Multi‐scale approach to mining significant spatial co‐location patterns

Spatial co‐location pattern mining aims to discover a collection of Boolean spatial features, which are frequently located in close geographic proximity to each other. Existing methods for identifying spatial co‐location patterns usually require users to specify two thresholds, i.e. the prevalence threshold for measuring the prevalence of candidate co‐location patterns and distance threshold to search the spatial co‐location patterns. However, these two thresholds are difficult to determine in practice, and improper thresholds may lead to the misidentification of useful patterns and the incorrect reporting of meaningless patterns. The multi‐scale approach proposed in this study overcomes this limitation. Initially, the prevalence of candidate co‐location patterns is measured statistically by using a significance test, and a non‐parametric model is developed to construct the null distribution of features with the consideration of spatial auto‐correlation. Next, the spatial co‐location patterns are explored at multi‐scales instead of single scale (or distance threshold) discovery. The validity of the co‐location patterns is evaluated based on the concept of lifetime. Experiments on both synthetic and ecological datasets show that spatial co‐location patterns are discovered correctly and completely by using the proposed method; on the other hand, the subjectivity in discovery of spatial co‐location patterns is reduced significantly.     

A UML‐based Representation of Spatio‐Temporal Evolution in Road Network Data

Geographic features change over time, this change being the result of some kind of event. Most database systems used in GIS are relational in nature, capturing change by exhaustively storing all versions of data, or updates replace previous versions. This stems from the inherent difficulty of modelling geographic objects and associated data in relational tables, and this is compounded when the necessary time dimension is introduced to represent how these objects evolve. This article describes an object‐oriented (OO) spatio‐temporal conceptual data model called the Feature Evolution Model (FEM), which can be used for the development of a spatio‐temporal database management system (STDBMS). Object versioning techniques developed in the fields of Computer Aided Design (CAD) and engineering design are utilized in the design. The model is defined using the Unified Modelling Language (UML), and exploits the expressiveness of OO technology by representing both geographic entities and events as objects. Further, the model overcomes the limitations inherent in relational approaches in representing aggregation of objects to form more complex, compound objects. A management object called the evolved feature maintains a temporally ordered list of references to features thus representing their evolution. The model is demonstrated by its application to road network data.     

Similarity Measurements on Multi‐Scale Qualitative Locations

Qualitative representation of spatial locations and their similarity measurements are essential for the analysis of linguistic term‐based data. Existing methods have focused on the similarities of spatial relations and spatial scenes but have not considered the variations in geometrical representations and relations over scales. This study developed some new measures to assess the similarities of both single‐ and multi‐scale qualitative locations. Region‐ and cell‐based models were used to formalize qualitative locations of spatial objects with respect to multi‐scale frames of reference. The similarities were assessed by integrating the similarities of frames and qualitative relations. The frame similarity measures how two objects are compared considering the common elements that they occupy in the reference frames. Moreover, the similarity of qualitative relation measures how two relations relate two objects to the corresponding elements in the frames. The location similarities at a single level integrate the similarities of the frames and qualitative relations, whereas the location similarities at multiple scales incorporate the variations in qualitative locations over scales. These methods were used to assess location similarities concerning residential areas, roads, and lakes. The results indicated that the location‐based measurements can disclose the distributions of the similarities and that the cell‐based model is more accurate than the region‐based model.     

Multi‐Scale Qualitative Location: A Topology‐Based Model

Qualitative locations describe spatial objects by relating the spatial objects to a frame of reference (e.g. a regional partition in this study) with qualitative relations. Existing models only formalize spatial objects, frames of reference, and their relations at one scale, thus limiting their applicability in representing location changes of spatial objects across scales. A topology‐based, multi‐scale qualitative location model is proposed to represent the associations of multiple representations of the same objects with respect to the frames of reference at different levels. Multi‐scale regional partitions are first presented to be the frames of reference at multiple levels of scale. Multi‐scale locations are then formalized to relate multiple representations of the same objects to the multiple frames of reference by topological relations. Since spatial objects, frames of reference, and topological relations in qualitative locations are scale dependent, scale transformation approaches are presented to derive possible coarse locations from detailed locations by incorporating polygon merging, polygon‐to‐line and polygon‐to‐point operators.     

