Suzana Dragicevic

Simon Fraser University · Department of Geography

The theoretical paradigm of geographic automata systems (GAS) underpins a wide range of studies to represent dynamic complex geospatial phenomena. Specifically, cellular automata (CA) were used extensively over the past 40 years for geospatial applications, though primarily for modeling urban growth. Currently, the hyper-specialized and fragmented...

Spatial multi‐criteria evaluation (MCE) techniques aid urban planning management by analyzing decision problem alternatives for solutions to help inform decision‐making. However, there is a lack of such methods that incorporate the temporal dimension, an important factor when analyzing the dynamic urban landscape and decisions surrounding its chang...

Unaddressed imbalance of multitemporal land cover (LC) data reduces deep learning (DL) model usefulness to forecast changes. To manage geospatial data imbalance, there is a lack of specialized cost-sensitive learning strategies available. Sample weights are typically derived from training instance frequencies which disregard spatial pattern complex...

Deforestation as a land-cover change process is linked to several environmental problems including desertification, biodiversity loss, and ultimately climate change. Understanding the land-cover change process and its relation to human–environment interactions is important for supporting spatial decisions and policy making at the global level. Howe...

Several complex dynamic spatial systems are operating on the global scale. Their representation with existing geosimulation models is limited to planar level and do not consider the curvature of the Earth's surface. Thus, the objective of this study is to propose and develop a spherical geographic automata (SGA) modeling approach to represent and s...

Marine spatial planning processes require integrating diverse opinions, knowledge, and goals of multiple stakeholders as well as large volumes of environmental data. Multicriteria evaluation (MCE) methods have been used to combine spatial data in a way that represents stakeholder preferences; however, conventional methods are limited in their abili...

Existing geosimulation land-use change models are predominantly designed to operate at local or regional spatial scales. When these models are applied on data at the global level, they do not consider the effects of spatial distortions caused by the curvature of the Earth’s surface and often lack some refinements related to land suitability analysi...

An open problem impeding the use of deep learning (DL) models for forecasting land cover (LC) changes is their bias toward persistent cells. By providing sample weights for model training, LC changes can be allocated greater influence in adjustments to model internal parameters. The main goal of this research study was to implement and evaluate tem...

Land cover change (LCC) studies are increasingly using deep learning (DL) modeling techniques. Past studies have leveraged temporal or spatiotemporal sequences of historical LC data to forecast changes with DL models. However, these studies do not adequately assess the association between neighborhood size and DL model capability to forecast LCCs,...

As many urban areas undergo increasing densification, there is a growing need for methods that can extend spatial analysis and decision-making for three-dimensional (3D) environments. Traditional multicriteria evaluation (MCE) methods implemented within geographic information systems (GIS) can assist in spatial decision-making but are rarely suited...

Urban Densification Suitability Analysis (UDSA) approach has been proposed using the GIS-based Logic Scoring of Preference (LSP) decision method. Our goal is to provide the methodology for the evaluation of suitability of locations for high density urban development to facilitate the spatial decision-making process and help justifiable urban planni...

An emerging priority in marine noise pollution research is identifying marine “acoustic refugia” where noise levels are relatively low and good-quality habitat is available to acoustically sensitive species. The endangered Southern Resident population of killer whales (Orcinus orca) that inhabits the transboundary Salish Sea in Canada and the USA a...

Social systems are inherently complex and can be represented using agent-based modelling (ABM) methods. Based on the innovative work of Thomas Schelling, ABMs are used to represent, analyze, and forecast emergent spatial-temporal dynamics of residential segregation. Segregation is modelled by representing the complex dynamics between individual age...

This research study extends the Logic Scoring of Preference (LSP) as a general multicriteria evaluation (MCE) method by presenting and evaluating a new GIS.LSP method and software tool implemented within the geographic information systems (GIS) environment. For the evaluation and validation of the method and software tool, we describe a case study...

Recurrent Neural Networks (RNNs), including Long Short-Term Memory (LSTM) architectures, have obtained successful outcomes in timeseries analysis tasks. While RNNs demonstrated favourable performance for Land Cover (LC) change analyses, few studies have explored or quantified the geospatial data characteristics required to utilize this method. Like...

Map comparisons in three‐dimensional space (3D) and 3D time series (4D) are becoming a necessity with increased availability of multidimensional data and model simulation outputs. Therefore, this research study extends the two‐dimensional (2D) map comparison methods with the aim to propose a suite of 3D approaches such as 3D Kappa, 3D Fuzzy, and 4D...

