Including Maximum Sustained Wind Speed in a Time Series Model to Forecast Hurricane Movement

Author

Timothy B. Mott

Date of Award

3-1993

Document Type

Thesis

Degree Name

Master of Science

Department

Department of Operational Sciences

First Advisor

Edward F. Mykytka, PhD

Abstract

Techniques for applying time series fundamentals to forecasting hurricane movement are thoroughly examined in this research. The objectives are: (1) to modify Dr. Thomas Curry's threshold autoregressive time series model to improve its ability to forecast hurricane movement, (2) to forecast the maximum sustained wind speed for a hurricane, and (3) to identify if wind speed should be included as an explanatory variable to aid in forecasting hurricane movement. Eleven different models to predict the latitude, longitude and maximum sustained wind speed are compared and contrasted with Curry's bivariate time series model. The results showed the modifications allow significant forecasting improvement to Curry's model in the 6-, 12-, 24-, 48- and 72-hour forecasts. The model recommended by this research shows a significant improvement in mean and variance of the overall forecast errors.

AFIT Designator

AFIT-GOR-ENS-93M-14

DTIC Accession Number

ADA262510

Comments

The author's Vita page is omitted.

Recommended Citation

Mott, Timothy B., "Including Maximum Sustained Wind Speed in a Time Series Model to Forecast Hurricane Movement" (1993). Theses and Dissertations. 7207.
https://scholar.afit.edu/etd/7207