic geographically weighted model was used to estimate annual spatial measures of user, producer and overall accuracies. A principal component analysis was then used to extract summaries of the multi-temporal accuracy. The results showed how the spatial distribution of user and producer accuracy varied over space and time, and overall spatial variance was confirmed by the principal component analysis. The results indicated that areas of homogeneous land cover were mapped with relatively high accuracy and low variability, and areas of mixed land cover with the opposite characteristics. A multi-temporal spatial approach to accuracy is shown to provide more informative measures of accuracy, allowing map producers and users to evaluate time series thematic maps more comprehensively than a standard confusion matrix approach. The need to identify suitable properties for a temporal kernel are discussed.     

基于空间建模的公共安全情报分析初探

空间建模及分析作为情报分析的主要技术手段之一,在欧美等国家得到了广泛实践和应用.本文在地理信息科学的主要空间模型基础上,进行了公共安全情报分析应用的研究和实践,并应用于警用地理信息系统建设中,为我国公安机关“情报信息主导警务”提供实战参考.     

Validation of MERIS Case-2 Water Products in Lake Taihu,China

Three artificial neural network (ANN) processors available as plug-in modules for the Basic ERS & ENVISAT (A)ATSR and MERIS Toolbox (BEAM) were validated in Lake Taihu, China. Mean deviations of reflectance derived from Lakes\Boreal and Lakes\Eutrophic were 10-90%, while reflectance from the FUB-WeW processor showed larger errors. All processors showed underestimates of chlorophyll a (Chl-a), total suspended matter (TSM), and phytoplankton pigment absorption, while particulate scattering values were severely overestimated. None of the readily available MERIS processors is currently able to separate atmospheric and water-leaving radiance over Lake Taihu, while the retrieval of phytoplankton biomass through ANN processors shows promise.     

利用AI进行电子地图制作的技术探讨与应用

国家测绘地理信息局开展了地理信息公共服务平台建设,依托地理信息数据进行电子地图制作。本文介绍了利用Adobe Illustrator进行人工精编的优势,着重说明了电子地图制作流程及相关技术要求。     

A GIS-based method for defining snow zones: application to the western United States

This study maps the geographic extent of intermittent and seasonal snow cover in the western United States using thresholds of 2000–2010 average snow persistence derived from moderate resolution imaging spectroradiometer snow cover area data from 1 January to 3 July. Results show seasonal snow covers 13% of the region, and intermittent snow covers 25%. The lower elevation boundaries of intermittent and seasonal snow zones increase from north-west to south-east. Intermittent snow is primarily found where average winter land surface temperatures are above freezing, whereas seasonal snow is primarily where winter temperatures are below freezing. However, temperatures at the boundary between intermittent and seasonal snow exhibit high regional variability, with average winter seasonal snow zone temperatures above freezing in west coast mountain ranges. Snow cover extent at peak accumulation is most variable at the upper elevations of the intermittent snow zone, highlighting the sensitivity of this snow zone boundary to climate conditions.     

Mapping leafy spurge (euphorbia esula) infestations using aerial photography and geographic information systems

Abstract

Leafy spurge is a troublesome weed on the northern Great Plains of the United States that chemicals and grazing management have not controlled. Remote sensing and geographic information system (GIS) technology have been used to detect and monitor numerous grassland related problems. The objectives of this study were to use both technologies to map and quantify the extent of leafy spurge within Theodore Roosevelt National Park and to provide information for managing the infestation. Analysis of the data indicated that 702 ha of the 18,680 ha park were infested by leafy spurge; however, leafy spurge populations occurring under dense woody canopies, in deep stream channels, and on steep slopes were not always detected. Infestations were especially dense in the western and southeast portions of the park. Most infestations were restricted to riparian zones and smaller drainage channels. Leafy spurge infestations decreased exponentially as distance from stream channels increased (r²=0.98). The significant association of leafy spurge with drainage channels suggests that the weed might be effectively managed on a watershed sub‐basin level. The joint use of GIS and remote sensing proved to be a powerful combination of tools which provided previously unavailable information about the extent and spatial dynamics of leafy spurge within the park. The results of this study will contribute to the development of a comprehensive leafy spurge management plan for Theodore Roosevelt National Park (South Unit).     