Long‐term residential segregation can exacerbate social inequality and exclusion in urban populations. Existing models of segregation aim to represent and better understand drivers of segregation and assess possible segregation effects in response to incoming immigrant populations. However, these studies are not typically implemented on real geospa...

Complex systems modeling approaches offer the means to examine the way in which local interactions between system components form emergent systems. Using these bottom‐up modeling approaches in combination with geographic information systems (GIS) and geospatial data, the complexity inherent to spatial phenomena including geographical, urban, ecolog...

Many real-world spatial systems can be conceptualized as networks. In these conceptualizations, nodes and links represent system components and their interactions, respectively. Traditional network analysis applies graph theory measures to static network datasets. However, recent interest lies in the representation and analysis of evolving networks...

Agent-based models (ABM) are used to represent a variety of complex systems by simulating the local interactions between system components from which observable spatial patterns at the system-level emerge. Thus, the degree to which these interactions are represented correctly must be evaluated. Networks can be used to discretely represent and quant...

Land cover change (LCC) is typically characterized by infrequent changes over space and time. Data-driven methods such as deep learning (DL) approaches have proven effective in many domains for predictive and classification tasks. When applied to geospatial data, sequential DL methods such as long short-term memory (LSTM) have yielded promising res...

Land use change (LUC) is a dynamic process that significantly affects the environment, and various approaches have been proposed to analyze and model LUC for sustainable land use management and decision making. Recurrent neural network (RNN) models are part of deep learning (DL) approaches, which have the capability to capture spatial and temporal...

Web-mapping has been widely used to facilitate citizen participation in smart cities. Web-mapping has evolved from 2D static maps towards more dynamic and immersive 3D worlds such as virtual globes and scenes. Although current technologies allow us to build multidimensional representations, there is still a lack of research studies on how to furthe...

Dynamic geospatial complex systems are inherently four‐dimensional (4D) processes and there is a need for spatio‐temporal models that are capable of realistic representation for improved understanding and analysis. Such systems include changes of geological structures, dune formation, landslides, pollutant propagation, forest fires, and urban densi...

Convolutional neural networks (CNN) have been used increasingly in several land-use classification tasks, but there is a need to further investigate its potential. This study aims to evaluate the performance of CNN methods for land classification and to identify land-use (LU) change. Eight transferred CNN-based models were fully evaluated on remote...

Scientific research skills can be a valuable asset for undergraduate students pursuing spatial modeling and geographic information science courses. These skills provide students with a systematic means to think critically, solve complex geospatial problems, and contribute in meaningful ways to the scientific knowledge creation and dissemination pro...

Almost all spatial systems can be modelled as networks. Typically, networks representations of real systems are static, useful for generating descriptive network measures. However, recent interest lies in the representation and analysis of evolving spatial networks that can facilitate the examination of the close coupling between network structure...

Landscape connectivity networks are composed of nodes representing georeferenced habitat patches that link together based on a species’ maximum dispersal distance. These static representations cannot capture the complexity in species dispersal where the network of habitat patch nodes changes structure over time as a function of local dispersal dyna...

One of the main tasks of data-driven modelling methods is to induce representative model of underlying spatial - temporal processes based on former-historical data and data mining approach. As relatively new methods, capable of solving complex nonlinear problems, like the land use changes/cover (LULC) and urban growth, their applications are attrac...

Multicriteria Evaluation (MCE) is a commonly used approach for creating suitability maps in a raster-based Geographic Information System (GIS) computing environment. MCE aggregation can be performed by a linear additive model known as the Weighted Linear Combination (WLC) or Simple Additive Scoring. The WLC uses normalized weights that allow decisi...

The representation of land use change (LUC) is often achieved using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN) and Support Vector Machines (SVM) for LUC modeling, to compare these three ML techniques and...

Numerous North American cities are experiencing constant population growth in regions with limited available land, encouraging urban densification processes with development in the vertical direction. Vertical urban development (VUD) is a form of mid- and high- rise building development, that supports urban compactness and is inherently a three-dim...

The issues of error, uncertainty, and representations in geospatial data have also increased the demand to use fuzzy set theory so as to better characterize the real nature of geographical boundaries and phenomena. This entry provides a summary of fuzzy sets and their application in a geospatial data context. Fuzzy classification and reasoning are...

