Forecasting the Evolution of North Atlantic Hurricanes: A Deep Learning Approach
Rikhi Bose, Adam L. Pintar, Emil Simiu
Accurate prediction of storm evolution from genesis onwards may be of great importance considering that billions of dollars worth of property damage and numerous casualties are inflicted each year all over the globe. In the present work, two classes of Recurrent Neural Network (RNN) models for predicting storm-eye trajectory have been developed. These models are trained on input features available in or derived from the North Atlantic hurricane database maintained by the National Hurricane Center (NHC). The models utilize historical data to estimate probabilities of storms passing through any location. Furthermore, inputs to the models are such so that the model development methodology is applicable to any oceanic basin in any part of the globe. Model forecasting errors have been analyzed in detail. The error analysis shows that the Many-To-Many class of models are appropriate for long-term forecasting while Many-To-One prediction models perform comparably well for 6 − hr predictions. Application of these models to predicting more than 40 test storms in the North Atlantic basin shows that, at least for forecasts of up to 12 hours, they outperform all data-based storm trajectory prediction models cited in the paper. Apart from providing very fast predictions, the RNN models require less information than models used in current practice. Because the models presented herein emulate the trajectory trends of historical storms, they are currently being used for the simulation of synthetic storm tracks and features and the subsequent estimation of extreme wind speeds with various mean recurrence intervals.
, Pintar, A.
and Simiu, E.
Forecasting the Evolution of North Atlantic Hurricanes: A Deep Learning Approach, Technical Note (NIST TN), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://doi.org/10.6028/NIST.TN.2167, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=932666
(Accessed December 9, 2022)