TITLE:
A Wavelet-Based Deep Learning Framework for Predicting Peak Intensity of Hurricanes in the Atlantic Ocean
AUTHORS:
Jiahe Liu, Xiaodi Wang
KEYWORDS:
Tropical Cyclone (TC), Hurricane Intensity, Convolutional Neural Network (CNN), Discrete Wavelet Transform (DWT)
JOURNAL NAME:
Atmospheric and Climate Sciences,
Vol.13 No.4,
October
30,
2023
ABSTRACT: Every year, hurricanes pose a serious threat to
coastal communities, and forecasting their maximum intensities has been a
crucial task for scientists. Computational methods have been used to forecast
the intensities of hurricanes across varying time horizons. However, as climate
change has increased the volatility of the intensities of recent hurricanes,
newer and adaptable methods must be devised. In this study, a framework is
proposed to estimate the maximum intensity of tropical cyclones (TCs) in the
Atlantic Ocean using a multi-input convolutional neural network (CNN). From the
Atlantic hurricane seasons of 2000 through 2021, over 100 TCs that reached
hurricane-level wind speeds are used. Novel algorithms are used to collect and
preprocess both satellite image data and non-image data for these TCs. Namely,
Discrete Wavelet Transforms (DWTs) are used to decompose individual bands of
satellite image data, eliminating noise and extracting hidden frequency details
before training. Validation tests indicate that this framework can estimate the
maximum wind speed of TCs with a root mean square error of 15 knots. This
framework provides preliminary predictions that can supplement current
computational methods that would otherwise not be able to account for climate
change. Future work can be done by forecasting with time constraints, and to
provide estimations for more metrics such as pressure and precipitation.