Geographically neural network weighted regression for the accurate estimation of spatial non-stationarity

ABSTRACT

Geographically weighted regression (GWR) is a classic and widely used approach to model spatial non-stationarity. However, the approach makes no precise expressions of its weighting kernels and is insufficient to estimate complex geographical processes. To resolve these problems, we proposed a geographically neural network weighted regression (GNNWR) model that combines ordinary least squares (OLS) and neural networks to estimate spatial non-stationarity based on a concept similar to GWR. Specifically, we designed a spatially weighted neural network (SWNN) to represent the nonstationary weight matrix in GNNWR and developed two case studies to examine the effectiveness of GNNWR. The first case used simulated datasets, and the second case, environmental observations from the coastal areas of Zhejiang. The results showed that GNNWR achieved better fitting accuracy and more adequate prediction than OLS and GWR. In addition, GNNWR is applicable to addressing spatial non-stationarity in various domains with complex geographical processes.     

Defining agents' behaviour based on urban economic theory to simulate complex urban residential dynamics

In recent years, agent-based models (ABMs) have become a prevalent approach for modelling complex urban systems. As a class of bottom-up method, ABMs are capable of simulating the decision-making as well as the multiple interactions of autonomous agents and between agents and the environment. The definition of agents' behaviour is a vital issue in implementing ABMs to simulate urban dynamics. Urban economic theory has provided effective ways to cope with this problem. This theory argues that the formation of urban spatial structure is an endogenous process resulting from the interactions among individual actors that are spatially distributed. However, this theory is used to explain urban phenomena regardless of spatial heterogeneity in most cases. This study combines GIS, ABM and urban economic models to simulate complex urban residential dynamics. The time-extended model is incorporated into an ABM so as to define agents' behaviour on a solid theoretical basis. A spatial variable is defined to address the neighbourhood effect by considering spatial heterogeneity. The proposed model is first verified by the simulation of three scenarios using hypothetical data: (1) single dominated preference; (2) varying preferences on the basis of income level; and (3) spatially heterogeneous environment. Then the model is implemented by simulating the residential dynamics in Guangzhou, China.     

Efficiently implementable algebra for distributed in-network spatial analysis

Existing sensor network query processors (SNQPs) have demonstrated that in-network processing is an effective and efficient means of interacting with wireless sensor networks (WSNs) for data collection tasks. Inspired by these findings, this article investigates the question as to whether spatial analysis over WSNs can be built upon established distributed query processing techniques, but, here, emphasis is on the spatial aspects of sensed data, which are not adequately addressed in the existing SNQPs. By spatial analysis, we mean the ability to detect topological relationships between spatially referenced entities (e.g. whether mist intersects a vineyard or is disjoint from it) and to derive representations grounded on such relationships (e.g. the geometrical extent of that part of a vineyard that is covered by mist). To support the efficient representation, querying and manipulation of spatial data, we use an algebraic approach. We revisit a previously proposed centralized spatial algebra comprising a set of spatial data types and a comprehensive collection of operations. We have redefined and re-conceptualized the algebra for distributed evaluation and shown that it can be efficiently implemented for in-network execution. This article provides rigorous, formal definitions of the spatial data types, points, lines and regions, together with spatial-valued and topological operations over them. The article shows how the algebra can be used to characterize complex and expressive topological relationships between spatial entities and spatial phenomena that, due to their dynamic, evolving nature, cannot be represented a priori.     

A Method for the Exploratory Analysis of Airline Networks

The airline industry in the United States has experienced significant changes in the spatial configuration of networks since the Airline Deregulation Act of 1978. Attempts have been made to study the structure of the hub-and-spoke network in the airline industry, but no efficient methodology has been available. This paper describes an exploratory approach to analyzing the spatial configuration of airline networks. Flight frequencies and numbers of passengers from published schedules of six U.S. domestic airlines (American, Continental, Delta, Northwest, United, and USAir) are used in this study. The analytic components in the exploratory system include the examination of network connectivity and network autocorrelation in a dynamic mapping environment. The results of the analyses show both the overall spatial patterns of airline networks and the hierarchical hubbing structures.     