A need exists for expanding agricultural lands due to increased demand for food production and security. Some regions can convert available land to agricultural land use. To evaluate available land for future agricultural production, geographic information systems (GIS) and GIS-based multicriteria evaluation (MCE) methods can be used to identify la...

Forest insect infestations behave as complex systems and can be represented using agent-based modeling (ABM) approaches to explore and optimize eradication strategies such as biological control. This study develops novel geospatial agent-based EAB-BioCon model for the interactions of emerald ash borer (EAB) with the parasitoid Tetrastichus planipen...

The raster and vector spatial data models are the most commonly used in geographic information systems (GIS) practice but are insufficient for the representation of dynamic spatiotemporal phenomena that operates in multiple dimensions. Although numerous improvements to the spatial data models have been proposed and various prototype implementations...

Spatial indices are used to quantitatively describe the spatial arrangements of the features within a study region. However, most of the indices used are two-dimensional in their representation of the surface characteristics, and this is insufficient to quantify the three-dimensional properties of an area or geospatial features. With the increased...

The growth of urban areas and industrial intensification has contributed to a reduction in valuable agricultural lands and to various environmental impacts including climate change. This reduction in agricultural land severely impacts food production and food security. In order to effectively address this issue, spatial analytical and optimization...

Insect infestation behaves as a complex system, characterized by non-linear spatial dynamics and emergent patterns that evolve from smaller to larger spatial scales. The emerald ash borer (EAB) is an invasive species that has infested and killed millions of ash trees across North America. Existing EAB models use traditional statistical approaches t...

Many geographic processes evolve in a three dimensional space and time continuum. However, when they are represented with the aid of geographic information systems (GIS) or geosimulation models they are modelled in a framework of two-dimensional space with an added temporal component. The objective of this study is to propose the design and impleme...

Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection...

Big data has now become a strong focus of global interest that is increasingly attracting the attention of academia, industry, government and other organizations. Big data can be situated in the disciplinary area of traditional geospatial data handling theory and methods. The increasing volume and varying format of collected geospatial big data pre...

Land use changes play an important role in interactions between human and physical systems, and have significant impacts on the environment at local, regional and global scales. Land use change is a complex process and so developing dynamic models to represent the process is a challenging task. Decision Trees (DT) is a Machine Learning (ML) method...

Agent-based modeling (ABM) is a bottom-up approach capable of operationalizing complex systems. The approach can be used to reproduce the spatio-temporal patterns in ecological processes such as insect infestation by representing individual dynamics and interactions between "agents" and their environment from which complex behavior emerges. The eme...

Infestations caused by the mountain pine beetle (MPB) can be seen as complex spatio-temporal process with severe ecological impacts on the forest environment. In order to manage and prevent the insect infestation and reduce significant forest loss it is necessary to improve knowledge about the infestation process. The main objective of this researc...

Understanding the driving forces of historical land-use change can provide insights about the pressures experienced in present-day landscapes. This study develops a model to examine the spatio-temporal land-use changes and population responses of early agricultural communities under a variety of environmental and cultural conditions. Complex system...

The Logic Scoring of Preference (LSP) is a general multicriteria decision-making method with origins in soft computing and fuzzy reasoning. It allows the nonlinear aggregation of a large number of input criteria without the loss of significance typical for additive GIS-based MCE methods. The objective of this study is to integrate the LSP method wi...

Environmental processes are usually conceptualized as complex systems whose dynamics are best understood by examining the relationships and interactions of their constituent parts. The cellular automata paradigm, as a bottom-up modeling approach, has been widely used to study the macroscopic behavior of these complex natural processes. However, the...

Increased sedimentation is widely acknowledged to be an important stressor for Caribbean coral reefs. However, for most locations we currently lack both accurate records of changes in sediment accumulation rates over reefs as well as a quantitative link between land-based sources of sediment and sediment delivery to coastal waters. This paper aims...

Landslides can have a severe negative impact on the socio-economic and environmental state of individuals and their communities. Minimizing these impacts is dependent on the effective identification of risk areas using a susceptibility analysis process. In such a process, output maps are generated to determine various levels of threat to human popu...

Emergency evacuations are essential for protecting humans from hazardous events such as wildfires, tsunamis, hurricanes, and industrial accidents. In urban regions, effective emergency management is highly dependent on reliable knowledge about potential traffic congestion hotspots that can arise during an evacuation. Spatially explicit models that...

