Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914750492835840 |
|---|---|
| author | Lehmann, Nils Gottschling, Nina Maria Depeweg, Stefan Nalisnick, Eric |
| author_facet | Lehmann, Nils Gottschling, Nina Maria Depeweg, Stefan Nalisnick, Eric |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08325 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data Lehmann, Nils Gottschling, Nina Maria Depeweg, Stefan Nalisnick, Eric Atmospheric and Oceanic Physics Machine Learning Applications 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. |
| title | Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Data |
| topic | Atmospheric and Oceanic Physics Machine Learning Applications |
| url | https://arxiv.org/abs/2404.08325 |