Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model

Urban land use information plays an essential role in a wide variety of urban planning and environmental monitoring processes. During the past few decades, with the rapid technological development of remote sensing (RS), geographic information systems (GIS) and geospatial big data, numerous methods have been developed to identify urban land use at a fine scale. Points-of-interest (POIs) have been widely used to extract information pertaining to urban land use types and functional zones. However, it is difficult to quantify the relationship between spatial distributions of POIs and regional land use types due to a lack of reliable models. Previous methods may ignore abundant spatial features that can be extracted from POIs. In this study, we establish an innovative framework that detects urban land use distributions at the scale of traffic analysis zones (TAZs) by integrating Baidu POIs and a Word2Vec model. This framework was implemented using a Google open-source model of a deep-learning language in 2013. First, data for the Pearl River Delta (PRD) are transformed into a TAZ-POI corpus using a greedy algorithm by considering the spatial distributions of TAZs and inner POIs. Then, high-dimensional characteristic vectors of POIs and TAZs are extracted using the Word2Vec model. Finally, to validate the reliability of the POI/TAZ vectors, we implement a K-Means-based clustering model to analyze correlations between the POI/TAZ vectors and deploy TAZ vectors to identify urban land use types using a random forest algorithm (RFA) model. Compared with some state-of-the-art probabilistic topic models (PTMs), the proposed method can efficiently obtain the highest accuracy (OA = 0.8728, kappa = 0.8399). Moreover, the results can be used to help urban planners to monitor dynamic urban land use and evaluate the impact of urban planning schemes.     

RecNet: a deep neural network for personalized POI recommendation in location-based social networks

How to exploit various features of users and points of interest (POIs) for accurate POI recommendation is important in location-based social networks (LBSNs). In this paper, a novel POI recommendation framework, named RecNet, is proposed, which is developed based on a deep neural network (DNN) to incorporate various features in LBSNs and learn their joint influence on user behavior. More specifically, co-visiting, geographical and categorical influences in LBSNs are exploited to alleviate the data sparsity issue in POI recommendation and are converted to feature vector representations of POIs and users via feature embedding. Moreover, the embedded POIs and users are fed into a DNN pairwise to adaptively learn high-order interactions between features. Our method is evaluated on two publicly available LBSNs datasets and experimental results show that RecNet outperforms state-of-the-art algorithms for POI recommendation.     

Geometric-based approach for integrating VGI POIs and road networks

Integrating heterogeneous spatial data is a crucial problem for geographical information systems (GIS) applications. Previous studies mainly focus on the matching of heterogeneous road networks or heterogeneous polygonal data sets. Few literatures attempt to approach the problem of integrating the point of interest (POI) from volunteered geographic information (VGI) and professional road networks from official mapping agencies. Hence, the article proposes an approach for integrating VGI POIs and professional road networks. The proposed method first generates a POI connectivity graph by mining the linear cluster patterns from POIs. Secondly, the matching nodes between the POI connectivity graph and the associated road network are fulfilled by probabilistic relaxation and refined by a vector median filtering (VMF). Finally, POIs are aligned to the road network by an affine transformation according to the matching nodes. Experiments demonstrate that the proposed method integrates both the POIs from VGI and the POIs from official mapping agencies with the associated road networks effectively and validly, providing a promising solution for enriching professional road networks by integrating VGI POIs.     

多样性视角下的城市复合功能特征及成因探测——以长春市为例

多功能要素的复合化已成为信息时代城市空间发展的重要趋势,而复合功能开发亦被认为是解决城市交通拥堵、低效能源消耗及职住不平衡等问题的重要手段,对促进有活力的、宜居的及可持续的城市环境建设具有重要意义。基于城市多样性的理论框架,在界定城市功能复合内涵的基础上,以长春市中心城区城市功能兴趣点（POI）数据为基础,采用区位熵指数、信息熵指数及地理探测器模型,分析城市居住、办公、商业、休闲四类功能要素的复合特征,并探讨城市功能复合空间分异的驱动因素。结果表明：① 城市功能要素集中度特征显著,各类型功能要素均形成了专业化的功能集聚区,但各区块间功能要素的专业化程度存在较大差异。② 城市功能要素复合度整体表现出核心—边缘的空间差异,核心区街道复合度整体高于外围开发区,办公、商业、休闲三种功能要素间的复合度要整体强于其各自与居住功能的复合。③ 以单一功能为主、多功能兼容的综合型复合是街道尺度功能复合的主要表现形式;各功能要素中,休闲、商业功能具有较强的兼容性。④ 城市功能复合的空间异质性特征显著,土地价格、休闲要素数量是造成多功能复合分异的主要原因;分类型复合中,各解释因子影响力度表现各异。     

