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.     

A citizen data-based approach to predictive mapping of spatial variation of natural phenomena

The vast accumulation of environmental data and the rapid development of geospatial visualization and analytical techniques make it possible for scientists to solicit information from local citizens to map spatial variation of geographic phenomena. However, data provided by citizens (referred to as citizen data in this article) suffer two limitations for mapping: bias in spatial coverage and imprecision in spatial location. This article presents an approach to minimizing the impacts of these two limitations of citizen data using geospatial analysis techniques. The approach reduces location imprecision by adopting a frequency-sampling strategy to identify representative presence locations from areas over which citizens observed the geographic phenomenon. The approach compensates for the spatial bias by weighting presence locations with cumulative visibility (the frequency at which a given location can be seen by local citizens). As a case study to demonstrate the principle, this approach was applied to map the habitat suitability of the black-and-white snub-nosed monkey (Rhinopithecus bieti) in Yunnan, China. Sightings of R. bieti were elicited from local citizens using a geovisualization platform and then processed with the proposed approach to predict a habitat suitability map. Presence locations of R. bieti recorded by biologists through intensive field tracking were used to validate the predicted habitat suitability map. Validation showed that the continuous Boyce index (B_cont(0.1)) calculated on the suitability map was 0.873 (95% CI: [0.810, 0.917]), indicating that the map was highly consistent with the field-observed distribution of R. bieti. B_cont(0.1) was much lower (0.173) for the suitability map predicted based on citizen data when location imprecision was not reduced and even lower (?0.048) when there was no compensation for spatial bias. This indicates that the proposed approach effectively minimized the impacts of location imprecision and spatial bias in citizen data and therefore effectively improved the quality of mapped spatial variation using citizen data. It further implies that, with the application of geospatial analysis techniques to properly account for limitations in citizen data, valuable information embedded in such data can be extracted and used for scientific mapping.     

Fine-resolution population mapping using OpenStreetMap points-of-interest

Data on population at building level is required for various purposes. However, to protect privacy, government population data is aggregated. Population estimates at finer scales can be obtained through areal interpolation, a process where data from a first spatial unit system is transferred to another system. Areal interpolation can be conducted with ancillary data that guide the redistribution of population. For population estimation at the building level, common ancillary data include three-dimensional data on buildings, obtained through costly processes such as LiDAR. Meanwhile, volunteered geographic information (VGI) is emerging as a new category of data and is already used for purposes related to urban management. The objective of this paper is to present an alternative approach for building level areal interpolation that uses VGI as ancillary data. The proposed method integrates existing interpolation techniques, i.e., multi-class dasymetric mapping and interpolation by surface volume integration; data on building footprints and points-of-interest (POIs) extracted from OpenStreetMap (OSM) are used to refine population estimates at building level. A case study was conducted for the city of Hamburg and the results were compared using different types of POIs. The results suggest that VGI can be used to accurately estimate population distribution, but that further research is needed to understand how POIs can reveal population distribution patterns.     

Quantitative assessment of the reliability of chironomid remains in paleoecology: effects of count density and sample size

Random distributions for a wide range (1–100,000) of chironomid head capsules (HC) were simulated on a 1-m² surface. The number of HC found in circular surfaces equivalent to standard core diameters (90 and 63 mm) was estimated 1000 times, over the range of tested densities. For each number of HC found in the samples, the range of simulated densities was estimated using a threshold probability (p > 0.95). This enabled us to develop equations to infer HC density from sample counts. Because of the threshold probability for comparable sample counts, the equations yield higher estimated densities under a random distribution than for a regular distribution. The probability of sampling at least one HC was >0.95 for densities of 900 HC m^?2 for the 90-mm core and 1400 HC m^?2 for the 63-mm core. For a specific sample count, the range of actual densities was ~10 times higher for the 63-mm core than the 90-mm core. Comparison with field larval densities revealed that most densities were too low to be suitable for annually resolved reconstruction of a quantitative signal, using current corer sizes, although a large number of populations can support sub-decadal analyses. Nonetheless, some lakes exhibit population sizes large enough to reconstruct robust quantitative estimates of past chironomid abundances. This work provides guidance to reconstruct species dynamics and fine-scale time series analyses in paleoecology.     

