This paper demonstrates that by using GIS spatial image categorised into themes, a fuzzy logic based forecasting methodology can be performed. Fuzzy logic is best suited to this type of problem as its requisite is in handling approximate data. The methodology would allow us to: 1) predict weed population reasonably well based on approximate data, 2) take into consideration additional parameters without re-writing the algorithm, 3) refine large-scale forecasts to suit localised situations, 4) allow users to determine and inspect individual infestation factors, and 5) adapt the methodology to other weed or plant species. This paper also briefly introduces a new fuzzy If-Then operand, Case-Of, specifically used in this methodology.
Funding
Category 1 - Australian Competitive Grants (this includes ARC, NHMRC)
History
Editor
Yu X; Kacprzyk J
Parent Title
Applied decision support with soft computing
Start Page
402
End Page
418
Number of Pages
17
ISBN-10
3540024913
Publisher
Springer-Verlag
Place of Publication
Berlin, Germany
Open Access
No
External Author Affiliations
Faculty of Informatics and Communication; RMIT University;