空气污染对城市活力的影响及其建成环境异质性——基于大数据的分析

建设充满活力的城市空间得到地理和城乡规划学者的广泛关注。随着空气污染问题的加剧,空气质量影响居民在城市空间中的活动,但鲜有研究考察空气污染与城市活力的定量关系。基于广州市2019年新浪微博签到记录、日气象和空气质量数据、以及建成环境数据,本研究构建以街道为空间单元、以天为时间单元的面板数据,通过标准差椭圆（SDE）以及面板回归模型测度空气污染对城市活力的抑制效应以及该抑制效应在不同建成环境上的异质性。研究得到以下结论：① 城市活力SDE面积随空气质量指数（AQI）上升而收缩,轻度污染和中度污染的城市活力SDE面积仅为空气质量优的约80%和30%。② 运用空间面板回归模型控制街道的空间关联性后,空气质量指数（AQI）对城市活力具有明显负向影响,AQI每增加1个单位,日活动强度减少约0.10次/10 km²;当空气质量恶化到中等污染后,AQI每增加1个单位,日活动强度减少约0.14次/10 km²。③ 空气污染对城市活力的抑制效应在不同建成环境上存在异质性,POI密度、离城市中心距离强化空气污染对城市活力的抑制效应,而地铁站密度、道路交叉口密度、土地利用混合度则弱化空气污染对城市活力的抑制效应。本研究有助于更好厘清空气污染、建成环境与城市活力的关系,并为优化建成环境以缓减空气污染对城市活力抑制效应提供分析支撑。     

Enabling maps/location searches on mobile devices: constructing a POI database via focused crawling and information extraction

With the popularity of mobile devices and smartphones, we have witnessed rapid growth in mobile applications and services, especially in location-based services (LBS). According to a mobile marketing survey, maps/location searches are among the most utilized services on smartphones. Points of interest (POIs), such as stores, shops, gas stations, parking lots, and bus stops, are particularly important for maps/location searches. Existing map services such as Google Maps and Wikimapia are constructed manually either professionally or with crowd sourcing. However, manual annotation is costly and limited in current POI search services. With the abundance of information on the Web, many store POIs can be extracted from the Web. In this paper, we focus on automatically constructing a POI database to enable store POI map searches. We propose techniques that are required to construct a POI database, including focused crawling, information extraction, and information retrieval techniques. We first crawl Yellow Page web sites to obtain vocabularies of store names. These vocabularies are then investigated with search engines to obtain sentences containing these store names from search snippets in order to train a store name recognition model. To extract POIs scattered across the Web, we propose a query-based crawler to find address-bearing pages that might be used to extract addresses and store names. We crawled 1.25 million distinct POI pairs scattered across the Web and implemented a POI search service via Apache Lucent’s search platform, called Solr. The experimental results demonstrate that the proposed geographical information retrieval model outperforms Wikimapia and a commercial app called ‘What’s the Number?’     

基于街景数据的建成环境与街道活力时空分析——以深圳福田区为例

建成环境对街道活力的影响是国内外城市研究的热点议题。然而,对于建成环境要素的测度与评估多偏重于二维建成环境指标,尚未充分挖掘三维建成环境指标。以深圳市福田区为例,采用街景数据、路网数据、POI数据及移动互联网位置服务数据,建立周末分时段模型,探讨商业街道和生活街道活力的时空间分布特征及建成环境对其产生的影响。结果表明：① 商业街道上居民全天活动的峰值时段为18:00~20:00,生活街道上居民全天活动的峰值时段为11:00~13:00。② 深圳市福田区街道活力总体呈现多中心结构,随时间变化显现出明显的空间差异。③ 不同的建成环境指标对街道活力的作用时段与影响程度存在差异。提高功能混合度有利于提升商业街道凌晨、上午和夜间的活力及生活街道午后和傍晚的活力;过宽的相对步行宽度对生活街道活力提升有抑制作用,更安全的步行环境对商业和生活街道夜间活力提升有促进作用;界面连续程度高的商业街道午后及夜间的活力更强,界面多样性丰富的生活街道白天活力更强。     

