Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts

Barnes, Elizabeth A.; Barnes, Randal J.; DeMaria, Mark

doi:10.1017/eds.2023.7

Cited by 2 publications

(2 citation statements)

References 33 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Uncertainty quantification for tropical cyclone intensity and track forecasts : Uncertainty quantification and communication can be incredibly challenging. We have explored a simple method for adding uncertainty to almost any neural network regression task via estimation of a general probability distribution (Barnes, Barnes, and DeMaria 2023). We showed that this intuitive approach can improve current tropical cyclone forecasts of intensity, as well as their track, by adding uncertainty estimates to an otherwise deterministic prediction.…”

Section: Example Success Stories: Text Boxesmentioning

confidence: 99%

AI2ES: The NSF AI Institute for Research on Trustworthy AI for Weather, Climate, and Coastal Oceanography

McGovern,

Ebert‐Uphoff,

Barnes

et al. 2024

AI Magazine

View full text Add to dashboard Cite

The NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography (AI2ES) focuses on creating trustworthy AI for a variety of environmental and Earth science phenomena. AI2ES includes leading experts from AI, atmospheric and ocean science, risk communication, and education, who work synergistically to develop and test trustworthy AI methods that transform our understanding and prediction of the environment. Trust is a social phenomenon, and our integration of risk communication research across AI2ES activities provides an empirical foundation for developing user‐informed, trustworthy AI. AI2ES also features activities to broaden participation and for workforce development that are fully integrated with AI2ES research on trustworthy AI, environmental science, and risk communication.

show abstract

Section: Example Success Stories: Text Boxesmentioning

confidence: 99%

AI2ES: The NSF AI Institute for Research on Trustworthy AI for Weather, Climate, and Coastal Oceanography

McGovern,

Ebert‐Uphoff,

Barnes

et al. 2024

AI Magazine

View full text Add to dashboard Cite

show abstract

“…For a comprehensive review in the context of scientific ML, refer to Psaros et al (2023). The topic has also started to increasingly gain attention in the climate literature (Barnes et al, 2023;Gordon & Barnes, 2022;Guillaumin & Zanna, 2021;Haynes et al, 2023). In this study, we will assess the performance of three common UQ methods (Bayesian, dropout, and variational NNs) by analyzing the relationships between uncertainty and accuracy during inference.…”

Section: Introductionmentioning

confidence: 99%

Data Imbalance, Uncertainty Quantification, and Transfer Learning in Data‐Driven Parameterizations: Lessons From the Emulation of Gravity Wave Momentum Transport in WACCM

Sun,

Pahlavan,

Chattopadhyay

et al. 2024

J Adv Model Earth Syst

View full text Add to dashboard Cite

Neural networks (NNs) are increasingly used for data‐driven subgrid‐scale parameterizations in weather and climate models. While NNs are powerful tools for learning complex non‐linear relationships from data, there are several challenges in using them for parameterizations. Three of these challenges are (a) data imbalance related to learning rare, often large‐amplitude, samples; (b) uncertainty quantification (UQ) of the predictions to provide an accuracy indicator; and (c) generalization to other climates, for example, those with different radiative forcings. Here, we examine the performance of methods for addressing these challenges using NN‐based emulators of the Whole Atmosphere Community Climate Model (WACCM) physics‐based gravity wave (GW) parameterizations as a test case. WACCM has complex, state‐of‐the‐art parameterizations for orography‐, convection‐, and front‐driven GWs. Convection‐ and orography‐driven GWs have significant data imbalance due to the absence of convection or orography in most grid points. We address data imbalance using resampling and/or weighted loss functions, enabling the successful emulation of parameterizations for all three sources. We demonstrate that three UQ methods (Bayesian NNs, variational auto‐encoders, and dropouts) provide ensemble spreads that correspond to accuracy during testing, offering criteria for identifying when an NN gives inaccurate predictions. Finally, we show that the accuracy of these NNs decreases for a warmer climate (4 × CO2). However, their performance is significantly improved by applying transfer learning, for example, re‐training only one layer using ∼1% new data from the warmer climate. The findings of this study offer insights for developing reliable and generalizable data‐driven parameterizations for various processes, including (but not limited to) GWs.

show abstract

Sinh-arcsinh-normal distributions to add uncertainty to neural network regression tasks: Applications to tropical cyclone intensity forecasts

Cited by 2 publications

References 33 publications

AI2ES: The NSF AI Institute for Research on Trustworthy AI for Weather, Climate, and Coastal Oceanography

AI2ES: The NSF AI Institute for Research on Trustworthy AI for Weather, Climate, and Coastal Oceanography

Data Imbalance, Uncertainty Quantification, and Transfer Learning in Data‐Driven Parameterizations: Lessons From the Emulation of Gravity Wave Momentum Transport in WACCM

Contact Info

Product

Resources

About