径向基函数神经网络的路网自动匹配算法

针对VGI数据中检测更新的问题,该文提出基于径向基函数的神经网络自动匹配算法。通过选取路段的距离、方向、形状和长度4个空间特征的相似度作为衡量路段是否匹配的指标。考虑到4个空间特征指标对匹配的影响力不同,在RBF(radial basis function)神经网络中的隐含层对基函数引入粒度拉伸因子,使径向对称的RBF顾及各向异性。同时对输出层在线性加权求和函数的基础上引入sigmoid函数,使计算结果(路段的匹配度值)归一化。该算法对数据质量较差的VGI路网具有很好的匹配能力,与BP神经网络相比,RBF神经网络在地图匹配中具有更好的匹配效率。     

Completeness of citizen science biodiversity data from a volunteered geographic information perspective

Observations of living organisms by citizen scientists that are reported to online portals are a valuable source of information. They are also a special kind of volunteered geographic information (VGI). VGI data have issues of completeness, which arise from biases caused by the opportunistic nature of the data collection process. We examined the completeness of bird species represented in citizen science observation data from eBird and iNaturalist in US National Parks (NPs). We used approaches for completeness estimation which were developed for data from OpenStreetMap, a crowdsourced map of the world. First, we used an extrinsic approach, comparing species lists from citizen science data with National Park Service lists. Second, we examined two intrinsic approaches using total observation numbers in NPs and the development of the number of new species being added to the data-set over time. Results from the extrinsic approach provided appropriate completeness estimations to evaluate the intrinsic approaches. We found that total observation numbers are a good estimator of species completeness of citizen science data from US NPs. There is also a close relationship between species completeness and the ratio of new species added to observation data vs. observation numbers in a given year.     

Assessing Resistance to Volunteered Geographic Information Reporting within Local Government

Using volunteered geographic information (VGI) as a cost‐saving environmental monitoring and public participation mechanism has been thought to be a proof of concept to assist environmental decision‐making with insufficient managerial resources. However, research literature also often found institutional resistance when implementing VGI as part of the decision‐making process. This research develops a conceptual framework as the foundation to conduct a cross‐case comparison for four empirical cases in recreation and invasive species monitoring, but general enough for other such case comparisons. The VGI Reporting Assessment Framework (VGI‐RAF) adopted aspects of the Decision Situation Assessment (DSA) framework as the foundation to address institutional flexibility, stakeholder dynamics, and technical considerations. Using a cross‐case comparison can accumulate deep observations from cases and increase validity of insights through comparing processes. Results show that eight aspects of the VGI‐RAF reveal the suitability of embedding voluntary information within existing institutional decision‐making processes. VGI‐RAF depicts considerations for: (1) existing participation arrangements, (2) institutional arrangements, (3) managers’ needs and stakeholder expectation, and (4) interaction mechanism and technical needs. The cross‐comparison results indicate that a public participation mechanism should be accompanied by VGI development to increase effectiveness. Institutional arrangements should match local government's information needs with participants’ expectations. Knowledge gaps between institutional information needs and volunteer knowledge should be filled through technology enhancements. For ease of implementation and to promote long‐term success, we recommend that volunteered information be connected with existing communication channels to minimize changes to existing information systems.     

Improvement of a location-aware recommender system using volunteered geographic information

Abstract

Recommender systems (RS), as supportive tools, filter information from a massive amount of data based on the determined preferences. Most of the RS require information about the context of users such as their locations. In such cases, location-aware recommender systems (LARS) can be employed to suggest more personalized items to the users. The most current research projects on LARS focus on the development of algorithms, evaluation methods and applications. However, the role of up-to-date spatial databases in LARS is not a well-researched area. The up-to-date spatial information would potentially improve the accuracy of items which are recommended by LARS. Volunteered geographic information (VGI) could be a low-cost source of up-to-date spatial information for LARS. This article proposes an approach to enrich spatial databases of LARS by VGI. Since not all records of VGI are fitted for use in LARS, a mechanism is developed to identify useful information. Some VGI data sets refer to existing spatial data in the database while other VGI data sets are shared for the first time. Therefore, the proposed method assessed the quality of VGI with reference source (for VGI which is existed in the database) and VGI without reference source (for VGI which is shared for the first time). To demonstrate the feasibility of the proposed approach, a mobile application has been developed to recommend suitable restaurants to the users based on their geospatial locations. The evaluation of the method indicates that VGI can potentially enhance the functionality of the LARS in predicting the users’ interests.     