A Patch‐based Cellular Automaton for Simulating Land‐use Changes at Fine Spatial Resolution

While cellular automata have become popular tools for modeling land‐use changes, there is a lack of studies reporting their application at very fine spatial resolutions (e.g. 5 m resolution). Traditional cell‐based CA do not generate reliable results at such resolutions because single cells might only represent components of land‐use entities (i.e. houses or parks in urban residential areas), while recently proposed entity‐based CA models usually ignore the internal heterogeneity of the entities. This article describes a patch‐based CA model designed to deal with this problem by integrating cell and object concepts. A patch is defined as a collection of adjacent cells that might have different attributes, but that represent a single land‐use entity. In this model, a transition probability map was calculated at each cell location for each land‐use transition using a weight of evidence method; then, land‐use changes were simulated by employing a patch‐based procedure based on the probability maps. This CA model, along with a traditional cell‐based model were tested in the eastern part of the Elbow River watershed in southern Alberta, Canada, an area that is under considerable pressure for land development due to its proximity to the fast growing city of Calgary. The simulation results for the two models were compared to historical data using visual comparison, K_simulation indices, and landscape metrics. The results reveal that the patch‐based CA model generates more compact and realistic land‐use patterns than the traditional cell‐based CA. The K_simulation values indicate that the land‐use maps obtained with the patch‐based CA are in higher agreement with the historical data than those created by the cell‐based model, particularly regarding the location of change. The landscape metrics reveal that the patch‐based model is able to adequately capture the land‐use dynamics as observed in the historical data, while the cell‐based CA is not able to provide a similar interpretation. The patch‐based approach proposed in this study appears to be a simple and valuable solution to take into account the internal heterogeneity of land‐use classes at fine spatial resolutions and simulate their transitions over time.     

An Event‐driven Spatiotemporal Data Model (E‐ST) Supporting Dynamic Expression and Simulation of Geographic Processes

The wide use of various sensors makes real‐time data acquisition possible. A new spatiotemporal data model, the Event‐driven Spatiotemporal Data Model (E‐ST), is proposed to dynamically express and simulate the spatiotemporal processes of geographic phenomena. In E‐ST, a sensor object is introduced into the model as a flexible real‐time data source. An event type that is generating and driving conditions is registered into a geographic object, so an event can not only express spatiotemporal change in a geographic object, but also drive spatiotemporal change in some geographic objects. As a dynamic GIS data model, the E‐ST has five characteristics – Temporality and Spatiality, Real‐time, Extendability, Causality, and Realizability. Described and realized in UML, a test‐case deployment demonstrating the impact of urban waterlogging on traffic confirms that a spatiotemporal change process in a geographic phenomena is expressed and simulated by this model. Summarizing this work, four directions for future research are outlined.     

An intersection‐based trajectory‐region movement study

In order to better understand the movement of an object with respect to a region, we propose a formal model of the evolving spatial relationships that transition between local topologies with respect to a trajectory and a region as well as develop a querying mechanism to analyze movement patterns. We summarize 12 types of local topologies built on trajectory‐region intersections, and derive their transition graph; then we capture and model evolving local topologies with two types of trajectory‐region strings, a movement string and a stop‐move string. The stop‐move string encodes the stop information further during a trajectory than the movement string. Such a string‐format expression of trajectory‐region movement, although conceptually simple, carries unprecedented information for effectively interpreting how trajectories move with respect to regions. We also design the corresponding Finite State Automations for a movement string as well as a stop‐move string, which are used not only to recognize the language of trajectory‐region strings, but also to deal effectively with trajectory‐region pattern queries. When annotated with the time information of stops and intersections, a trajectory‐region movement snapshot and its evolution during a time interval can be inferred, and even the relationships among trajectories with respect to the same region can be explored.     