基于多源数据和集成学习的城市住宅地价分布模拟——以武汉市为例

精准刻画城市住宅地价分布特征,对于科学引导城市空间布局规划、有效实现城市精明增长等具有重要意义。而城市住宅地价与其潜在影响因素之间的复杂非线性关系,给地价分布精细模拟带来了挑战。论文旨在探索基于地理大数据和集成学习的城市住宅地价分布模拟方法体系,以满足快速、精准监测地价动态变化的需要。选取武汉市为典型区,以住宅用地交易样点、兴趣点(points of interest, POI)和夜间灯光影像为数据源,以500 m分辨率网格为估价单元,提取POI核密度和夜间灯光强度作为住宅地价预测变量,采用机器学习算法和bagging、stacking集成方法构建住宅地价预测模型,并对比分析其精度。研究发现：① 单个机器学习算法中,支持向量回归(support vector regression, SVR)预测精度最高,接下来依次是k最近邻算法(k-nearest neighbor algorithm, k-NN)、高斯过程回归(Gaussian process regression, GPR)和BP神经网络(back propagation neural networks, BP-NN);② 在提升单个算法预测精度方面,stacking方法的性能优于bagging方法,使用stacking集成SVR和k-NN的地价预测模型精度最高,其平均绝对百分误差仅为8.29%,拟合优度R²达0.814;③ 基于论文所构建模型生成的城市住宅地价分布图能有效表征价格圈层分布特征和局部奇异性。研究结果可为城市住宅地价评估提供新的思路和方法借鉴。     

Characterizing mixed-use buildings based on multi-source big data

To-date few research has successfully integrated big data from multiple sources to characterize urban mixed-use buildings. In this paper, we introduce a probabilistic model to integrate multi-source and geospatial big data (social network data, taxi trajectories, Points of Interest and remote sensing images) to characterize urban mixed-use buildings. The usefulness of our model is demonstrated with a case study of the Tianhe District in megacity Guangzhou, China. The model predicted building functions at 85% accuracy based on ground truth data from field surveys. We further explored the spatial patterns of the identified building functions. Most mixed-use buildings are located along major streets. Our proposed model can identify mixed-use buildings in a city; information is useful for planning evaluation and urban policymaking.     

Optimizing a Knowledge-driven Prospectivity Model for Gold Deposits Within Peräpohja Belt,Northern Finland

This paper combines knowledge- and data-driven prospectivity mapping approaches by using the receiver operating characteristics (ROC) spatial statistical technique to optimize the process of rescaling input datasets and the process of data integration when using a fuzzy logic prospectivity mapping method. The methodology is tested in an active mineral exploration terrain within the Paleoproterozoic Peräpohja Belt (PB) in the Northern Fennoscandian Shield, Finland. The PB comprises a greenschist to amphibolite facies, complexly deformed supracrustal sequence of variable quartzites, mafic volcanic rocks and volcaniclastic rocks, carbonate rocks, black shales, mica schists and graywackes. These formations were deposited on Archean basement and 2.44 Ga layered intrusions, during the multiple rifting of the Archean basement (2.44–1.92 Ga). Younger intrusive units in the PB comprise 2.20–2.13 Ga gabbroic sills or dikes and 1.98 Ga A-type granites. Metamorphism and complex deformation of the PB took place during the Svecofennian orogeny (1.9–1.8 Ga) and were followed by intrusions of post-orogenic granitoids (1.81–1.77 Ga). The recent mineral exploration activities have indicated several gold-bearing mineral occurrences within the PB. The Rompas Au-U mineralization is hosted within deformed and metamorphosed calc-silicate veins enclosed within mafic volcanic rocks and contains uranium-bearing zones without gold and very high-grade (>10,000 g/t Au) gold pockets with uraninite and uraninite-pyrobitumen nodules. In the vicinity of the Rompas, a magnesium skarn hosted disseminated-stockwork gold mineralization was also recognized at the Palokas-Rajapalot prospect. The exploration criteria translated into a fuzzy logic prospectivity model included data derived from regional till geochemistry (Fe, Cu, Co, Ni, Au, Te, K), high-resolution airborne geophysics (magnetic field total intensity, electromagnetic, gamma radiation), ground gravity and regional bedrock map (structures). The current exploration licenses and exploration drilling sites for gold were used to validate the knowledge-driven mineral prospectivity model.     

A hybrid parallel cellular automata model for urban growth simulation over GPU/CPU heterogeneous architectures

As an important spatiotemporal simulation approach and an effective tool for developing and examining spatial optimization strategies (e.g., land allocation and planning), geospatial cellular automata (CA) models often require multiple data layers and consist of complicated algorithms in order to deal with the complex dynamic processes of interest and the intricate relationships and interactions between the processes and their driving factors. Also, massive amount of data may be used in CA simulations as high-resolution geospatial and non-spatial data are widely available. Thus, geospatial CA models can be both computationally intensive and data intensive, demanding extensive length of computing time and vast memory space. Based on a hybrid parallelism that combines processes with discrete memory and threads with global memory, we developed a parallel geospatial CA model for urban growth simulation over the heterogeneous computer architecture composed of multiple central processing units (CPUs) and graphics processing units (GPUs). Experiments with the datasets of California showed that the overall computing time for a 50-year simulation dropped from 13,647 seconds on a single CPU to 32 seconds using 64 GPU/CPU nodes. We conclude that the hybrid parallelism of geospatial CA over the emerging heterogeneous computer architectures provides scalable solutions to enabling complex simulations and optimizations with massive amount of data that were previously infeasible, sometimes impossible, using individual computing approaches.     

