k.matthews, a.r.sibbald @ mluri.sari.ac.uk This paper explores the application of multiobjective Genetic Algorithms (mGAs) to rural land use planning, a spatial allocation problem. Two mGAs are proposed. Both share an underlying structure of: fitness assignment using Pareto-dominance ranking, niche induction and an individual replacement strategy. They are differentiated by their representations: a fixedlength genotype composed of genes that map directly to a land parcel's use and a variablelength, order-dependent representation making allocations indirectly via a greedy algorithm. The latter representation requires additional breeding operators to be defined and post-processing of the genotype structure to identify and remove duplicate genotypes. The two mGAs are compared on a real land use planning problem and the strengths and weaknesses of the underlying framework and each representation are identified. 1

There are three main objectives of this monograph: (i) to provide an introduction to geographical information technology along with an historical perspective on the evolving role of Geographic Information Systems (GIS) in planning, (ii) to overview relevant methods and techniques for GISbased land-use suitability mapping and modeling, and (iii) to identify the trends, challenges and prospects of GIS-based land-use suitability analysis. The monograph focuses on two perspectives of GIS-based land-use suitability analysis: the techno-positivist perspective and the socio-political, public participation perspectives. It is organized into six chapters. After an introductory setting chapter, which defines the scope of land-use suitability analysis, an overview of relevant GIS technology is provided in Chapter 2. Chapter 3 offers an historical account of the development of GIS. It also discusses the development of GIS in the context of evolving perspectives of planning. Chapter 4 gives an overview of the methods for GIS-based land-use suitability modeling. The overview provides a background against which selected case studies are discussed in Chapter 5. The concluding chapter summarized the main points of the monographs and discusses problems and prospects for GIS-based land-use suitability analysis.

Land managers are increasingly faced with complex decisions requiring the consideration of tradeoffs between multiple, non-commensurable objectives. Such decisions have profound effects on the financial, social and environmental sustainability of land use systems. One approach to assisting land managers with these decisions has been the development of computer-based decision support systems (DSS). While such systems are demonstrably able to make analyses of multi-objective land-use planning problems, are the answers they produce relevant and useful to practitioners? This paper reports on a workshop-based, soft-systems analysis of outputs from a spatial, multi-objective land-use planning tool. The paper outlines the approach taken in developing the decision support system, focusing on the land-use planning tools. These tools use multi-objective genetic algorithms to define the structure of the trade-off between objectives. The paper then details the softsystems -based evaluation strategy. Land managers and other professionals from a range of backgrounds were asked to devise individual "best compromise" plans, balancing financial and landscape diversity goals, for a farm in upland Scotland. Sub-groups of land managers were then set the task of agreeing on a plan between the members of the group. This process used the soft-systems methods of facilitated discussion and reporting back from sub-groups. The land managers' and sub-groups' plans were analysed with the DSS tools and the results compared with outputs from the land-use planning tools. From this analysis and the qualitative responses within the workshop it was possible to conclude that the land-use planning tools provided a useful means of exploring the patterns of land use that could be adopted for a land managem...