edu.ucar.opensky::articles:24749 UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact 2025-12-24T23:04:50.680958 ISO 19115-2 Geographic Information - Metadata - Part 2: Extensions for Imagery and Gridded Data ISO 19115-2:2009(E) https://n2t.org/ark:/85065/d73b63m3 https://doi.org/10.5065/D6V40SXP https Related Dataset #1 High Resolution WRF Simulations of the Current and Future Climate of North America https://doi.org/10.5281/zenodo.4052585 https Related Dataset #2 DATA: A benchmark to test generalization capabilities of deep learning methods to classify severe convective storms in a changing climate https://doi.org/10.5065/D6RX99HX https Related Service #1 Cheyenne: SGI ICE XA Cluster A benchmark to test generalization capabilities of deep learning methods to classify severe convective storms in a changing climate 2021-09-01T00:00:00Z publication https://n2t.org/ark:/85065/d73b63m3 https://doi.org/10.1029/2020EA001490 Molina, Maria author Gagne, David John author Prein, Andreas author UCAR/NCAR - Library publisher This is a test case study assessing the ability of deep learning methods to generalize to a future climate (end of 21st century) when trained to classify thunderstorms in model output representative of the present-day climate. A convolutional neural network (CNN) was trained to classify strongly rotating thunderstorms from a current climate created using the Weather Research and Forecasting model at high-resolution, then evaluated against thunderstorms from a future climate and found to perform with skill and comparatively in both climates. Despite training with labels derived from a threshold value of a severe thunderstorm diagnostic (updraft helicity), which was not used as an input attribute, the CNN learned physical characteristics of organized convection and environments that are not captured by the diagnostic heuristic. Physical features were not prescribed but rather learned from the data, such as the importance of dry air at mid-levels for intense thunderstorm development when low-level moisture is present (i.e., convective available potential energy). Explanation techniques also revealed that thunderstorms classified as strongly rotating are associated with learned rotation signatures. Results show that the creation of synthetic data with ground truth is a viable alternative to human-labeled data and that a CNN is able to generalize a target using learned features that would be difficult to encode due to spatial complexity. Most importantly, results from this study show that deep learning is capable of generalizing to future climate extremes and can exhibit out-of-sample robustness with hyperparameter tuning in certain applications. UCAR/NCAR - Library OpenSky Support PO Box 3000 Boulder CO 80307-3000 opensky@ucar.edu http://opensky.ucar.edu/ homepage pointOfContact PDF Text theme Resource Type 2016-01-01T00:00:00Z publication Copyright author(s). This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. None eng geoscientificInformation