Transcribing from the Mind To the Map: Tracing the Evolution of a Concept

Transcribing what is held in one's mind to a tangible map is experiencing a multidisciplinary renewal. Sketch mapping is being utilized to identify a range of community concerns, as well as for more generally revealing otherwise invisible landscapes. Whether the aim is to understand preference, perception, knowledge, or behavior, the result is some form of map. The genesis of this concept is usually attributed to seminal work in the 1960s and 1970s geography, planning, and environmental psychology. However, its resurgence in the past decade has been driven by a confluence of recent methodological and epistemological developments across numerous disciplines surrounding the role of local knowledge in ecological frameworks and how this can be mapped and analyzed with and without geospatial technologies. With growing adoption of sketch mapping well beyond its initial disciplinary niches, it is appropriate to review its evolution in order to inform ongoing and future research.     

Preliminary mapping of high-resolution rural population distribution based on imagery from Google Earth: A case study in the Lake Tai basin, eastern China

There is a large rural population in China. Throughout the country, sewage from rural households is mostly discharged with minimal treatment. Knowledge of rural population distribution is essential to study the rural households’ impacts on their surrounding environment. However, high-resolution spatial datasets on rural population distribution are rarely available in China. This study explores the feasibility of using the image from Google Earth to derive a high-resolution map on rural population distribution for a town in the Lake Tai basin of eastern China. Study results show that texture analysis in conjunction with other processing procedures can extract man-made building features from the image reasonably, which can then serve as the basis for the preliminary mapping of rural population distribution in the study region. This may prove to be a promising alternative for deriving spatial datasets on rural population distribution in many parts of the world.     

基于规则数据驱动的专题制图技术及其应用研究

地图制图自动化是地图学的重要目标之一,也是当前研究的热点问题之一,对地球空间信息科学的发展具有十分重要的意义。通过采用Representation技术,以昆明市入滇河道(管线)专题地图制图项目为例,研究探讨基于规则化数据驱动的计算机地图制图表达,部分解决了传统上必须通过大量人工编辑才能够完成的制图任务,特别是实现了传统上需要以破坏数据的GIS属性为代价才能够实现的地图制图效果,结果表明:基于规则驱动的计算机地图制图表达技术能够兼顾GIS和地图制图对数据的不同要求,可快速完成地图制作,并达到传统地图制图效果,节省大量的人力物力,具有广阔的推广和工程应用价值。     

A land use/land cover change geospatial cyberinfrastructure to integrate big data and temporal topology

ABSTRACT

Big data have shifted spatial optimization from a purely computational-intensive problem to a data-intensive challenge. This is especially the case for spatiotemporal (ST) land use/land cover change (LUCC) research. In addition to greater variety, for example, from sensing platforms, big data offer datasets at higher spatial and temporal resolutions; these new offerings require new methods to optimize data handling and analysis. We propose a LUCC-based geospatial cyberinfrastructure (GCI) that optimizes big data handling and analysis, in this case with raster data. The GCI provides three levels of optimization. First, we employ spatial optimization with graph-based image segmentation. Second, we propose ST Atom Model to temporally optimize the image segments for LUCC. At last, the first two domain ST optimizations are supported by the computational optimization for big data analysis. The evaluation is conducted using DMTI (DMTI Spatial Inc.) Satellite StreetView imagery datasets acquired for the Greater Montreal area, Canada in 2006, 2009, and 2012 (534 GB, 60 cm spatial resolution, RGB image). Our LUCC-based GCI builds an optimization bridge among LUCC, ST modelling, and big data.     

