Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data
This work addresses the need for reliable uncertainty estimates in earth observation applications, particularly for critical decision-making in tropical cyclone monitoring, but it is incremental as it compares existing methods rather than introducing new ones.
This paper tackled the problem of estimating wind speeds from satellite imagery of tropical cyclones using deep neural networks, focusing on comparing uncertainty quantification methods to improve reliability for decision-making, and found that predictive uncertainties can enhance accuracy across storm categories.
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.