Automated extraction of hydrographically corrected contours for the conterminous United States: the US Geological Survey US Topo product

The US Topo is a new generation of digital topographic maps delivered by the US Geological Survey (USGS). These maps include contours in the traditional 7.5-min quadrangle format. The process for producing digital elevation contours has evolved over several years, but automated production of contours for the US Topo product began in 2010. This process, which is quite complex yet fairly elegant, automatically chooses the proper USGS quadrangle, captures the corresponding 1/3 as grid points from the national elevation data set (3D Elevation Program), and adjusts elevation data to better fit water features from the National Hydrography Dataset. After additional processing, such as identifying and tagging depressions, constructing proper contours across double-line streams, and omitting contours from water bodies, contours are automatically produced for the quadrangle. The resulting contours are then compared to the contours on the original (legacy) topographic map sheets, or to the 10-m contours from the original map sheets. Where the elevation surface used to generate the contours has been derived from the previously published contours for a quadrangle, the generated contours match the legacy contours quite well. Where newer elevation sources, such as lidar, originate the elevation surface, generated contours may vary significantly from the previous cartographically produced contours due to more accurate representations of the surface, and less reliance on cartographic interpretation.     

The Scale of VGI in Map Production: A Perspective on European National Mapping Agencies

The perspective of European National Mapping Agencies (NMA) on the role of citizen sensing in map production was explored. The NMAs varied greatly in their engagement with the community generating volunteered geographic information (VGI) and in their future plans. From an assessment of NMA standard practices, it was evident that much VGI was acquired with a positional accuracy that, while less than that typically acquired by NMAs, actually exceeded the requirements of the nominal data capture scale used by most NMAs. Opportunities for VGI use in map revision and updating were evident, especially for agencies that use a continuous rather than cyclical updating policy. Some NMAs had also developed systems to engage with citizen sensors and examples are discussed. Only rarely was VGI used to collect data on features beyond the standard set used by the NMAs. The potential role of citizen sensing and so its current scale of use by NMAs is limited by a series of concerns, notably relating to issues of data quality, the nature and motivation of the contributors, legal issues, the sustainability of data source, and employment fears of NMA staff. Possible priorities for future research and development are identified to help ensure that the potential of VGI in mapping is realized.     

Assessing quality of volunteer crowdsourcing contributions: lessons from the Cropland Capture game

Volunteered geographic information (VGI) is the assembly of spatial information based on public input. While VGI has proliferated in recent years, assessing the quality of volunteer-contributed data has proven challenging, leading some to question the efficiency of such programs. In this paper, we compare several quality metrics for individual volunteers’ contributions. The data were the product of the ‘Cropland Capture’ game, in which several thousand volunteers assessed 165,000 images for the presence of cropland over the course of 6 months. We compared agreement between volunteer ratings and an image's majority classification with volunteer self-agreement on repeated images and expert evaluations. We also examined the impact of experience and learning on performance. Volunteer self-agreement was nearly always higher than agreement with majority classifications, and much greater than agreement with expert validations although these metrics were all positively correlated. Volunteer quality showed a broad trend toward improvement with experience, but the highest accuracies were achieved by a handful of moderately active contributors, not the most active volunteers. Our results emphasize the importance of a universal set of expert-validated tasks as a gold standard for evaluating VGI quality.     

Obituary

Abstract

title/>

In the area of volunteered geographical information (VGI), the issue of spatial data quality is a clear challenge. The data that are contributed to VGI projects do not comply with standard spatial data quality assurance procedures, and the contributors operate without central coordination and strict data collection frameworks. However, similar to the area of open source software development, it is suggested that the data hold an intrinsic quality assurance measure through the analysis of the number of contributors who have worked on a given spatial unit. The assumption that as the number of contributors increases so does the quality is known as ‘Linus’ Law’ within the open source community. This paper describes three studies that were carried out to evaluate this hypothesis for VGI using the OpenStreetMap dataset, showing that this rule indeed applies in the case of positional accuracy.     

