The primary goal of this research is to examine the efficacy of using a fuzzy logic/adaptive weighting (FLAW) technique to predict hurricane intensity change in the eastern North Pacific (ENP) basin. The intensity change forecasts, for 12-hour intervals ranging from 12 to 72 hours, produced by a ... Show moreThe primary goal of this research is to examine the efficacy of using a fuzzy logic/adaptive weighting (FLAW) technique to predict hurricane intensity change in the eastern North Pacific (ENP) basin. The intensity change forecasts, for 12-hour intervals ranging from 12 to 72 hours, produced by a model using FLAW are compared to a model developed using the standard statistical technique of multiple linear regression (MLR). To this end, climatology and persistence variables, as well as observed intensity changes, are computed and extracted from the National Hurricane Center (NHC) best-track dataset and the weekly National Oceanic and Atmospheric Administration (NOAA) global optimum interpolation weekly sea surface temperature dataset for the years of 1982-99. The climatology and persistence predictors used for both models include the previous 6-hour intensity change, latitude of the hurricane center, current intensity at the time of the observation, and sea surface temperature interpolated to the time and location of the observed hurricane center. The FLAW technique is based on the Standard Additive Method (SAM) developed by Kosko. The method adapts the weights given to predictors to decrease the difference between the forecast and observed value. Preliminary results suggest that the FLAW model produces errors comparable in magnitude to the MLR model. The bias is significantly less for the 36-, 48-, 60-, and 72-hour forecast periods. Several case studies show that the model is able to adapt the weighting appropriately when the one or more predictors become over-dominant. With more work and the inclusion of synoptic predictors, this method may eventually offer improved hurricane intensity change guidance for forecasters, thus reducing the loss of lives and property. Show less