@article{TEXTUAL,
      recid = {13011},
      author = {Sun, Y. Qiang and Pahlavan, Hamid A. and Chattopadhyay,  Ashesh and Hassanzadeh, Pedram and Lubis, Sandro W. and  Alexander, M. Joan and Gerber, Edwin P. and Sheshadri,  Aditi and Guan, Yifei},
      title = {Data Imbalance, Uncertainty Quantification, and Transfer  Learning in Data-Driven Parameterizations: Lessons From the  Emulation of Gravity Wave Momentum Transport in WACCM},
      journal = {Journal of Advances in Modeling Earth Systems},
      address = {2024-07-26},
      number = {TEXTUAL},
      abstract = {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 × CO<sub>2</sub>). 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.},
      url = {http://knowledge.uchicago.edu/record/13011},
}