Understanding spatial structures and organizational patterns of city networks in China: A highway passenger flow perspective

The use of multi-perspective and multi-scalar city networks has gradually developed into a range of critical approaches to understand spatial interactions and linkages. In particular, road linkages represent key characteristics of spatial dependence and distance decay, and are of great significance in depicting spatial relationships at the regional scale. Therefore, based on highway passenger flow data between prefecture-level administrative units, this paper attempted to identify the functional structures and regional impacts of city networks in China, and to further explore the spatial organization patterns of the existing functional regions, aiming to deepen our understanding of city network structures and to provide new cognitive perspectives for ongoing research. The research results lead to four key conclusions. First, city networks that are based on highway flows exhibit strong spatial dependence and hierarchical characteristics, to a large extent spatially coupled with the distributions of major megaregions in China. These phenomena are a reflection of spatial relationships at regional scales as well as core-periphery structure. Second, 19 communities that belong to an important type of spatial configuration are identified through community detection algorithm, and we suggest they are correspondingly urban economic regions within urban China. Their spatial metaphors include the administrative region economy, spatial spillover effects of megaregions, and core-periphery structure. Third, each community possesses a specific city network system and exhibits strong spatial dependence and various spatial organization patterns. Regional patterns have emerged as the result of multi-level, dynamic, and networked characteristics. Fourth, adopting a morphology-based perspective, the regional city network systems can be basically divided into monocentric, dual-nuclei, polycentric, and low-level equilibration spatial structures, while most are developing monocentrically.     

基于公路客流的中国城市网络结构与空间组织模式（英文）

The use of multi-perspective and multi-scalar city networks has gradually developed into a range of critical approaches to understand spatial interactions and linkages. In particular, road linkages represent key characteristics of spatial dependence and distance decay, and are of great significance in depicting spatial relationships at the regional scale. Therefore, based on highway passenger flow data between prefecture-level administrative units, this paper attempted to identify the functional structures and regional impacts of city networks in China, and to further explore the spatial organization patterns of the existing functional regions, aiming to deepen our understanding of city network structures and to provide new cognitive perspectives for ongoing research. The research results lead to four key conclusions. First, city networks that are based on highway flows exhibit strong spatial dependence and hierarchical characteristics, to a large extent spatially coupled with the distributions of major megaregions in China. These phenomena are a reflection of spatial relationships at regional scales as well as core-periphery structure. Second, 19 communities that belong to an important type of spatial configuration are identified through community detection algorithm, and we suggest they are correspondingly urban economic regions within urban China. Their spatial metaphors include the administrative region economy, spatial spillover effects of megaregions, and core-periphery structure. Third, each community possesses a specific city network system and exhibits strong spatial dependence and various spatial organization patterns. Regional patterns have emerged as the result of multi-level, dynamic, and networked characteristics. Fourth, adopting a morphology-based perspective, the regional city network systems can be basically divided into monocentric, dual-nuclei, polycentric, and low-level equilibration spatial structures, while most are developing monocentrically.     

Agent-based modeling within a cyberinfrastructure environment: a service-oriented computing approach

Agent-based models (ABM) allow for the bottom-up simulation of dynamics in complex adaptive spatial systems through the explicit representation of pattern–process interactions. This bottom-up simulation, however, has been identified as both data- and computing-intensive. While cyberinfrastrucutre provides such support for intensive computation, the appropriate management and use of cyberinfrastructure (CI)-enabled computing resources for ABM raise a challenging and intriguing issue. To gain insight into this issue, in this article we present a service-oriented simulation framework that supports spatially explicit agent-based modeling within a CI environment. This framework is designed at three levels: intermodel, intrasimulation, and individual. Functionalities at these levels are encapsulated into services, each of which is an assembly of new or existing services. Services at the intermodel and intrasimulation levels are suitable for generic ABM; individual-level services are designed specifically for modeling intelligent agents. The service-oriented simulation framework enables the integration of domain-specific functionalities for ABM and allows access to high-performance and distributed computing resources to perform simulation tasks that are often computationally intensive. We used a case study to investigate the utility of the framework in enabling agent-based modeling within a CI environment. We conducted experiments using supercomputing resources on the TeraGrid – a key element of the US CI. It is indicated that the service-oriented framework facilitates the leverage of CI-enabled resources for computationally intensive agent-based modeling.     

