Genetic Algorithms (GAs) in the Role of Intelligent Regional Adaptation Agents for Agricultural Decision Support Systems
An AI adaptation methodology designed to assist in transporting agricultural models between regions is presented. A methodology to perform model adaptation (viz. localization) is frequently necessary when models are transported because models developed in one region often do not produce valid results when used in a different region. In this methodology, a GA plays the role of the adaptation agent. By linking a GA to an agricultural model, the model become more robust because it is able to adapt to the region in which the model is being used. This methodology has been implemented within a decision support system (DSS) developed within an EC project called SYBIL. The DSS helps farmers predict when diseases and funguses will attack their plants, so they can make intelligent decisions on preventing these attacks. Preliminary testing within this environment indicates this adaptation methodology has the ability to allow agricultural models developed in one area to be effectively utilized in other regions.
KeywordsGenetic Algorithm Decision Support System Downy Mildew Risk Assessment Model Adaptation Agent
Unable to display preview. Download preview PDF.
- Grefenstette, J.J. 1985, ed. Proc. of an International Conference on Genetic Algorithms and Their Applications. Carnegie-Mellon University, Pittsburgh, PA, USA, July 24–26, 1985. U.S. Navy Center for Applied Research in Artificial Intelligence, USA.Google Scholar
- Grefenstette, J.J. 1987, ed. Proc. of the Second International Conference on Genetic Algorithms. Massachusetts Instituted of Technology, Cambridge, MA, USA, July 28–31, 1987. L. Erlbaum Associates, USA.Google Scholar
- Schaffer, J.D. 1989, ed. Proceedings of the Third International Conference on Genetic Algorithms. George Mason University, Fairfax, VA, USA, June 4–7, 1989. Morgan Kaufmann Publishers, Inc., USA.Google Scholar
- Hill, G.K. 1989. Mit P.R.O. System Spritzungen Sparen. Die Weinwirtschaft, 125, pp. 28–31.Google Scholar
- Hill, G.K. 1990. Das Peronospora-Riskoprognosemodell Oppenheim (P.R.O.) im Praxistest. Der Deutsche Weinbau, 44 (12/27 April 1990), pp. 514–517.Google Scholar
- Hill, G.K. 1990. Studies on Plasmopara Viticola Epidemics in the Vineyard. Proc. Atti del Convengo su Modelli Euristici ed Operativi in Agricoltora, Caserta, Italy, 27–29 Sept. 1990, Societa Italiana de Fitoiatria ed., pp. 266–273.Google Scholar
- Hill, G.K. 1990. Plasmopara Risk Oppenheim — A Deterministic Computer Model for the Viticultural Extension. Proc. Atti del Convengo su Modelli Euristici ed Operativi in Agricoltora, Caserta, Italy, 27–29 Sept. 1990, Società Italiana de Fitoiatria ed., pp. 182–194.Google Scholar
- Hill, G.K. 1993. Severe Primary Infections of Plasmopara Viticola at bloom-Causal Climatic Conditions and Threshold of Damage on Bunches. Proc. OILB Meeting on Integrated Control in Viticulture, Bordeaux, France, 2–5 March, 1993.Google Scholar
- Hill, G.K., Breth, K., Spies, S. 1993. The Application of the P.R.O. — Simulator for Minimizing of Plasmopara Sprays in the Frame of an Integrated Control Project in Rheinhessen/Germany. Vitic. Enol. Sci., 48, pp. 176–183Google Scholar
- Jacucci, G., Foy, M., and Uhrik, C. 1994. SYBIL DSS:Localization of Agricultural Risk Assessment Models. Proceedings of Decision Support 2001 (DSS2001) (The 17th Annual Geographic Information Seminar & The Resource Technology’94 Symposium), Toronto, Canada, 12–16 Sept. 1994, American Society of Photogrammetry and Remote Sensing.Google Scholar