中国人口分布的密度分级与重心曲线特征分析

依据2000年全国第五次人口普查数据,利用ArcGIS的空间分析功能,将人口密度图分层显示,并形成中国人口分布图系.在此基础上,建立人口重心曲线,根据人口重心曲线上点的邻近性实施人口密度再分级,由此获得了更具空间集聚特征的人口密度图.基于人口密度分级的多圈层迭加分析表明:随着人口密度增大,人口分布重心逐渐由西北向东南移动,由稀疏趋于稠密,中国人口分布多圈层集聚特征明显.人口重心曲线表明,人口分布总体上是从高密度向低密度分布过渡的,其中在低密度中也有高密度地区分布,高密度地区也有相对稀疏的地区.基于人口重心曲线的中国人口密度再分级表明,中国人口密度可以适度划分为9级,据此可以将中国人口地理分布划分为集聚核心区、高度集聚区、中度集聚区、低度集聚区、一般过渡区、相对稀疏区、绝对稀疏区、极端稀疏区、基本无人区等9大类型区.统计表明,中国3/4以上的人口集中分布在不到1/5的国土面积上,半数以上的国土面积上居住着不到2%的人口,研究结果较好地揭示了中国人口分布的空间规律性.     

A high-performance cellular automata model for urban simulation based on vectorization and parallel computing technology

Cellular automata (CA) models can simulate complex urban systems through simple rules and have become important tools for studying the spatio-temporal evolution of urban land use. However, the multiple and large-volume data layers, massive geospatial processing and complicated algorithms for automatic calibration in the urban CA models require a high level of computational capability. Unfortunately, the limited performance of sequential computation on a single computing unit (i.e. a central processing unit (CPU) or a graphics processing unit (GPU)) and the high cost of parallel design and programming make it difficult to establish a high-performance urban CA model. As a result of its powerful computational ability and scalability, the vectorization paradigm is becoming increasingly important and has received wide attention with regard to this kind of computational problem. This paper presents a high-performance CA model using vectorization and parallel computing technology for the computation-intensive and data-intensive geospatial processing in urban simulation. To transfer the original algorithm to a vectorized algorithm, we define the neighborhood set of the cell space and improve the operation paradigm of neighborhood computation, transition probability calculation, and cell state transition. The experiments undertaken in this study demonstrate that the vectorized algorithm can greatly reduce the computation time, especially in the environment of a vector programming language, and it is possible to parallelize the algorithm as the data volume increases. The execution time for the simulation of 5-m resolution and 3 × 3 neighborhood decreased from 38,220.43 s to 803.36 s with the vectorized algorithm and was further shortened to 476.54 s by dividing the domain into four computing units. The experiments also indicated that the computational efficiency of the vectorized algorithm is closely related to the neighborhood size and configuration, as well as the shape of the research domain. We can conclude that the combination of vectorization and parallel computing technology can provide scalable solutions to significantly improve the applicability of urban CA.     

GIS Investigation of the relationship of sex and season on the population distribution of common bottlenose dolphins (Tursiops truncatus) in Charleston,South Carolina

ABSTRACT

The Charleston Estuarine System Stock (CESS) of common bottlenose dolphins (Tursiops truncatus) has been the focus of population monitoring for the past 20 years. Photo-id studies have determined abundance and survival estimates for this population, which exhibits high site fidelity in this area. However, fine-scale distribution, utilization patterns, and the driving forces behind these patterns are lacking. Using historical photo-id data and a novel application of geographic information system (GIS) analysis, the present study identified core use areas within Charleston Harbor, as well as patterns specific to sexes and seasons. Photo-id data of 319 dolphins sighted 11 times or more during 2004–2009 were analyzed. Heat maps were developed to examine spatial distributions using kernel density estimates (KDE) and were compared between sexes and seasons. Multiple high-density core use areas were identified for this population, with the most noteworthy near the mouth of the harbor toward the Atlantic Ocean. Fine-scale distribution varied across sexes, as well as seasons. Some areas were identified as more specifically inhabited by one sex, while other areas overlapped between sexes. Females were more tightly concentrated within their distribution while males were more dispersed. Although population distribution varied across seasons, sex distributions remained.     

Mapping illegal domestic waste disposal potential to support waste management efforts in Queensland,Australia

Illegal disposal of waste is a significant management issue for contemporary governments because of the hazards posed to both human and ecosystem health. Understanding the complex distribution pattern of illegal waste and the range of economic, environmental and social factors influencing this distribution is valuable for improving the effectiveness and efficiency of waste management efforts. This article examines the applicability of mapping illegal waste disposal in the Sunshine Coast (Queensland, Australia) through the identification and integration of predictive spatial data in a geographic information system. A statistical model of illegal waste disposal was developed using a binary logistic regression analysis to identify explanatory variables suitable for predicting the distribution of illegal waste. Five statistically significant explanatory variables were identified through this analysis: population density, primary land use, distance to the nearest road, waste facility and roadside amenity. The generated statistical model had a predictive success of 86.1% with all indicators suggesting good model fit (χ² = 474.3, P = 0 with df = 22) across the study area. Standardised spatial data on each explanatory variable were combined using a weighted linear combination analysis and the results were classified into five categories from very low to very high illegal waste disposal potentials using the equal interval method. The resultant mapping identified 6.9% of the study area as having very high illegal waste disposal potential, and subsequent validation indicated that 32.9% of known illegal waste disposal sites were located within these areas.     