Agent-based model of land system: Theory,application and modelling framework

Land change science has become an interdisciplinary research direction for understanding human-natural coupling systems. As a process-oriented modelling approach, agent based model(ABM) plays an important role in revealing the driving forces of land change and understanding the process of land change. This paper starts from three aspects: The theory, application and modeling framework of ABM. First, we summarize the theoretical basis of ABM and introduce some related concepts. Then we expound the application and development of ABM in both urban land systems and agricultural land systems, and further introduce the case study of a model on Grain for Green Program in Hengduan Mountainous region, China. On the basis of combing the ABM modeling protocol, we propose the land system ABM modeling framework and process from the perspective of agents. In terms of urban land use, ABM research initially focused on the study of urban expansion based on landscape, then expanded to issues like urban residential separation, planning and zoning, ecological functions, etc. In terms of agricultural land use, ABM application presents more diverse and individualized features. Research topics include farmers' behavior, farmers' decision-making, planting systems, agricultural policy, etc. Compared to traditional models, ABM is more complex and difficult to generalize beyond specific context since it relies on local knowledge and data. However, due to its unique bottom-up model structure, ABM has an indispensable role in exploring the driving forces of land change and also the impact of human behavior on the environment.     

土地系统多主体模型的理论与应用

土地变化科学是理解人类—自然耦合系统的交叉学科研究方向。多主体模型（ABM）作为过程导向模型,对揭示土地变化驱动力,理解土地变化过程有重要作用。本文从理论、应用与建模框架三方面出发,总结了ABM理论基础和相关概念;阐述了ABM在城市和农业土地系统两方面的应用与发展,进一步介绍了横断山区退耕还林ABM研究案例;在梳理ABM建模协议的基础上,提出了主体视角的土地系统ABM建模框架和实施流程。在城市土地利用方面,ABM研究从最初基于景观研究城市扩张,到研究城市内部居住分隔,规划分区,生态功能等多方面;在农业土地利用方面,ABM应用则呈现出更加多样化和个性化的特征,包括农民行为、农户决策、种植系统、农业政策等。相比于传统模型,ABM因其依靠本地知识与数据而使得其构建更为复杂,且不易推广;但因其独特的自下而上模型构架,在探究土地变化驱动力、刻画人类行为对自然环境影响等方面具有不可或缺的作用。     

A cost path and network analysis methodology to calculate distances along a complex river network in the Peruvian Amazon

Distance is a key variable in explicating environmental, social, and economic conditions and in defining spatial and temporal patterns. Prior research has primarily focused on using simple to complex algorithms for calculating distances along road networks. In contrast, few algorithms are available for distance calculations along fluvial networks which are often more erratic, divergent and transient than road networks. Fluvial transportation is relied upon worldwide, particularly in developing regions, where communities use river networks for transportation, access to natural resources and for trade and commerce. This paper presents a methodology developed for mapping complex fluvial networks for travel distance analysis. The methodology was applied in four major river basins in western Amazonia over some 35,000 km of river length and incorporating 919 communities as origins/destinations. A cost path and network analysis methodology was created using vector and raster datasets in a Geographic Information System (GIS) to assess interactions among communities and the distances traveled by river to reach district capitals, major urban centres and marketplaces. An accuracy assessment using distance values calculated from a previous study using a different methodological approach in the region as well as Google Earth Pro, found a high degree of concordance for distance calculations. Our methodology creates a very flexible approach for complex river systems that can be use to calculate river distances in an adaptive and efficient manner and that can be use in other regions of the world where rural communities must rely on rivers for transportation.     

Simulating the spatial diffusion of memes on social media networks

This article reports the findings from simulating the spatial diffusion processes of memes over social media networks by using the approach of agent-based modeling. Different from other studies, this article examines how space and distance affect the diffusion of memes. Simulations were carried out to emulate and to allow assessment of the different levels of efficiency that memes spread spatially and temporally. Analyzed network structures include random networks and preferential attachment networks. Simulated spatial processes for meme diffusion include independent cascade models and linear threshold models. Both simulated and real-world social networks were used in the analysis. Findings indicate that the numbers of information sources and opinion leaders affect the processes of meme diffusion. In addition, geography is still important in the processes of spatial diffusion of memes over social media networks.     

