Structural Forecasting for Tropical Cyclone Intensity Prediction: Providing Insight with Deep Learning
This work addresses the need for interpretable forecasting tools for human experts at operational centers like the National Hurricane Center, offering a novel approach to enhance decision-making in cyclone intensity prediction.
The paper tackles the problem of tropical cyclone intensity prediction by developing a deep learning framework that provides forecasters with interpretable monitoring of high-dimensional, physically relevant predictors and their relationships to short-term intensity changes, without specifying concrete numerical results.
Tropical cyclone (TC) intensity forecasts are ultimately issued by human forecasters. The human in-the-loop pipeline requires that any forecasting guidance must be easily digestible by TC experts if it is to be adopted at operational centers like the National Hurricane Center. Our proposed framework leverages deep learning to provide forecasters with something neither end-to-end prediction models nor traditional intensity guidance does: a powerful tool for monitoring high-dimensional time series of key physically relevant predictors and the means to understand how the predictors relate to one another and to short-term intensity changes.