基于POI数据的建设用地多功能混合利用空间分异研究

建设用地多功能混合利用对提升区域用地效率、增进国土空间效能具有重要意义。论文构建基于生产—生活—生态空间(即三生空间)的建设用地多功能混合利用分析框架,以济南市为研究区,采用POI数据,利用熵模型、景观格局分析和关联规则挖掘方法,探究土地混合利用的空间分异特征。结果显示,研究区建设用地混合利用以生产空间、生产—生活空间和生活空间为主;核心城区的建设用地混合利用度较高,而生产、生活空间集中连片,生态空间嵌入不足;乡村地区景观的破碎化特征明显,以生产—生活空间引领的建设用地混合利用度较低;产业园区的生活—生态空间在网络中处于边缘位置,加强园区内部规划与周边区域形成互补的生活、生态空间,是实现园区土地可持续利用的关键。关联规则的分析结果表明,科学的生产空间规划是优化混合利用的重要抓手,而合理的生态空间布局对带动区域建设用地混合利用起着关键作用。研究基于POI数据,从行为空间互动理论视角探究建设用地多功能混合规律,丰富了现有土地混合利用理论与方法体系,也为土地利用政策制定及城市空间格局优化提供了科学依据。     

Points of interest recommendation from GPS trajectories

Recently, points of interest (POIs) recommendation has evolved into a hot research topic with real-world applications. In this paper, we propose a novel semantics-enhanced density-based clustering algorithm SEM-DTBJ-Cluster, to extract semantic POIs from GPS trajectories. We then take into account three different factors (popularity, temporal and geographical features) that can influence the recommendation score of a POI. We characterize the impacts caused by popularity, temporal and geographical information, by using different scoring functions based on three developed recommendation models. Finally, we combine the three scoring functions together and obtain a unified framework PTG-Recommend for recommending candidate POIs for a mobile user. To the best of our knowledge, this work is the first that considers popularity, temporal and geographical information together. Experimental results on two real-world data sets strongly demonstrate that our framework is robust and effective, and outperforms the baseline recommendation methods in terms of precision and recall.     

Beyond density: municipal expenditures and the shape and location of development

A clear understanding of the relationship between development patterns and municipal expenditures is complicated by how one chooses to quantify these patterns. Extant literature often employs a single density measure to capture the low-density nature of sprawl. While density provides an intuitive link to economies of scale and congestion costs, it fails to capture other spatial characteristics of sprawl related to centrality, connectedness, and mixed use that may influence municipal expenditures according to Smart Growth and New Urbanism advocates. This study uses Massachusetts orthoimagery data to construct multidimensional measures of residential and commercial land use patterns. Municipal expenditures associated with public works, fire, and police are regressed on multidimensional measures of land use as well as a number of demand controls. Findings indicate that economies and diseconomies do exist with respect to the multidimensional metrics considered. Support is mixed for development patterns emphasized by Smart Growth and New Urbanism advocates.     

Unusual behavior detection and object ranking from movement trajectories in target regions

Unusual behavior detection has been of interest in video analysis, transportation systems, movement trajectories, and so on. In movement trajectories, only a few works identify unusual behavior of objects around pre-defined points of interest (POI), such as surveillance cameras, commercial buildings, etc., that may be interesting for several application domains, mainly for security. In this article, we define new types of unusual behaviors of moving objects in relation to POI, including surround, escape, and return. Based on these types of unusual behavior, we (i) present an algorithm to compute these behaviors, (ii) define a set of functions to weight the degree of unusual behavior of every moving object in the database, and (iii) rank the moving objects according to the degree of unusual behavior in relation to a set of POIs. We evaluate the proposed method with real trajectory data and show that the closest work does not detect the proposed behaviors and ranks objects considering only one type of unusual movement.     