事件框架的应急地理信息抽取

针对现有的通用信息抽取技术无法实现结构化的应急信息抽取和完整的地名地址识别的问题,该文提出了面向众源数据的地理信息抽取技术,采用了基于事件框架的应急信息抽取方法,利用层次模型与N-最短路径算法,解决了完整的地名地址的识别与提取的问题,较好地实现了应急地理信息的自动化抽取。通过实验的进一步分析,此方法取得了最优化的应急地理信息抽取结果。实验表明,基于事件框架的应急地理信息抽取技术不仅可以快速有效地抽取应急地理信息,还能够识别完整的地名地址。     

An iterative approach based on contextual information for matching multi‐scale polygonal object datasets

Object matching facilitates spatial data integration, updating, evaluation, and management. However, data to be matched often originate from different sources and present problems with regard to positional discrepancies and different levels of detail. To resolve these problems, this article designs an iterative matching framework that effectively combines the advantages of the contextual information and an artificial neural network. The proposed method can correctly aggregate one‐to‐many (1:N) and many‐to‐many (M:N) potential matching pairs using contextual information in the presence of positional discrepancies and a high spatial distribution density. This method iteratively detects new landmark pairs (matched pairs), based on the prior landmark pairs as references, until all landmark pairs are obtained. Our approach has been experimentally validated using two topographic datasets at 1:50 and 1:10k. It outperformed a method based on a back‐propagation neural network. The precision increased by 4.5% and the recall increased by 21.6%, respectively.     

高分辨率遥感影像智能解译研究进展与趋势

遥感影像解译是一个不断发展的研究方向,随着日新月异的遥感应用需求、高分辨率遥感数据的快速发展、地理知识的日积月累、以及人工智能技术的发展,亟需发展自动化、智能化的遥感影像解译技术。本文针对遥感影像智能解译,首先从遥感影像解译单元、分类方法、解译认知3个方面阐述遥感影像解译的研究进展,然后提出了面向地理场景的 “地理知识图谱构建—深度学习模型构建—地理知识图谱与深度学习模型协同的遥感影像语义分类”遥感影像智能解译总体框架,并给出初步试验成果,最后对智能解译的重要发展趋势予以展望,以期拓展遥感影像智能解译研究的思路与方法,提高遥感影像智能解译的精细程度和智能化水平,使智能解译具备地理空间理解能力,推动“数据—信息—知识—智能”的深度转化。     

基于GIS的马尾松毛虫灾害空间扩散规律分析

主要利用GIS的空间分析技术 ,探讨了松毛虫灾害的发生发展与地形、道路、居民地等的相关关系 ,科学地验证了松毛虫常发区的地理分布、发展过程等经验知识 ,充分肯定和展示了GIS用于松毛虫灾害定量、定位预测预报的可行性。     

AUTO-IDENTIFICATION OF FOREST FIRE-POINTS IN NOAA IMAGES BASED ON NEURAL NETWORK

1　ＩｎｔｒｏｄｕｃｔｉｏｎＴｈｅｉｄｅｎｔｉｆｉｃａｔｉｏｎｏｆｆｏｒｅｓｔｆｉｒｅ＿ｐｏｉｎｔｓｉｎＮＯＡＡｉｍａｇｅｓｉｓｔｈｅｂａｓｉｓｏｆｍｏｎｉｔｏｒｉｎｇｆｏｒｅｓｔｆｉｒｅｕｓｉｎｇＮＯＡＡｓａｔｅｌｌｉｔｅｄａｔａ .Ｔｈｅｔｒａｄｉｔｉｏｎａｌａｐｐｒｏａｃｈｏｆｉ ｄｅｎｔｉｆｉｃａｔｉｏｎｉｓｖｉｓｕａｌｉｎｔｅｒｐｒｅｔａｔｉｏｎ .Ｂｙｔｈｅｖｉｓｕａｌｉｎｔｅｒｐｒｅｔａｔｉｏｎ ,ｂｅｔｔｅｒｐｒｅｃｉｓｉｏｎｉｓｏｂｔａｉｎｅｄｉｎｐｒａｃ ｔｉｃｅ,ｂｕｔｅｘｐｅｒｉｅ…     

Auto-identification of forest fire-points in NOAA images based on neural network

Identification of forest fire-points in NOAA images in the basis of monitoring forest fire using NOAA satellite data. Traditional visual interpretation is difficult to settle for auto identification with computer. The artificial neural network technique provides a new means for solving this problem. In this paper, the principles and method of using neural network technique to automatically identify fire-points in NOAA images are discussed and the test in the range of Hubei province is presented. The result of the test shows that the disciplined neural network has collected the character of fire-points and has ability to identify fire-points in NOAA images. Comparing neural network with visual interpretation, the conclusion is drawn that by using neural network the purpose of auto-identification of forest fire-points in NOAA images can be realized with the almost same precision.