A New 3‐D Solar Radiation Model for 3‐D City Models

Estimates of solar radiation distribution in urban areas are often limited by the complexity of urban environments. These limitations arise from spatial structures such as buildings and trees that affect spatial and temporal distributions of solar fluxes over urban surfaces. The traditional solar radiation models implemented in GIS can address this problem only partially. They can be adequately used only for 2‐D surfaces such as terrain and rooftops. However, vertical surfaces, such as facades, require a 3‐D approach. This study presents a new 3‐D solar radiation model for urban areas represented by 3‐D city models. The v.sun module implemented in GRASS GIS is based on the existing solar radiation methodology used in the topographic r.sun model with a new capability to process 3‐D vector data representing complex urban environments. The calculation procedure is based on the combined vector‐voxel approach segmenting the 3‐D vector objects to smaller polygon elements according to a voxel data structure of the volume region. The shadowing effects of surrounding objects are considered using a unique shadowing algorithm. The proposed model has been applied to the sample urban area with results showing strong spatial and temporal variations of solar radiation flows over complex urban surfaces.     

Extracting invariant characteristics of sketch maps: Towards place query‐by‐sketch

In geography, invariant aspects of sketches are essential to study because they reflect the human perception of real‐world places. A person's perception of a place can be expressed in sketches. In this article, we quantitatively and qualitatively analyzed the characteristics of single objects and characteristics among objects in sketches and the real world to find reliable invariants that can be used to establish references/correspondences between sketch and world in a matching process. These characteristics include category, shape, name, and relative size of each object. Moreover, quantity and spatial relationships—such as topological, ordering, and location relationships—among all objects are also analyzed to assess consistency between sketched and actual places. The approach presented in this study extracts the reliable invariants for query‐by‐sketch and prioritizes their relevance for a sketch‐map matching process.     

Measuring Dynamic Interaction in Movement Data

The emergence of technologies capable of storing detailed records of object locations has presented scientists and researchers with a wealth of data on object movement. Yet analytical methods for investigating more advanced research questions from such detailed movement datasets remain limited in scope and sophistication. Recent advances in the study of movement data has focused on characterizing types of dynamic interactions, such as single‐file motion, while little progress has been made on quantifying the degree of such interactions. In this article, we introduce a new method for measuring dynamic interactions (termed DI) between pairs of moving objects. Simulated movement datasets are used to compare DI with an existing correlation statistic. Two applied examples, team sports and wildlife, are used to further demonstrate the value of the DI approach. The DI method is advantageous in that it measures interaction in both movement direction (termed azimuth) and displacement. Also, the DI approach can be applied at local, interval, episodal, and global levels of analysis. However the DI method is limited to situations where movements of two objects are recorded at simultaneous points in time. In conclusion, DI quantifies the level of dynamic interaction between two moving objects, allowing for more thorough investigation of processes affecting interactive moving objects.     

Street‐level Spatial Scan Statistic and STAC for Analysing Street Crime Concentrations

This study develops new types of hotspot detection methods to describe the micro‐space variation of the locations of crime incidents at the street level. It expands on two of the most widely used hotspot detection methods, Spatial and Temporal Analysis of Crime and Spatial Scan Statistic, and applies them to the analysis of the network space. The study first describes the conceptual and the methodological framework of the new methods followed by analyses using: (1) a simulated distribution of points along the street network; and (2) real street‐crime incident data. The simulation study using simulated point distributions confirms that the proposed methods is more accurate, stable and sensitive in detecting street‐level hotspots than their conventional counterparts are. The empirical analysis with real crime data focuses on the distribution of the drug markets and robberies in downtown Buffalo, NY in 1995 and 1996. The drug markets are found to form hotspots that are dense, compact and stable whereas hotspots of the robberies are observed more thinly across a wider area. The study also reveals that the location of the highest risk remains on the same spot over time for both types of crimes, indicating the presence of hotbeds which requires further attention.     