基于遥感数据和POI数据的GDP空间化研究 ——以北京市为例

为了比较分析不同数据对格网化社会经济活动空间分布精度差异性的影响,以北京市为例,基于土地利用数据对第一产业空间建模,基于NPP/VIIRS夜间灯光数据和POI数据运用熵值赋权和代用数据空间展布的方法对第二、三产业空间建模,将第一产业和第二、三产业进行格网叠加,并与辖区GDP统计数据进行误差分析。结果表明:借助土地利用数据、NPP/VIIRS夜间灯光数据和POI数据的GDP空间模拟结果与真实分布格局较为一致,而使用土地利用数据和夜间灯光数据进行GDP空间化模拟的精度明显降低。因此,将反映细节信息的POI数据加入到GDP空间化研究后,能够进一步扩展GDP空间化的数据源,提高GDP空间化模拟精度。基于土地利用数据、NPP/VIIRS夜光数据和POI数据可以实现较高精度的GDP空间化模拟。     

基于多源数据的城市活力空间特征及建成环境对其影响机制研究

采用城市POI、手机信令数据及夜间灯光遥感数据,以深圳市为例,构建城市活力度量指标分析城市活力的空间特征。构建“5D”指标体系度量城市建成环境,并运用地理探测器,探究建成环境对城市活力的影响机制。结果表明：1）深圳市城市综合活力显示出“南强北弱,西强东弱”的空间分异特征,空间分布极不均衡。城市综合活力最主要反映的是社会活力。2）城市综合活力、经济活力、社会活力、文化活力均受到建成环境的显著影响。高POI密度、高建筑密度、高平均建筑层数和高土地利用混合度对城市活力具有显著促进作用。3）居住人口密度与路网密度、土地利用混合度与路网密度等交互作用对城市活力产生更为积极的影响。4）在影响机制中,建筑密度、平均建筑层数为底层支撑因素,POI密度、土地利用混合度为直接驱动因素,居住人口密度为诱发因素,距行政区中心距离、交叉口密度、路网密度、地铁站点密度和公交站点密度为调节因素。     

基于POI数据的城市用地功能识别与评价研究

充分利用大数据开展城市用地功能识别,有助于把握城市空间结构,推动城市内部空间合理布局。POI数据是大数据时代一种较易获得且极具代表性的空间点状数据,能够有效地确定城市用地的实际功能。以济南市内五区的185126条POI数据为基础,对所得数据进行去重、纠偏、重分类,构建城市用地功能分类体系,运用频数密度、类型比例及核密度估计,识别济南市内五区城市用地功能并利用误差矩阵对识别结果进行检验。结果表明：①混合功能用地与单一功能用地呈现圈层化地域分布特征,“核心-外围”分异明显;②由内向外单一功能用地集聚趋势减弱,混合功能用地多样性降低,不同用地表现出不同的空间分布模式;③通过误差矩阵及与用地规划图中规划用地及电子地图的实际用地对比,识别总体精度为75.67%,识别结果较为准确。     

基于POI数据的巨型城市消防站空间优化——以北京市五环内区域为例

消防站的空间布局事关城市发展与城市安全。本文以北京市五环内中心城区为研究区,使用44.34万条POI数据和道路网等相关数据,考虑易燃易爆、人群脆弱等不同特征的火灾风险因子,采用核密度分析、SAVEE模型等方法,识别出研究区内的火灾风险空间分布,进一步借助“位置—分配”模型和网络分析,并结合优化目标对研究区内消防站进行空间优化。主要研究结论为：①按照火灾风险从高到低排序,前10%的火灾风险区域主要集中在CBD—三里屯、北京古玩城—双井、王府井、南锣鼓巷—雍和宫等区域。②现有消防站对全部44.34万个POI请求点5分钟响应时间内的覆盖率为96.46%,总体覆盖效果较好,但在研究区西北和西南部的世纪城—闵庄一带覆盖不足。③综合考虑高火灾风险区、重要火灾风险因子、POI总体覆盖率和个体消防站覆盖面积相关标准等因素,经多次迭加运算分析得到最终需新增15个消防站点。优化后的各指标均有较大提升,可满足研究区的消防需求。     