The representation and modelling of physical and natural systems are mostly implemented using partial differential equations. Physical processes such as flooding, tsunamis, avalanches, earthquakes and landslides undeniably possess complex systems behaviour. Modelling such dynamic phenomena can be adequately addressed by using geocomplexity – comple...

As a landscape changes, so do the flows of matter that run across it. These flows modify the landscape and can thereby alter their own course in a feedback mechanism. This study focuses on one instance of this process: medium-term background soil redistribution induced by sheet erosion. Previous studies that have modelled this phenomenon have eithe...

Mountain pine beetle (Dendroctonus Ponderosae) infestations in Western Canada have reached alarming proportions. The spread of attacks has significantly impacted pine tree stocks, the forest ecosystem in general and the overall socio-economic condition of residents in communities that depend on the forest industry. The ability to track these attack...

Land-use change models grounded in complexity theory such as agent-based models (ABMs) are increasingly being used to examine evolving urban systems. The objective of this study is to develop a spatial model that simulates land-use change under the influence of human land-use choice behavior. This is achieved by integrating the key physical and soc...

Forest insect disturbances have an ecological impact and are the cause of partial or complete stands mortality; hence they influence the forest cover change. The modeling of ecological processes such as insect disturbance is challenging due to the complexity of insect outbreaks in forest ecological systems, thus diverse spatial scales need to be co...

The link between theoretical complexity-based land-use models, more particularly agent-based models, and practical planning support systems (PSS) is not yet fully elaborated in the current literature. Land-use models that use agent-based approaches still need to be improved and robustly tested if they are to be used effectively as a component of PS...

The process of urban land use change is influenced by the interactions of various stakeholders who have conflicting values and priorities. These interactions, which are characterized by a strong competition for advantageous land locations, can be represented by an agent-based model in order to better understand, analyze and forecast possible future...

Many GIS-based landslide models require detailed datasets that are ideally collected from field measurements, which can incur high costs for carrying out surveys. Even when the data is on hand, implementing physics-based slope stability techniques can be difficult. Common research practice uses differential equations to characterize the dynamic flo...

This introductory chapter presents an overview of recent advances in web-based Geographic Information Systems (GIS), mapping services and applications, and identifies some of the issues and challenges faced by researchers and professionals in the field. Primarily driven by current advances in web technologies and the expressed needs from geospatial...

A spectrum of methods exists for investigating and providing solutions for land use change. These methods can be broadly categorized as either 'top-down' or 'bottom-up' approaches according to how land use change is modeled and analyzed. Although there has been much research in recent years advancing the use of these techniques for both theoretical...

The widespread outbreaks of Mountain Pine Beetle (MPB) are responsible for infestations of lodgepole pine forests since 1990 in Canada. In British Columbia, this forest insect disturbance has resulted in losses of more than 13million hectares of pine trees. The complexity of the MPB emergence, aggregation and attack behaviour is captured by this st...

Geographic processes are embedded within complex spatial systems containing multiple interacting variables. These processes have spatial and temporal dynamics that are difficult to represent and model with the standard tools of geographic information systems (GIS) software. Consequently, representing the dynamics of geographic process and accountin...

Space and time are intrinsic components of the decision-making process in natural resource management. Decisions to extract resources from a specific location have consequences for all future decisions as they may lead to profitable opportunities or, conversely, towards unfavorable outcomes. As such, the spatio-temporal nature of decision-making sh...

Spatial optimization and agent-based modeling present two distinct approaches that have been implemented in forest management research for incorporating the objectives of multiple stakeholders. However, challenges arise in their implementation as optimization procedures do not consider the interactions amongst stakeholders, and agent-based models g...

Extensive outbreaks of tree-killing insects have been occurring in many parts of North America, including the province of British Columbia, raising concerns about the health of pine forest ecosystems. The dynamic phenomenon of mountain pine beetle (MPB), Dendroctonus ponderosae Hopkins, infestation outbreaks is an inherent spatial and temporal comp...

The forests of British Columbia, Canada have undergone an unprecedented Mountain Pine Beetle, Dendroctonus ponderosae Hopkins, (MPB) infestation that has resulted in extensive mortality of lodgepole pine, Pinus contorta. The objective of this study is to apply the agent-based model (ABM) to simulate the MPB attack behaviour in order to evaluate how...