A Space‐Time Raster GIS Data Model for Spatiotemporal Analysis of Vegetation Responses to a Freeze Event

Many past space‐time GIS data models viewed the world mainly from a spatial perspective. They attached a time stamp to each state of an entity or the entire area of study. This approach is less efficient for certain spatio‐temporal analyses that focus on how locations change over time, which require researchers to view each location from a temporal perspective. In this article, we present a data model to organize multi‐temporal remote sensing datasets and track their changes at the individual pixel level. This data model can also integrate raster datasets from heterogeneous sources under a unified framework. The proposed data model consists of several object classes under a hierarchical structure. Each object class is associated with specific properties and behaviors to facilitate efficient spatio‐temporal analyses. We apply this data model to a case study of analyzing the impact of the 2007 freeze in Knoxville, Tennessee. The characteristics of different vegetation clusters before, during, and after the 2007 freeze event are compared. Our findings indicate that the majority of the study area is impacted by this freeze event, and different vegetation types show different response patterns to this freeze.     

Urban event detection with big data of taxi OD trips: A time series decomposition approach

Big urban mobility data, such as taxi trips, cell phone records, and geo‐social media check‐ins, offer great opportunities for analyzing the dynamics, events, and spatiotemporal trends of the urban social landscape. In this article, we present a new approach to the detection of urban events based on location‐specific time series decomposition and outlier detection. The approach first extracts long‐term temporal trends and seasonal periodicity patterns. Events are defined as anomalies that deviate significantly from the prediction with the discovered temporal patterns, i.e., trend and periodicity. Specifically, we adopt the STL approach, i.e., seasonal and trend decomposition using LOESS (locally weighted scatterplot smoothing), to decompose the time series for each location into three components: long‐term trend, seasonal periodicity, and the remainder. Events are extracted from the remainder component for each location with an outlier detection method. We analyze over a billion taxi trips for over seven years in Manhattan (New York City) to detect and map urban events at different temporal resolutions. Results show that the approach is effective and robust in detecting events and revealing urban dynamics with both holistic understandings and location‐specific interpretations.     

Building Agent‐Based Walking Models by Machine‐Learning on Diverse Databases of Space‐Time Trajectory Samples

We introduce a novel scheme for automatically deriving synthetic walking (locomotion) and movement (steering and avoidance) behavior in simulation from simple trajectory samples. We use a combination of observed and recorded real‐world movement trajectory samples in conjunction with synthetic, agent‐generated, movement as inputs to a machine‐learning scheme. This scheme produces movement behavior for non‐sampled scenarios in simulation, for applications that can differ widely from the original collection settings. It does this by benchmarking a simulated pedestrian's relative behavioral geography, local physical environment, and neighboring agent‐pedestrians; using spatial analysis, spatial data access, classification, and clustering. The scheme then weights, trains, and tunes likely synthetic movement behavior, per‐agent, per‐location, per‐time‐step, and per‐scenario. To prove its usefulness, we demonstrate the task of generating synthetic, non‐sampled, agent‐based pedestrian movement in simulated urban environments, where the scheme proves to be a useful substitute for traditional transition‐driven methods for determining agent behavior. The potential broader applications of the scheme are numerous and include the design and delivery of location‐based services, evaluation of architectures for mobile communications technologies, what‐if experimentation in agent‐based models with hypotheses that are informed or translated from data, and the construction of algorithms for extracting and annotating space‐time paths in massive data‐sets.     

A time‐geographic approach to quantifying wildlife–road interactions

Recent advances in time geography offer new perspectives for studying animal movements and interactions in an environmental context. In particular, the ability to estimate an animal's spatial location probabilistically at temporal sampling intervals between known fix locations allows researchers to quantify how individuals interact with one another and their environment on finer temporal and spatial scales than previously explored. This article extends methods from time geography, specifically probabilistic space–time prisms, to quantify and summarize animal–road interactions toward understanding related diurnal movement behaviors, including road avoidance. The approach is demonstrated using tracking data for fishers (Martes pennanti) in New York State, where the total probability of interaction with roadways is calculated for individuals over the duration tracked. Additionally, a summarization method visualizing daily interaction probabilities at 60 s intervals is developed to assist in the examination of temporal patterns associated with fishers’ movement behavior with respect to roadways. The results identify spatial and temporal patterns of fisher–roadway interaction by time of day. Overall, the methodologies discussed offer an intuitive means to assess moving object location probabilities in the context of environmental factors. Implications for movement ecology and related conservation planning efforts are also discussed.     

