Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data

TL;DR

This paper evaluates various uncertainty quantification methods for deep neural networks applied to satellite imagery of tropical cyclones, aiming to improve wind speed estimation accuracy and reliability for critical decision-making.

Contribution

It provides a comprehensive theoretical and empirical comparison of existing UQ methods for DNNs in tropical cyclone wind speed estimation from satellite data.

Findings

Predictive uncertainties can enhance wind speed estimation accuracy.

Different UQ methods show varying effectiveness across storm categories.

Uncertainty estimates help in better understanding model confidence.

Abstract

Deep neural networks (DNNs) have been successfully applied to earth observation (EO) data and opened new research avenues. Despite the theoretical and practical advances of these techniques, DNNs are still considered black box tools and by default are designed to give point predictions. However, the majority of EO applications demand reliable uncertainty estimates that can support practitioners in critical decision making tasks. This work provides a theoretical and quantitative comparison of existing uncertainty quantification methods for DNNs applied to the task of wind speed estimation in satellite imagery of tropical cyclones. We provide a detailed evaluation of predictive uncertainty estimates from state-of-the-art uncertainty quantification (UQ) methods for DNNs. We find that predictive uncertainties can be utilized to further improve accuracy and analyze the predictive uncertainties of different methods across storm categories.