Diverging Narratives: Evaluating the Uses of the Ideal-Typical Sequence of Transport Network Development

Abstract

The development of new transport systems has been an important and highly visible component of economic development and spatial reorganization in the past two centuries. The Ideal-Typical Sequence of network development has been a widely used model of transport development. This paper shows that this model has been used in several different ways, with different notions regarding the appropriate use, interpretation, and limitations of the model over time. Students must therefore think critically about ongoing changes to transport and communications systems and their impacts on economic and social conditions, as well as how these impacts are represented in models.     

Constructing personalized transportation networks in multi-state supernetworks: a heuristic approach

An integrated view encompassing the networks for public and private transport modes as well as the activity programs of travelers is essential for accessibility analysis. In earlier research, the multi-state supernetwork has been put forward by the authors as a suitable technique to model the system in such an integrated fashion. An essential part of a supernetwork involving multi-modal and multi-activity is the personalized transportation network, which is an under-researched topic in the academic community. This article attempts to develop a heuristic approach to construct personalized transportation networks for an individual's activity program. In this approach, the personalized network consists of two types of network extractions from the original transportation system: public transport network and private vehicle network. Three examples are presented to illustrate that the public transport network and private vehicle network can represent an individual's attributes and be applied in large-scale applications for analyzing the synchronization of land-use and transportation systems.     

灾害链灾情累积放大研究方法进展

近年来全球范围内频发的重大自然灾害事件,表明一种灾害引发一系列次生灾害的灾害链现象使得灾情通过累积放大效应而大大超过单一灾种灾情,深入研究灾害链灾情累积放大过程是有效防范巨灾风险的前提.首先,本文梳理了国内外研究中不同视角下对灾害链现象的理解,认为灾害链一般性概念中应当包含孕灾环境、致灾因子链、承灾体以及它们在时间和空间上复杂相互作用关系,只有从地理学的综合性角度出发,才能正确而完整的理解灾害链过程灾情累积放大机制.其次,按研究思路的差异,综述了当前研究灾害链灾情累积放大过程的5 类方法,包括经验地学统计方法、概率模型、复杂网络模型、灾害模拟以及多学科理论方法.从描述灾害链要素在时间和空间上复合作用的角度出发,分别讨论了它们在刻画灾害链灾情放大过程中的优势与不足.选取了影响较大、灾害引发关系典型的地震灾害链与台风灾害链,从灾种维度综述上述几种方法在实际应用中的概况及进展.最后,提出综合多种方法发展与完善灾害链灾情累积放大效应过程的动态模拟是灾害链的研究趋势,其中关键在于模拟灾害链系统各要素的时间与空间上的耦合,研究思路从“静态—描述—解释”向“动态—过程—模拟”的转变是理解灾害链、灾害系统复杂性的重要途径.     

A novel residual graph convolution deep learning model for short-term network-based traffic forecasting

ABSTRACT

Short-term traffic forecasting on large street networks is significant in transportation and urban management, such as real-time route guidance and congestion alleviation. Nevertheless, it is very challenging to obtain high prediction accuracy with reasonable computational cost due to the complex spatial dependency on the traffic network and the time-varying traffic patterns. To address these issues, this paper develops a residual graph convolution long short-term memory (RGC-LSTM) model for spatial-temporal data forecasting considering the network topology. This model integrates a new graph convolution operator for spatial modelling on networks and a residual LSTM structure for temporal modelling considering multiple periodicities. The proposed model has few parameters, low computational complexity, and a fast convergence rate. The framework is evaluated on both the 10-min traffic speed data from Shanghai, China and the 5-min Caltrans Performance Measurement System (PeMS) traffic flow data. Experiments show the advantages of the proposed approach over various state-of-the-art baselines, as well as consistent performance across different datasets.     

