Non‐Linear Dimensionality Reduction With a Variational Encoder Decoder to Understand Convective Processes in Climate Models

Deep learning can accurately represent sub‐grid‐scale convective processes in climate models, learning from high resolution simulations. However, deep learning methods usually lack interpretability due to large internal dimensionality, resulting in reduced trustworthiness in these methods. Here, we...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of advances in modeling earth systems Ročník 14; číslo 8; s. e2022MS003130 - n/a
Hlavní autoři: Behrens, Gunnar, Beucler, Tom, Gentine, Pierre, Iglesias‐Suarez, Fernando, Pritchard, Michael, Eyring, Veronika
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States John Wiley & Sons, Inc 01.08.2022
American Geophysical Union (AGU)
Témata:
Atmosphere
Climate
Climate models
Clouds
Convection
Cumulus clouds
Deep learning
Diabatic heating
dimensionality reduction
Dimensions
ENVIRONMENTAL SCIENCES
explainable artificial intelligence
generative deep learning
Long wave radiation
Machine learning
Modelling
Moisture content
parameterization
Precipitation
Radiation
Simulation
Topography
convection
explainable artificial intelligence
parameterization
dimensionality reduction
generative deep learning
machine learning
ISSN:1942-2466, 1942-2466
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Deep learning can accurately represent sub‐grid‐scale convective processes in climate models, learning from high resolution simulations. However, deep learning methods usually lack interpretability due to large internal dimensionality, resulting in reduced trustworthiness in these methods. Here, we use Variational Encoder Decoder structures (VED), a non‐linear dimensionality reduction technique, to learn and understand convective processes in an aquaplanet superparameterized climate model simulation, where deep convective processes are simulated explicitly. We show that similar to previous deep learning studies based on feed‐forward neural nets, the VED is capable of learning and accurately reproducing convective processes. In contrast to past work, we show this can be achieved by compressing the original information into only five latent nodes. As a result, the VED can be used to understand convective processes and delineate modes of convection through the exploration of its latent dimensions. A close investigation of the latent space enables the identification of different convective regimes: (a) stable conditions are clearly distinguished from deep convection with low outgoing longwave radiation and strong precipitation; (b) high optically thin cirrus‐like clouds are separated from low optically thick cumulus clouds; and (c) shallow convective processes are associated with large‐scale moisture content and surface diabatic heating. Our results demonstrate that VEDs can accurately represent convective processes in climate models, while enabling interpretability and better understanding of sub‐grid‐scale physical processes, paving the way to increasingly interpretable machine learning parameterizations with promising generative properties. Plain Language Summary Deep neural nets are hard to interpret due to their hundred thousand or million trainable parameters without further postprocessing. We demonstrate in this paper the usefulness of a network type that is designed to drastically reduce this high dimensional information in a lower‐dimensional space to enhance the interpretability of predictions compared to regular deep neural nets. Our approach is, on the one hand, able to reproduce small‐scale cloud related processes in the atmosphere learned from a physical model that simulates these processes skillfully. On the other hand, our network allows us to identify key features of different cloud types in the lower‐dimensional space. Additionally, the lower‐order manifold separates tropical samples from polar ones with a remarkable skill. Overall, our approach has the potential to boost our understanding of various complex processes in Earth System science. Key Points A Variational Encoder Decoder (VED) can predict sub‐grid‐scale thermodynamics from the coarse‐scale climate state The VED's latent space can distinguish convective regimes, including shallow/deep/no convection The VED's latent space reveals the main sources of convective predictability at different latitudes
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
National Science Foundation Science and Technology Center
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
Columbia University
European Research Council (ERC)
SC0022331; 855187; PG010560-01; 2019625
ISSN:1942-2466
1942-2466
DOI:10.1029/2022MS003130