David A. Bennett

Using evolutionary algorithms to generate alternatives for multiobjective site-search problems

Multiobjective site-search problems are a class of decision problems that have geographical components and multiple, often conflicting, objectives; this kind of problem is often encountered and is technically difficult to solve. In this paper we describe an evolutionary algorithm (EA) based approach that can be used to address such problems. We first describe the general design of EAs that can be used to generate alternatives that are optimal or close to optimal with respect to multiple criteria. Then we define the problem addressed in this research and discuss how the EA was designed to solve it. In this procedure, called MOEA/Site, a solution (that is, a site) is encoded by using a graph representation that is operated on by a set of specifically designed evolutionary operations. This approach is applied to five different types of cost surfaces and the results are compared with 10 000 randomly generated solutions. The results demonstrate the robustness and effectiveness of this EA-based approach to geographical analysis and multiobjective decisionmaking. Critical issues regarding the representation of spatial solutions and associated evolutionary operations are also discussed.

A framework for the integration of geographical information systems and modelbase management

Existing geoprocessing technologies lack the modelbase management capabilities needed to construct dynamic simulation models of geographical systems. A geoprocessing framework is presented here that incorporates the fundamental precepts of GIS, computer simulation, modelbase management, and SDSS into an integrated environment that supports the development and use of geographical models. To support this framework the field and object-based geographical data models are extended to include spatial processes and spatial relations. A prototype system was developed to test the utility of this framework and data model.

Modelling adaptive, spatially aware, and mobile agents: Elk migration in Yellowstone

The potential utility of agent‐based models of adaptive, spatially aware, and mobile entities in geographic and ecological research is considerable. Developing this potential, however, presents significant challenges to geographic information science. Modelling the spatio‐temporal behaviour of individuals requires new representational forms that capture how organisms store and use spatial information. New procedures must be developed that simulate how individuals produce bounded knowledge of geographical space through experiential learning, adapt this knowledge to continually changing environments, and apply it to spatial decision‐making processes. In this paper, we present a framework for the representation of adaptive, spatially aware, and mobile agents. To provide context to this research, a multiagent model is constructed to simulate the migratory behaviour of elk (Cervus elaphus) on Yellowstones northern range. In this simulated environment, intelligent agents learn in ways that enable them to mimic real‐world behaviours and adapt to changing landscapes.

Agent-based modelling environment for spatial decision support

The goal of Spatial Decision Support Systems (SDSS) is to assist decision-makers as they generate alternative solutions to a variety of semi-structured geographical problems, and to evaluate these solutions with the help of applicable data and analytical models. Most existing SDSS, however, support only a limited number of decision-making environments, and are not designed to utilize web-accessible repositories of spatial data and models. These limitations are overcome through the use of ‘software agents’ within an agent-oriented modelling framework, called ‘Distributed Intelligent Geographical Modelling Environment (DIGME)’. The utility of this framework is demonstrated through the development of an SDSS to evaluate the ecological and economic impacts of agricultural policy for the Cache River watershed of southern Illinois.

Using Genetic Algorithms to Create Multicriteria Class Intervals for Choropleth Maps

Abstract During the past three decades a large body of research has investigated the problem of specifying class intervals for choropleth maps. This work, however, has focused almost exclusively on placing observations in quasi-continuous data distributions into ordinal bins along the number line. All enumeration units that fall into each bin are then assigned an areal symbol that is used to create the choropleth map. The geographical characteristics of the data are only indirectly considered by such approaches to classification. In this article, we design, implement, and evaluate a new approach to classification that places class-interval selection into a multicriteria framework. In this framework, we consider not only number–line relationships, but also the area covered by each class, the fragmentation of the resulting classifications, and the degree to which they are spatially autocorrelated. This task is accomplished through the use of a genetic algorithm that creates optimal classifications with respect to multiple criteria. These results can be evaluated and a selection of one or more classifications can be made based on the goals of the cartographer. An interactive software tool to support classification decisions is also designed and described.

