Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning

dc.citation.articleNumbere2020MS002084en_US
dc.citation.issueNumber11en_US
dc.citation.journalTitleJournal of Advances in Modeling Earth Systemsen_US
dc.citation.volumeNumber12en_US
dc.contributor.authorChattopadhyay, Asheshen_US
dc.contributor.authorSubel, Adamen_US
dc.contributor.authorHassanzadeh, Pedramen_US
dc.date.accessioned2020-12-16T19:47:16Zen_US
dc.date.available2020-12-16T19:47:16Zen_US
dc.date.issued2020en_US
dc.description.abstractTo make weather and climate models computationally affordable, small‐scale processes are usually represented in terms of the large‐scale, explicitly resolved processes using physics‐based/semi‐empirical parameterization schemes. Another approach, computationally more demanding but often more accurate, is super‐parameterization (SP). SP involves integrating the equations of small‐scale processes on high‐resolution grids embedded within the low‐resolution grid of large‐scale processes. Recently, studies have used machine learning (ML) to develop data‐driven parameterization (DD‐P) schemes. Here, we propose a new approach, data‐driven SP (DD‐SP), in which the equations of the small‐scale processes are integrated data‐drivenly (thus inexpensively) using ML methods such as recurrent neural networks. Employing multiscale Lorenz 96 systems as the testbed, we compare the cost and accuracy (in terms of both short‐term prediction and long‐term statistics) of parameterized low‐resolution (PLR) SP, DD‐P, and DD‐SP models. We show that with the same computational cost, DD‐SP substantially outperforms PLR and is more accurate than DD‐P, particularly when scale separation is lacking. DD‐SP is much cheaper than SP, yet its accuracy is the same in reproducing long‐term statistics (climate prediction) and often comparable in short‐term forecasting (weather prediction). We also investigate generalization: when models trained on data from one system are applied to a more chaotic system, we find that models often do not generalize, particularly when short‐term prediction accuracies are examined. However, we show that transfer learning, which involves re‐training the data‐driven model with a small amount of data from the new system, significantly improves generalization. Potential applications of DD‐SP and transfer learning in climate/weather modeling are discussed.en_US
dc.identifier.citationChattopadhyay, Ashesh, Subel, Adam and Hassanzadeh, Pedram. "Data‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learning." <i>Journal of Advances in Modeling Earth Systems,</i> 12, no. 11 (2020) Wiley: https://doi.org/10.1029/2020MS002084.en_US
dc.identifier.digital2020MS002084en_US
dc.identifier.doihttps://doi.org/10.1029/2020MS002084en_US
dc.identifier.urihttps://hdl.handle.net/1911/109721en_US
dc.language.isoengen_US
dc.publisherWileyen_US
dc.rightsThis is an open access article under the terms of the Creative Commons Attribution‐NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.en_US
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/en_US
dc.titleData‐Driven Super‐Parameterization Using Deep Learning: Experimentation With Multiscale Lorenz 96 Systems and Transfer Learningen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2020MS002084.pdf
Size:
3.64 MB
Format:
Adobe Portable Document Format