- 1Faculty of Geosciences and Environment, University of Lausanne, Switzerland (tom.beucler@unil.ch)
- 2Expertise Center for Climate Extremes, University of Lausanne, Switzerland (tom.beucler@unil.ch)
- 3Deutsches Zentrum für Luft- und Raumfahrt, Institut für Physik der Atmosphäre, Oberpfaffenhofen, Germany (arthur.grundner@dlr.de)
- 4Courant Institute of Mathematical Sciences, New York University, New York, NY, USA
- 5Department of Physics, University of Oxford, Oxford, United Kingdom
- 6European Centre for Medium-Range Weather Forecasts, Reading, United Kingdom
- 7Cooperative Institute for Research in the Atmosphere (CIRA), Colorado State University, Fort Collins, CO, USA
- 8National Oceanic and Atmospheric Administration (NOAA) Global Systems Laboratory (GSL), Boulder, CO, USA
The added value of machine learning for weather and climate applications is measurable through performance metrics, but explaining it remains challenging, particularly for large deep learning models. Inspired by climate model hierarchies, we propose that a full hierarchy of Pareto-optimal models, defined within an appropriately determined error-complexity plane, can guide model development and help understand the models' added value. We demonstrate the use of Pareto fronts in atmospheric physics through three sample applications, with hierarchies ranging from semi-empirical models with minimal parameters (simplest) to deep learning algorithms (most complex). First, in cloud cover parameterization, we find that neural networks identify nonlinear relationships between cloud cover and its thermodynamic environment, and assimilate previously neglected features such as vertical gradients in relative humidity that improve the representation of low cloud cover. This added value is condensed into a ten-parameter equation that rivals deep learning models. Second, we establish a machine learning model hierarchy for emulating shortwave radiative transfer, distilling the importance of bidirectional vertical connectivity for accurately representing absorption and scattering, especially for multiple cloud layers. Third, we emphasize the importance of convective organization information when modeling the relationship between tropical precipitation and its surrounding environment. We discuss the added value of temporal memory when high-resolution spatial information is unavailable, with implications for precipitation parameterization. Therefore, by comparing data-driven models directly with existing schemes using Pareto optimality, we promote process understanding by hierarchically unveiling system complexity, with the hope of improving the trustworthiness of machine learning models in atmospheric applications.
Preprint: https://arxiv.org/abs/2408.02161
How to cite: Beucler, T., Grundner, A., Shamekh, S., Ukkonen, P., Chantry, M., and Lagerquist, R.: Distilling Machine Learning's Added Value: Pareto Fronts in Atmospheric Applications, EGU General Assembly 2025, Vienna, Austria, 27 Apr–2 May 2025, EGU25-15200, https://doi.org/10.5194/egusphere-egu25-15200, 2025.