Interactive evolutionary approaches to multiobjective spatial decision making: A synthetic review

Abstract This paper reviews recent developments in evolutionary algorithms and visualization in the context of multiobjective spatial decision making. A synthetic perspective is employed to bridge these two areas and to create a unified conceptual framework that can be used to address a broad range of multiobjective spatial decision problems. In this framework, evolutionary algorithms are employed to generate optimal, or near-optimal, solutions to a problem being addressed. Alternatives created are then displayed in an interactive visual support system that can be used by decision makers to discover the competing nature of multiple objectives and to gain knowledge about the tradeoffs among alternatives.

Towards Ubiquitous Cartography

Computer-generated maps have become commonplace over the past decade. Most internet search engines, for example, have the ability to generate maps in response to spatial queries and routes between specified origins and destinations. Advances in mobile computing technologies provide access to these mapping capabilities from virtually any location on the Earths surface. Maps and map-making have become ubiquitous, and this phenomenon requires cartographers to rethink basic concepts about map design and map use. In this special issue we present five research projects that are focused on the emerging field of ubiquitous cartography. These projects were selected, in part, because they are representative of key research challenges that face the cartographic research community. In this introductory paper, key terms are defined and research challenges outlined. By way of this collected set of papers, ubiquitous cartography is presented as a new and important arena for cartographic research.

Exploring the Geographic Consequences of Public Policies Using Evolutionary Algorithms

Abstract Public policies with geographical consequences are often difficult to analyze because they affect multiple stakeholders with competing objectives. While such problems fall conceptually into the domain of multiobjective evaluation, associated analytical techniques often search for a single optimum solution. Within the context of geographical problems, optimality often means different things to different stakeholders and, thus, an optimum optimorum may not exist. In this article, we present a new technique based on an evolutionary algorithm (EA) that produces a large number of optimal and near-optimal solutions to a large class of land management problems. As implemented for this article, solutions represent landscape patterns that produce services that meet stakeholder needs to varying degrees. The construction of curves that illustrate the trade-offs among various services given limited resources is central to this approach. Decision makers can use these curves to help find solutions that strike a balance among conflicting objectives and, thus, meet stakeholder needs. To provide context to this work we consider the impact of the U.S. Department of Agricultures (USDA) Conservation Reserve Program on rural landscapes. Three objectives are assumed: (1) maximize farm income, (2) maximize environmental quality, (3) minimize public investment in conservation programs; the first two are viewed as services desired by stakeholders. Analytical and visualization tools are developed to reduce the burden associated with exploring the large number of solutions that are produced by this technique. The results illustrate that the EA-based approach can produce results equal to and significantly more diverse than conventional integer programming techniques.

Landscape Models and Explanation in Landscape Ecology—A Space for Generative Landscape Science?

Abstract Further development of process-based spatial models is needed to facilitate explanation in landscape ecology. We discuss the dual modeling goals of prediction and explanation and identify challenges faced in explaining landscape patterns. These challenges are especially acute in attempts to explain patterns that result from complex adaptive systems. We compare examples of two process models used to describe landscape changes in Yellowstone National Park as a consequence of predator-prey interactions. Generative landscape science is offered as a complementary approach to explanation, combining models of candidate processes that are believed to give rise to observed patterns with empirical observations.

A parallel agent-based model of land use opinions

In this article we present a parallel agent-based model (ABM) to support large-scale simulations of land use change. ABMs are a commonly used simulation approach for the investigation of land use systems. The computationally intense nature of these models, however, often prohibits the development of models that fully capture the complex dynamics of land use systems when using typical desktop computing environments. The search for scientific understanding and solutions to real-world problems is, therefore, often limited by an inability to explore a wide range of scales or the impact of complex interactions. Parallel computing provides a potential solution for this limitation issue. Our ABM is designed using parallel computing to simulate the formation of large-scale land use opinions within spatially explicit environments. Agents, environments, and interactions among agents are distributed among processors through parallel computing strategies, including spatial domain decomposition, ghost zones, and synchronization. We examine the computational performance of the model within a supercomputing environment. It is demonstrated that by leveraging increasingly available high-performance parallel computing resources large-scale ABMs of land use systems can be developed and, ultimately, underlying processes that drive these systems better understood.