The propagation of communicable diseases through a population is an inherent spatial and temporal process of great importance for modern society. For this reason a spatially explicit epidemiologic model of infectious disease is proposed for a greater understanding of the disease's spatial diffusion through a network of human contacts. The objective...

Validation of agent-based models (ABMs) of land-use change is a significant challenge in current spatial-modelling research and application. During the validation process, model performance and accuracy assessment depend mostly on pixel-by-pixel comparisons. However, in urban land-use planning problems the use of vector spatial data to develop ABMs...

Abstract An important component of natural resource management is determining how to allocate resources within a landscape to different stakeholders in a manner that satisfies multiple objectives. Developing decision making tools for assisting natural resource allocation is a challenging endeavor as stakeholders' objectives typically exist at varyi...

Spatio-temporal modeling provides the opportunity to simulate geographic processes of land use and land cover change (LUCC) by integrating geographic information systems (GIS) with various machine learning approaches to computing. Contemporary models are often developed using a training dataset to define a set of probabilistic transition rules that...

Constrained cellular automata (CA) are frequently used for modeling land use change and urban growth. In these models land use dynamics are generated by a set of cell state transition rules that incorporate a neighborhood effect. Generally, neighborhoods are relatively small and therefore only a limited amount of spatial information is included. In...

In this paper we investigate properties of multicriteria methods that are used for building land-use suitability assessment criteria. We identify and describe fundamental properties that are of interest in the land-use suitability analysis and the design of suitability maps. The existing multicriteria methods can be evaluated from the standpoint of...

Background: The propagation of communicable diseases through a population is an inherent spatial and temporal process of great importance for modern society. For this reason a spatially explicit epidemiologic model of infectious disease is proposed for a greater understanding of the disease's spatial diffusion through a network of human contacts. O...

The objective of this study is to integrate agent-based modeling and geographic information systems (GIS) for examining how interactions within forest management lead to patterns of land-cover change. Specifically, this study evaluates how management agents behave in the presence of variable timber prices, harvesting costs, and accessibility to tim...

Information and communication technologies (ICT) have created many new opportunities for teaching, learning and administration. This study elaborates a new embedded collaborative systems (ECS) model to structure and manage the implementation of ICT-based pedagogies in a blended learning environment. Constructivist learning, systems theory, and mult...

This study was aimed at detecting the spatial characteristics of forest floor properties and litterfall amounts related to bigleaf maple (Acer macrophyllum Pursh) within conifer forest. Two 36-m x 36-m plots, centered on individual dominant bigleaf maple stems, were sampled at 129 systematic locations and tested for forest floor pH, cation exchange...

Various difficulties are encountered when integrating spatial and temporal goals of forest planning with dynamics of natural processes. Some of these difficulties stem from the difference between the data and models involved in the various processes to be integrated. The focus of this study is the development of a decentralized spatial decision sup...

The integration of geographic information systems (GIS) and spatio-temporal modeling procedures with Internet technology can significantly improve the decision-making process for environmental and disaster management. The objective of this study is to develop an approach to integrate a cellular automata (CA) forest fire behavior model with the worl...

The interaction spaces between instructors and learners in the traditional face-to-face classroom environment are being changed by the diffusion and adoption of many forms of computer-based pedagogy. An integrated understanding of these evolving interaction spaces together with how they interconnect and leverage learning are needed to develop meani...

The integration of geographic information systems (GIS) and environmental modelling has been widely investigated for more than a decade. However, such integration has remained a challenging task due to the temporal changes of environmental processes and the static nature of GIS. This study integrates GIS and cellular automata (CA) techniques to dev...

This study describes the origins, boundaries, and structures of collaborative geographic information systems (CGIS). A working definition is proposed, together with a discussion about the subtle collaborative vs. cooperative distinction, and culminating in a philosophical description of the research area. The literatures on planning and policy anal...

This chapter describes the origins, boundaries, and structures of collaborative geographic information systems (CGIS). A working definition is proposed, together with a discussion about the subtle collaborative vs. cooperative distinction, and culminating in a philosophical description of the research area. The literatures on planning and policy an...

This study describes the origins, boundaries, and structures of collaborative geographic information systems (CGIS). A working definition is proposed, together with a discussion about the subtle collaborative vs. cooperative distinction, and culminating in a philosophical description of the research area. The literatures on planning and policy anal...