地理信息志愿者信誉度评估的版本相似度模型——以面目标为例

针对自发地理信息中存在大量恶意、虚假、低质量数据,提出了一种基于版本相似度的VGI志愿者信誉度计算模型。该模型将每个志愿者对某个地理空间目标的一次编辑结果定义为一个版本,当其他用户编辑该目标版本时,通过计算版本相似度来获得其他用户对该志愿者这个目标版本的支持度;然后通过计算其他贡献者对某志愿者所贡献的每个目标的支持度,对所有目标的支持度进行加权平均获得该志愿者的综合信誉度。其中版本相似度综合目标空间和属性相似性的主要因素进行加权计算。然后以面目标为例阐述了本文志愿者信誉度计算过程。为了验证本文信誉度计算模型的合理性,笔者采用德国柏林OpenStreetMap数据进行试验,试验表明通过本文模型计算获得的用户信誉度与其贡献的要素质量总体上正相关。     

Matching authority and VGI road networks using an extended node-based matching algorithm

The amount of volunteered geographic information (VGI) has increased over the past decade, and several studies have been conducted to evaluate the quality of VGI data. In this study, we evaluate the completeness of the road network in the VGI data set OpenStreetMap (OSM). The evaluation is based on an accurate and efficient network-matching algorithm. The study begins with a comparison of the two main strategies for network matching: segment-based and node-based matching. The comparison shows that the result quality is comparable for the two strategies, but the node-based result is considerably more computationally efficient. Therefore, we improve the accuracy of node-based algorithm by handling topological relationships and detecting patterns of complicated network components. Finally, we conduct a case study on the extended node-based algorithm in which we match OSM to the Swedish National Road Database (NVDB) in Scania, Sweden. The case study reveals that OSM has a completeness of 87% in the urban areas and 69% in the rural areas of Scania. The accuracy of the matching process is approximately 95%. The conclusion is that the extended node-based algorithm is sufficiently accurate and efficient for conducting surveys of the quality of OSM and other VGI road data sets in large geographic regions.     

VGI and crowdsourced data credibility analysis using spam email detection techniques

Volunteered geographic information (VGI) can be considered a subset of crowdsourced data (CSD) and its popularity has recently increased in a number of application areas. Disaster management is one of its key application areas in which the benefits of VGI and CSD are potentially very high. However, quality issues such as credibility, reliability and relevance are limiting many of the advantages of utilising CSD. Credibility issues arise as CSD come from a variety of heterogeneous sources including both professionals and untrained citizens. VGI and CSD are also highly unstructured and the quality and metadata are often undocumented. In the 2011 Australian floods, the general public and disaster management administrators used the Ushahidi Crowd-mapping platform to extensively communicate flood-related information including hazards, evacuations, emergency services, road closures and property damage. This study assessed the credibility of the Australian Broadcasting Corporation’s Ushahidi CrowdMap dataset using a Naïve Bayesian network approach based on models commonly used in spam email detection systems. The results of the study reveal that the spam email detection approach is potentially useful for CSD credibility detection with an accuracy of over 90% using a forced classification methodology.     

Mapping from ASTER stereo image data: DEM validation and accuracy assessment

The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) on-board the National Aeronautics and Space Administration's (NASA's) Terra spacecraft provides along-track digital stereo image data at 15-m resolution. As part of ASTER digital elevation model (DEM) accuracy evaluation efforts by the US/Japan ASTER Science Team, stereo image data for four study sites around the world have been employed to validate prelaunch estimates of heighting accuracy. Automated stereocorrelation procedures were implemented using the Desktop Mapping System (DMS) software on a personal computer to derive DEMs with 30- to 150-m postings. Results indicate that a root-mean-square error (RMSE) in elevation between ±7 and ±15 m can be achieved with ASTER stereo image data of good quality. An evaluation of an ASTER DEM data product produced at the US Geological Survey (USGS) EROS Data Center (EDC) yielded an RMSE of ±8.6 m. Overall, the ability to extract elevations from ASTER stereopairs using stereocorrelation techniques meets expectations.     

Modeling aggregated expertise of user contributions to assess the credibility of OpenStreetMap features

The emergence of volunteered geographic information (VGI) during the past decade has fueled a wide range of research and applications. The assessment of VGI quality and fitness‐of‐use is still a challenge because of the non‐standardized and crowdsourced data collection process, as well as the unknown skill and motivation of the contributors. However, the frequent approach of assessing VGI quality against external data sources using ISO quality standard measures is problematic because of a frequent lack of available external (reference) data, and because for certain types of features, VGI might be more up‐to‐date than the reference data. Therefore, a VGI‐intrinsic measure of quality is highly desirable. This study proposes such an intrinsic measure of quality by developing the concept of aggregated expertise based on the characteristics of a feature's contributors. The article further operationalizes this concept and examines its feasibility through a case study using OpenStreetMap (OSM). The comparison of model OSM feature quality with information from a field survey demonstrates the successful implementation of this novel approach.     