地理空间元数据关联网络的构建

利用资源描述框架（RDF）设计地理空间元数据关联模型,根据地理空间元数据之间的语义关系和语义相关度的计算,以构建以元数据为节点、元数据之间的语义关系为边、语义相关度为权重的关联网络。在这一网络中,一个节点是一个地理空间元数据的资源描述图,包含属性特征（数据来源、空间特征、时间特征、内容）及其关系特征（元数据之间的语义关系、语义相关度）。实验及其分析表明,地理空间元数据关联网络可以有效地支持地理空间数据语义关联检索、推荐等应用,这与传统的基于关键词的元数据检索方式相比,具有更高的准确度。     

On the distribution of diatoms on cover slips: cause for concern

We investigated the effect of frustule morphology on the distribution of various diatom taxa on microscope cover slips, using an artificial assemblage. Seven diatom morphotypes were processed separately in nitric acid and an eighth morphotype (Chaetoceros muelleri) was processed in Lugol’s. These were mixed into a single assemblage and dried on a cover slip. We then mapped the locations of all 1,664 valves in the debris area, which covered 244.4 mm². The inner half of the debris area (A = 122.2 mm², r ≤ 6.237 mm,), the “Central Region,” contained 1,303 valves (78 % of the total). Each of the eight morphotypes was significantly (p ≤ 0.035) more numerous in the Central Region than in the Marginal Region. In addition, the assemblages in the two Regions were quite distinct: C. muelleri accounted for 19 % of the Central Region diatoms, but 57 % of the Marginal Region ones, whereas Surirella peisonis accounted for 17 and 6 %, respectively. We also considered valve distribution relative to aliquot volume by comparing the number of valves under the proximal 50 μl of the aliquot (r ≤ 4.758 mm) with the number of valves under the distal 50 μl. Four morphotypes were significantly (p < 0.02) more numerous in the Proximal Region. In contrast, valves of C. muelleri were significantly more numerous in the Distal Region (p < 10^?43). Valve distribution may reflect valve morphology, such as spine length and degree of silicification. Also important may be other environmental variables, such as the abundance and size of sediment particles. Although preliminary, these data indicate that some taxa are not distributed randomly on cover slips, especially valves that have long spines, thin walls, or thick walls. Whereas many natural assemblages lack such morphotypes, investigators must be aware of such potential heterogenous distributions when counting.     

Classifying urban land use by integrating remote sensing and social media data

Urban land use information plays an important role in urban management, government policy-making, and population activity monitoring. However, the accurate classification of urban functional zones is challenging due to the complexity of urban systems. Many studies have focused on urban land use classification by considering features that are extracted from either high spatial resolution (HSR) remote sensing images or social media data, but few studies consider both features due to the lack of available models. In our study, we propose a novel scene classification framework to identify dominant urban land use type at the level of traffic analysis zone by integrating probabilistic topic models and support vector machine. A land use word dictionary inside the framework was built by fusing natural–physical features from HSR images and socioeconomic semantic features from multisource social media data. In addition to comparing with manual interpretation data, we designed several experiments to test the land use classification accuracy of our proposed model with different combinations of previously acquired semantic features. The classification results (overall accuracy = 0.865, Kappa = 0.828) demonstrate the effectiveness of our strategy that blends features extracted from multisource geospatial data as semantic features to train the classification model. This method can be applied to help urban planners analyze fine urban structures and monitor urban land use changes, and additional data from multiple sources will be blended into this proposed framework in the future.     

Geospatial Analysis of Space–Time Patterning of ENSO Forced Daily Precipitation Distributions in the Gulf of Mexico

The Gulf of Mexico experiences significant changes in the distribution of daily precipitation totals that are linked to the El Niño–Southern Oscillation (ENSO). This research uses geospatial techniques to examine distribution patterns of ENSO-related precipitation. Kolmogorov–Smirnov test results comparing daily rainfall distributions for El Niño and La Niña are mapped at a 1° × 1° latitude/longitude resolution, and hotspot analysis using local Moran's I is performed to identify spatial clustering. Results indicate that ENSO-forced spatial and temporal variation in daily precipitation distributions influence large areas of the Gulf of Mexico region from August through January.