Using Pattern‐oriented Modeling (POM) to Cope with Uncertainty in Multi‐scale Agent‐based Models of Land Change

Local land‐use and ‐cover changes (LUCCs) are the result of both the decisions and actions of individual land‐users, and the larger global and regional economic, political, cultural, and environmental contexts in which land‐use systems are embedded. However, the dearth of detailed empirical data and knowledge of the influences of global/regional forces on local land‐use decisions is a substantial challenge to formulating multi‐scale agent‐based models (ABMs) of land change. Pattern‐oriented modeling (POM) is a means to cope with such process and parameter uncertainty, and to design process‐based land change models despite a lack of detailed process knowledge or empirical data. POM was applied to a simplified agent‐based model of LUCC to design and test model relationships linking global market influence to agents’ land‐use decisions within an example test site. Results demonstrated that evaluating alternative model parameterizations based on their ability to simultaneously reproduce target patterns led to more realistic land‐use outcomes. This framework is promising as an agent‐based virtual laboratory to test hypotheses of how and under what conditions driving forces of land change differ from a generalized model representation depending on the particular land‐use system and location.     

Trajectory Ontologies and Queries

Many real world applications today are built on analyses of movement and related features. Examples of such applications include transportation management, urban planning, tourism services, and animal migration monitoring, among others. Recent database modeling and management research prototypes have the capability to store and manipulate movement data in terms of point or region geometries that evolve over time (moving point or moving and deforming region). This captures the spatio‐temporal trace left by a moving object, but ignores its links with non‐geometric information that enable a semantic interpretation of the movement of moving objects. The concept of trajectory has been introduced to express a more semantic understanding of movement, taking it closer to the perception of applications. This article describes a framework for a semantics‐oriented structuring, modeling and querying of trajectory data. The framework relies on the definition of trajectory‐related ontologies, addressing domain‐independent and application‐specific geometric and semantic facets. Last we briefly discuss how the proposed approach has been applied for a traffic management application.     

Multi‐temporal transport network models for accessibility studies

Vehicle tracking is a spatio‐temporal source of high‐granularity travel time information that can be used for transportation planning. However, it is still a challenge to combine data from heterogeneous sources into a dynamic transport network, while allowing for network modifications over time. This article uses conceptual modeling to develop multi‐temporal transport networks in geographic information systems (GIS) for accessibility studies. The proposed multi‐temporal network enables accessibility studies with different temporal granularities and from any location inside the city, resulting in a flexible tool for transport and urban planning. The implemented network is tested in two case studies that focus on socially excluded people in a large global city, São Paulo, Brazil, including accessibility analyses from slum areas. It explores variations within a day and differences between transport modes across time. Case study results indicate how the accessibility is heterogeneous in low‐income regions.     

Fine‐scale intra‐ and inter‐city commercial store site recommendations using knowledge transfer

The rapid development of urban retail companies brings new opportunities to the Chinese economy. Due to the spatiotemporal heterogeneity of different cities, selecting a business location in a new area has become a challenge. The application of multi‐source geospatial data makes it possible to describe human activities and urban functional zones at fine scale. We propose a knowledge transfer‐based model named KTSR to support citywide business location selections at the land‐parcel scale. This framework can optimize customer scores and study the pattern of business location selection for chain brands. First, we extract the features of each urban land parcel and study the similarities between them. Then, singular value decomposition was used to build a knowledge‐transfer model of similar urban land parcels between different cities. The results show that: (1) compared with the actual scores, the estimated deviation of the proposed model decreased by more than 50%, and the Pearson correlation coefficient reached 0.84 or higher; (2) the decomposed features were good at quantifying and describing high‐level commercial operation information, which has a strong relationship with urban functional structures. In general, our method can work for selecting business locations and estimating sale volumes and user evaluations.