面向灾害管理的自发地理信息研究及应用

针对目前自发地理信息(VGI)应用于灾害管理的巨大潜力和需求,该文系统地介绍了VGI应用于灾害管理中所面临的机遇及数据可用性、数据质量、数据管理和法律议题等方面的挑战;在此基础上,针对VGI数据质量问题,结合我国灾害管理实际情况,提出了3种提高VGI数据质量的方法,即VGI数据贡献者分类与权限设计、政府引导下的灾害管理VGI数据采集框架以及VGI数据质量评估体系;最后,以开发的地震灾情信息管理原型系统为例,讨论VGI应用于灾害管理中的数据采集框架、数据模型等关键技术问题,具有一定的推广和应用价值。     

Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud

ABSTRACT

The South Asia (India, Pakistan, Bangladesh, Nepal, Sri Lanka and Bhutan) has a staggering 900 million people (~43% of the population) who face food insecurity or severe food insecurity as per United Nations, Food and Agriculture Organization’s (FAO) the Food Insecurity Experience Scale (FIES). The existing coarse-resolution (≥250-m) cropland maps lack precision in geo-location of individual farms and have low map accuracies. This also results in uncertainties in cropland areas calculated from such products. Thereby, the overarching goal of this study was to develop a high spatial resolution (30-m or better) baseline cropland extent product of South Asia for the year 2015 using Landsat satellite time-series big-data and machine learning algorithms (MLAs) on the Google Earth Engine (GEE) cloud computing platform. To eliminate the impact of clouds, 10 time-composited Landsat bands (blue, green, red, NIR, SWIR1, SWIR2, Thermal, EVI, NDVI, NDWI) were derived for each of the three time-periods over 12 months (monsoon: Days of the Year (DOY) 151–300; winter: DOY 301–365 plus 1–60; and summer: DOY 61–150), taking the every 8-day data from Landsat-8 and 7 for the years 2013–2015, for a total of 30-bands plus global digital elevation model (GDEM) derived slope band. This 31-band mega-file big data-cube was composed for each of the five agro-ecological zones (AEZ’s) of South Asia and formed a baseline data for image classification and analysis. Knowledge-base for the Random Forest (RF) MLAs were developed using spatially well spread-out reference training data (N = 2179) in five AEZs. The classification was performed on GEE for each of the five AEZs using well-established knowledge-base and RF MLAs on the cloud. Map accuracies were measured using independent validation data (N = 1185). The survey showed that the South Asia cropland product had a producer’s accuracy of 89.9% (errors of omissions of 10.1%), user’s accuracy of 95.3% (errors of commission of 4.7%) and an overall accuracy of 88.7%. The National and sub-national (districts) areas computed from this cropland extent product explained 80-96% variability when compared with the National statistics of the South Asian Countries. The full-resolution imagery can be viewed at full-resolution, by zooming-in to any location in South Asia or the world, at www.croplands.org and the cropland products of South Asia downloaded from The Land Processes Distributed Active Archive Center (LP DAAC) of National Aeronautics and Space Administration (NASA) and the United States Geological Survey (USGS): https://lpdaac.usgs.gov/products/gfsad30saafgircev001/.     

众源地理信息研究现状与展望

众源地理信息作为新型地理信息模式,是指由互联网用户借助交互式平台,通过直接上传传感器数据或提供数字化劳动而贡献的地理信息数据。近20年来,众源地理信息热度上升,并受到越来越多研究者的关注,正在逐渐成为一种重要的地理信息数据来源。本文对近十几年来关于众源地理信息的中文和英文文献进行了系统性的分析与研究,力图展现出众源地理信息研究的发展现状,同时以这些研究发现的规律为基础,结合当前的国际形势,探讨了众源地理信息的发展机遇与挑战,同时对发展自主众源地理信息给出了建议。     

Using control data to determine the reliability of volunteered geographic information about land cover

