Deep Learning Models for Revealing the Climate Trends of Tropical Cyclone Intensity and Energy Extremes and its Usage in Operational Typhoon Forecasting

Deep learning (DL) is useful in various regression tasks for tropical cyclone (TC) analysis and forecasting, including regression to the current TC radial wind profile and regression to future TC structure parameters (i.e., statistical forecasts of intensity or size).

The first part showcases the usefulness of DL for reconstructing homogenized and trustworthy global TC wind profile datasets since 1981 and thus facilitating an examination of climate trends of TC structure/energy extremes. Understanding past TC trends and variability is critical for projecting future TC impacts on human society considering the changing climate. By training with uniquely labeled data integrating best tracks and numerical model analysis, our model converts multichannel satellite imagery to a 0-750-km wind profile of axisymmetric surface winds. The model performance is verified to be sufficient for climate studies by comparing it to independent satellite-radar surface winds.

Based on the new homogenized dataset, the major TC proportion has increased by ~13% in the past four decades. Moreover, the proportion of extremely high-energy TCs has increased by ~25%, along with an increasing trend (> one standard deviation of the 40-y variability) of the mean total energy of high-energy TCs. Although the warming ocean favors TC intensification, the TC track migration to higher latitudes and altered environments further affect TC structure and energy.

On the other hand, this presentation demonstrates the usage of the proposed DL model for TC structure analysis in operational typhoon forecasting and quickly introduces subsequent DL models for predicting TC intensity and size in the western North Pacific.