Articles | Volume 18, issue 4
https://doi.org/10.5194/gmd-18-1017-2025
https://doi.org/10.5194/gmd-18-1017-2025
Methods for assessment of models
 | 
24 Feb 2025
Methods for assessment of models |  | 24 Feb 2025

Explaining neural networks for detection of tropical cyclones and atmospheric rivers in gridded atmospheric simulation data

Tim Radke, Susanne Fuchs, Christian Wilms, Iuliia Polkova, and Marc Rautenhaus

Related authors

Explaining patterns learned by neural networks for detection of atmospheric surface fronts in gridded atmospheric data
Tim Radke, Johanna Baehr, and Marc Rautenhaus
EGUsphere, https://doi.org/10.5194/egusphere-2026-3877,https://doi.org/10.5194/egusphere-2026-3877, 2026
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary

Cited articles

Abu Alhaija, H., Mustikovela, S. K., Mescheder, L., Geiger, A., and Rother, C.: Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes, Int. J. Comput. Vis., 126, 961–972, https://doi.org/10.1007/s11263-018-1070-x, 2018. 
Achtibat, R., Dreyer, M., Eisenbraun, I., Bosse, S., Wiegand, T., Samek, W., and Lapuschkin, S.: From attribution maps to human-understandable explanations through Concept Relevance Propagation, Nat. Mach. Intell., 5, 1006–1019, https://doi.org/10.1038/s42256-023-00711-8, 2023. 
Ahmed, A. M. A. and Ali, L.: Explainable Medical Image Segmentation via Generative Adversarial Networks and Layer-wise Relevance Propagation, Nordic Machine Intelligence, 1, 20–22, https://doi.org/10.5617/nmi.9126, 2021. 
Ahrens, C. D., Jackson, P. L., and Jackson, C. E. O.: Meteorology Today: An Introduction to Weather, Climate, and the Environment, Nelson Education, 710 pp., ISBN-10 0357452070, ISBN-13 978-0357452073, 2012. 
Alves, D. B. M., Sapucci, L. F., Marques, H. A., and Souza, E. M.: Using a regional numerical weather prediction model for GNSS positioning over Brazil, GPS Solut., 20, 677–685, https://doi.org/10.1007/s10291-015-0477-x, 2016. 
Download
Short summary
In our study, we built upon previous work to investigate the patterns artificial intelligence (AI) learns to detect atmospheric features like tropical cyclones (TCs) and atmospheric rivers (ARs). As primary objective, we adopt a method to explain the AI used and investigate the plausibility of learned patterns. We find that plausible patterns are learned for both TCs and ARs. Hence, the chosen method is very useful for gaining confidence in the AI-based detection of atmospheric features.
Share
Altmetrics
Final-revised paper
Preprint