There is much interest in using volunteered geographic information (VGI) in formal scientific analyses. This analysis uses VGI describing land cover that was captured using a web-based interface, linked to Google Earth. A number of control points, for which the land cover had been determined by experts allowed measures of the reliability of each volunteer in relation to each land cover class to be calculated. Geographically weighted kernels were used to estimate surfaces of volunteered land cover information accuracy and then to develop spatially distributed correspondences between the volunteer land cover class and land cover from 3 contemporary global datasets (GLC-2000, GlobCover and MODIS v.5). Specifically, a geographically weighted approach calculated local confusion matrices (correspondences) at each location in a central African study area and generated spatial distributions of user's, producer's, portmanteau, and partial portmanteau accuracies. These were used to evaluate the global datasets and to infer which of them was 'best’ at describing Tree cover at each location in the study area. The resulting maps show where specific global datasets are recommended for analyses requiring Tree cover information. The methods presented in this research suggest that some of the concerns about the quality of VGI can be addressed through careful data collection, the use of control points to evaluate volunteer performance and spatially explicit analyses. A research agenda for the use and analysis of VGI about land cover is outlined.     

Finding meaningful participation in volunteer geographic information and citizen science: a case comparison in environmental application

ABSTRACT

Volunteer geographic information (VGI) and citizen science (CS) have been used as a way to promote a form of democratization of knowledge. Crowdsourcing facilitates the massive collection of data through nonexpert volunteers. This study compares 57 VGI and CS projects through a cross-case comparison method to explore the level of involvement of participants, based on three main analytic dimensions (project rationale, actor interaction, and data flow) and 12 sub-variables. The primary goal of this research is to analyze the purpose and the role of technology in VGI and CS projects, using three matrices to explore emerging trade-offs. Finally, we synthesized the workflow of VGI and CS project and compared based on project purposes. At the end of this study, five main purposes were found among the selected projects, uncovering that data collection is the most common purpose. A general workflow can be conceptualized, but detail implementation will involve various trade-offs, especially between local involvement and large-area expert-oriented protocol implementations. By exploring diverse relationships among selected variables of analysis in VGI and CS projects, this study pretends to build a foundation for larger, global meta-analysis that can bring some transparency in the epistemic interactions between experts and nonexperts.     

Validating the use of object-based image analysis to map commonly recognized landform features in the United States

ABSTRACT

The U.S. Geological Survey (USGS) National Geospatial Program (NGP) seeks to i) create semantically accessible terrain features from the pixel-based 3D Elevation Program (3DEP) data, and ii) enhance the usability of the USGS Geographic Names Information System (GNIS) by associating boundaries with GNIS features whose spatial representation is currently limited to 2D point locations. Geographic object-based image analysis (GEOBIA) was determined to be a promising method to approach both goals. An existing GEOBIA workflow was modified and the resulting segmented objects and terrain categories tested for a strategically chosen physiographic province in the mid-western US, the Ozark Plateaus. The chi-squared test of independence confirmed that there is significant overall spatial association between terrain categories of the GEOBIA and GNIS feature classes. Contingency table analysis also suggests strong category-specific associations between select GNIS and GEOBIA classes. However, 3D visual analysis revealed that GEOBIA objects resembled segmented regions more than they did individual landform objects, with their boundaries often failing to correspond to match what people would likely perceive as landforms. Still, objects derived through GEOBIA can provide initial baseline landscape divisions that can improve the efficiency of more specialized feature extraction methods.     

Partial polygon pruning of hydrographic features in automated generalization

This article demonstrates a working method to automatically detect and prune portions of waterbody polygons to support creation of a multi‐scale hydrographic database. Water features are sensitive to scale change, therefore multiple representations are required to maintain visual and geographic logic at smaller scales. Partial pruning of polygonal features – such as long, sinuous reservoir arms, stream channels too narrow at the target scale, and islands that begin to coalesce – entails concurrent management of the length and width of polygonal features as well as integrating pruned polygons with other generalized point and linear hydrographic features to maintain stream network connectivity. The implementation follows data representation standards developed by the US Geological Survey (USGS) for the National Hydrography Dataset (NHD). Portions of polygonal rivers, streams, and canals are automatically characterized for width, length, and connectivity. This article describes an algorithm for automatic detection and subsequent processing, and shows results for a sample of NHD subbasins in different landscape conditions in the US.