The sustainability assessment of projects : an artificial intelligence approach, with application to Tasmania

摘要

This thesis develops and presents a practical method of assessing the sustainability impact ofudprojects. The research has been motivated by the fact that sustainability is an accepted goaludof resource management and planning legislation, and yet we have few tools with which toudquantitatively assess sustainability impacts.udThe history of the sustainability imperative is reviewed, and it is proposed that sustainabilityudbe considered in terms of three themes which match the way in which most planners thinkudabout sustainability issues, and commission specialist studies:ud1. Biodiversity. Biological diversity and integrity.ud2. Socio-economic. Well being and equity within and between generations.ud3. Physical environmental. Local, regional and global environmental quality.udA sustainability assessment method is developed, whereby project impacts are measuredudusing indicators of the sustainability issues associated with the project. This takes advantageudof the indicator sets being developed by the Local Agenda 21 initiative, and by the State ofudthe Environment reporting process. Ways are examined to aggregate indicators into indices,udusing both traditional approaches and expert systems. Fuzzy rule systems and neuraludnetworks are shown to offer powerful, natural alternatives to traditional aggregationudmethods, and case studies are presented which use these tools to aggregate informationudrelating to roadside vegetation quality, algal blooms, urban air quality, and sewage treatmentudplant performance. A traditional modelling approach to predicting indicator changes would solve (numericallyudintegrate) the differential equations governing the interactions between the indicators,udcomputing interaction terms at each time step. However, in this instance the equations areudunknown, and the inputs are often known only semi-quantitatively. A modelling approachudbased on a fuzzy rule system is developed that overcomes these barriers, in which indicatorudchanges due to interactions between indicators are computed iteratively. The model isudapplied to a number of basic situations, and approaches to driving the model are discussed.udModel performance and sensitivity tests are carried out that demonstrate the behaviour ofudthe model to be reasonable, and an illustrative application is presented. The sustainability assessment method is further validated by case studies in mining, forestryudand road transport planning. The model predictions compare well to expectations, althoughudrigorous test data are not yet available, and the method is shown to be an effective tool forudscreening projects, particularly when used to compare project options. It can be used toudimprove the design of baseline studies, to design appropriate monitoring programs, and toudexamine the need for application of the precautionary principle.udThe use of multi-criteria decision-making methods and genetic algorithms to select andudoptimise a preferred project option is explored, and illustrated by application to a proposedudroad upgrade project. The thesis concludes by discussing follow-on areas of research, andudapproaches to improving the assessment method.