83rd Annual

Tuesday, 11 February 2003: 3:14 PM
Fuzzy Case-Based Prediction of Cloud Ceiling and Visibility
Bjarne K. Hansen, Dalhousie University, Halifax, NS, Canada; and D. Riordan
Poster PDF (92.7 kB)
Fuzzy logic and case-based reasoning are leading methodologies for the application of artificial intelligence. We describe a system, WIND-1, that combines fuzzy logic and case-based reasoning to produce forecasts of airport cloud ceiling and visibility. Knowledge about meteorological and temporal features that experienced forecasters use to construct analogous climatological scenarios is encoded in a fuzzy similarity measure. The fuzzy similarity measure is used to locate k-nearest neighbors from airports' historical databases. These nearest neighbors are adapted to produce values of forecast parameters. Experiments show that the WIND-1 system produces highly accurate forecasts. It takes about one second for WIND-1 to produce a forecast.

Supplementary URL: http://chebucto.ca/~bjarne/wind