A spatial fuzzy influence diagram for modelling spatial objects’ dependencies: a case study on tree-related electric outages

Spatial objects can be interconnected and mutually dependent in complex ways. In Geographical Information Science, spatial objects’ topological relationships are not discussed together with their attributes’ dependencies, and the vagueness of spatial objects is often ignored during the spatial modelling process. To address this, a spatial fuzzy influence diagram (SFID) is introduced. Compared to the traditional statistical or fuzzy modelling approach, the influence diagram brings advantages in helping decision-makers structure complex interdependency problems. A questionnaire was developed to evaluate the applicability of using an influence diagram in modelling spatial objects’ dependencies. As a case study, an SFID is applied to tree-related electric outages. The result of the case study is represented as a vulnerability map of electrical networks. The map shows areas at risk due to tree-related electric outages. The results were first validated by using a visual comparison of the vulnerability map and electricity fault data. In the second validation step, the percentage of fault data, which has received values in different vulnerability categories, was calculated. The results of the case study can be used to support the decision-making process of electrical network maintenance and planning.     

土地变化模型方法综述

土地系统变化长期以来不仅是地理学研究热点,也是资源环境经济学、生态学、城市规划等多学科领域关注的主题。构建模型模拟土地变化能够促进理解人地相互作用机制,模拟结果可为土地资源优化与资源环境政策制定提供依据。不同研究者基于不同学科理论、应用多种方法构建土地变化模型,模型从早期关注自然覆被类型变化发展到对人类决策行为的刻画,从统计方法发展到更突出空间分布的元胞自动机方法,以及更聚焦土地变化过程的经济学方法和多主体方法。未来土地变化模型发展方向为：在多尺度进行多方法耦合,对土地变化过程进行更为明晰地刻画,将土地变化模型与其他地球系统模型耦合等方面,进一步能够促进解释复杂人地系统,并推进模型在决策支持层面的应用。     

城市网络联系对城市群空间体系集聚水平的影响——基于2003—2018年中国12个城市群面板数据的实证

本文分析了2003—2018年中国12个规模较大的城市群的空间体系特征及其变动趋势,并借助城际投资联系数据,分析了各城市群城市网络特征,实证检验了城市网络联系度对城市群空间体系集聚水平的影响。研究发现,2003—2018年城市群空间体系总体呈均衡化发展趋势,且不同城市群城市网络特征差异明显,按发育程度可以分为四种类型：联系紧密-结构均衡-强中心带动型城市网络,联系紧密-弱中心带动-相对开放型城市网络,结构均衡但联系相对较弱型城市网络,以及联系相对较弱且结构极化型城市网络。实证结果证实了城市网络联系的紧密程度和连通度的提高有利于降低城市群空间体系的极化水平,城市网络联系带来的外部性有助于避免城市群空间体系的过度极化及由此带来的集聚负外部性,实现更加均衡的城市群空间结构。但城市网络联系对城市群空间体系均衡化发展的作用依赖于城市网络的结构特征,城市网络结构的极化对城市群空间体系均衡化发展存在抑制作用。     

多元交通流视角下的空间级联系统比较与地理空间约束

交通运输联系是区域空间级联系统与城市体系结构研究的重要视角之一,而不同交通运输方式表达的级联体系结构亦存在一定的差异。为综合研究交通运输体系刻画的空间级联系统及克服单一交通方式的局限性,基于长途汽车、高铁和航班时刻表数据,比较分析了多元交通网络的空间级联体系结构及其表达的城市网络组织体系,并进一步揭示了地理空间的约束作用。研究发现：① 每种交通运输方式适合在一定的空间尺度和行政范围内刻画和表达城市网络体系结构与城市联系,公路客运受省域行政范围约束,高铁联系具有廊道影响效应,航空运输体现全国和区域尺度较高层次的社会经济联系。② 从旅客直达视角分析,长途汽车与高铁的城际运输市场重叠最大,近年来长途汽车的运输市场受高铁影响明显。③ 地理空间是影响陆路交通运输和组织的重要约束因子,距离衰减效应明显;结合设施空间、行政空间和管理体制的作用,长途汽车和高铁运输在空间上形成分异的社区结构;航空运输由于具有超空间连接特性,既不遵循距离衰减规律,社区结构也并不明显。