1 code implementation • 13 Oct 2023 • Randy J. Chase, Amy McGovern, Cameron Homeyer, Peter Marinescu, Corey Potvin
Updraft proxies, like overshooting top area from satellite images, have been linked to severe weather hazards but only relate to a limited portion of the total storm updraft.
no code implementations • 18 Nov 2022 • Montgomery Flora, Corey Potvin, Amy McGovern, Shawn Handler
This study is one of the first to quantify the improvement in explainability from limiting correlated features and knowing the relative fidelity of different explainability methods.
no code implementations • 16 Nov 2022 • Montgomery Flora, Corey Potvin, Amy McGovern, Shawn Handler
With increasing interest in explaining machine learning (ML) models, the first part of this two-part study synthesizes recent research on methods for explaining global and local aspects of ML models.
2 code implementations • 31 Oct 2022 • Randy J. Chase, David R. Harrison, Gary Lackmann, Amy McGovern
In order to fill the dearth of resources covering neural networks with a meteorological lens, this paper discusses machine learning methods in a plain language format that is targeted for the operational meteorological community.
no code implementations • 23 May 2022 • Ignacio Lopez-Gomez, Amy McGovern, Shreya Agrawal, Jason Hickey
We find that training models to minimize custom losses tailored to emphasize extremes leads to significant skill improvements in the heat wave prediction task, compared to NWMs trained on the mean squared error loss.
1 code implementation • 15 Apr 2022 • Randy J. Chase, David R. Harrison, Amanda Burke, Gary M. Lackmann, Amy McGovern
Recently, the use of machine learning in meteorology has increased greatly.
no code implementations • 15 Dec 2021 • Amy McGovern, Imme Ebert-Uphoff, David John Gagne II, Ann Bostrom
In fact, much can be learned from other domains where AI was introduced, often with the best of intentions, yet often led to unintended societal consequences, such as hard coding racial bias in the criminal justice system or increasing economic inequality through the financial system.
no code implementations • 12 Nov 2020 • Montgomery Flora, Corey K. Potvin, Patrick S. Skinner, Shawn Handler, Amy McGovern
Using a novel ensemble storm track identification method, we extracted three sets of predictors from the WoFS forecasts: intra-storm state variables, near-storm environment variables, and morphological attributes of the ensemble storm tracks.