城市分形中心与占优标度区选择

用回转半径法研究城市分形特征时,中心点位置的选择至关重要。以反映城市基础设施情况的兴趣点(point of interest,POI)作为基础数据,分析中心点位置对标度区识别的影响。将POI几何中心、重心、密度中心、中心城区几何中心和重心5种统计中心作为待选中心,给出辐射范围、核心密度与分形维数、中心漂移度等标度区相关指标,提出判断占优标度区的POI数量最大化原则。通过统计中心与地标中心标度区对比,确定城市分形中心和占优标度区。省会城市及直辖市标度区分析结果显示:统计中心各有优劣,占优中心总体上更倾向于POI几何中心和密度中心,地标中心有时优于统计中心;密度中心对应的占优标度区半径维数较低,若半径维数太低则容易陷入局部密度中心;中心漂移度指标表明可能存在更好的分形中心选择方案。     

基于手机定位数据的深圳市热浪人口暴露度分析

热浪作为城市化特征灾害之一,严重影响着城市居民的生命健康。目前针对热浪的研究主要聚焦基于静态数据的时空模式、风险管理和脆弱性评价分析方向,对动态人口暴露度的研究尚少。论文基于手机定位数据,首先融合深圳市逐时人口与气温时空分布模型,揭示热浪动态人口暴露度水平;其次,构建基于7类城市兴趣点(point of interest,POI)与不同时段人口分布的地理加权回归模型,初步分析了热浪环境下POI对人群行为模式的影响机制。结果显示：① 相比于基准时段(2018年7月28日12:00~18:00),2018年7月26日至8月1日热浪平均辐射范围在7月29日以8.66倍速增长,至7月30日则以18.93倍速跃至峰值,覆盖区域整体呈现西部高于东部、南部低于北部的特征;② 人口在不同时段均表现为明显的带状聚集分布态势,且人口暴露度与气温和人口的动态演变紧密关联,其暴露度同热浪扩散幅度相似,总体呈2.29倍等比增长,辐射范围包括南山区、福田区、罗湖区等城市商业、工业、住宅中心人口密集区域;③ 同类POI在不同时刻、不同POI在相同时刻对人群减少热浪暴露的移动交互行为具有明显的时空驱动机制差异及选择偏好特征。在持续性城市化背景下,该研究方法可为同类的城市灾害人口暴露度分析提供一定的科学参考。     

Spatiotemporal model for assessing the stability of urban human convergence and divergence patterns

Understanding the stability of urban flows is critical for urban transportation, urban planning and public health. However, few studies have measured the stability of aggregate human convergence or divergence patterns. We propose a spatiotemporal model for assessing the stability of human convergence and divergence patterns. A mobile phone location data set obtained from Shenzhen, China, was used to assess the stability of daily human convergence and divergence patterns at three different spatial scales, i.e. points (cell phone towers), lines (bus lines) and areas (traffic analysis zones [TAZs]). Our analysis results demonstrated that the proposed model can identify points and bus lines with time-dependent variations in stability, which is useful for delineating TAZs for transportation planning, or adjusting bus timetables and routes to meet the needs of bus riders. Comparisons of the results obtained from the proposed model and the widely used entropy measure indicated that the proposed model is suitable for assessing the differences in stability for various types of spatial analysis units, e.g. cell phone towers. Therefore, the proposed model is a useful alternative approach of measuring spatiotemporal stability of aggregate human convergence and divergence patterns, which can be derived from the space–time trajectories of moving objects.     

基于卫星遥感和POI数据的人口空间化研究——以广州市为例

以广州市为例,基于NPP/VIIRS夜间灯光、土地利用、POI（Points of Interest）等自然地理和社会经济因素,构建了人口空间化指标体系,采用主成分赋权法确定人口分布权重,利用GIS技术对人口统计数据进行了空间化处理。结果显示：综合考虑了自然地理和社会经济因素的人口空间化结果与真实的人口空间格局相吻合,空间分辨率为30 m,且相对误差绝对值＜25%的乡镇有62个,所占比例为36.47%;而不加POI数据得到的人口空间化结果,相对绝对值＜25%的乡镇有33个,所占比例约为20%,精度明显降低。结果表明：1）综合考虑NPP/VIIRS夜间灯光、土地利用、POI等自然地理和社会经济因素,有助于实现精度较高的人口空间化结果;2）将能够反映微观细节信息的POI数据引入人口空间化研究,扩展了人口空间化的数据源,并且可以提高人口空间化结果的精度。