Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5

Simple item page
dc.citation.firstpage2221en_US
dc.citation.issueNumber5en_US
dc.citation.journalTitleGeoscientific Model Developmenten_US
dc.citation.lastpage2237en_US
dc.citation.volumeNumber15en_US
dc.contributor.authorChattopadhyay, Asheshen_US
dc.contributor.authorMustafa, Mustafaen_US
dc.contributor.authorHassanzadeh, Pedramen_US
dc.contributor.authorBach, Eviataren_US
dc.contributor.authorKashinath, Karthiken_US
dc.date.accessioned2022-04-15T14:45:31Zen_US
dc.date.available2022-04-15T14:45:31Zen_US
dc.date.issued2022en_US
dc.description.abstractThere is growing interest in data-driven weather prediction (DDWP), e.g., using convolutional neural networks such as U-NET that are trained on data from models or reanalysis. Here, we propose three components, inspired by physics, to integrate with commonly used DDWP models in order to improve their forecast accuracy. These components are (1) a deep spatial transformer added to the latent space of U-NET to capture rotation and scaling transformation in the latent space for spatiotemporal data, (2) a data-assimilation (DA) algorithm to ingest noisy observations and improve the initial conditions for next forecasts, and (3) a multi-time-step algorithm, which combines forecasts from DDWP models with different time steps through DA, improving the accuracy of forecasts at short intervals. To show the benefit and feasibility of each component, we use geopotential height at 500 hPa (Z500) from ERA5 reanalysis and examine the short-term forecast accuracy of specific setups of the DDWP framework. Results show that the spatial-transformer-based U-NET (U-STN) clearly outperforms the U-NET, e.g., improving the forecast skill by 45 %. Using a sigma-point ensemble Kalman (SPEnKF) algorithm for DA and U-STN as the forward model, we show that stable, accurate DA cycles are achieved even with high observation noise. This DDWP+DA framework substantially benefits from large (O(1000)) ensembles that are inexpensively generated with the data-driven forward model in each DA cycle. The multi-time-step DDWP+DA framework also shows promise; for example, it reduces the average error by factors of 2–3. These results show the benefits and feasibility of these three components, which are flexible and can be used in a variety of DDWP setups. Furthermore, while here we focus on weather forecasting, the three components can be readily adopted for other parts of the Earth system, such as ocean and land, for which there is a rapid growth of data and need for forecast and assimilation.en_US
dc.identifier.citationChattopadhyay, Ashesh, Mustafa, Mustafa, Hassanzadeh, Pedram, et al.. "Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5." <i>Geoscientific Model Development,</i> 15, no. 5 (2022) Copernicus Publications: 2221-2237. https://doi.org/10.5194/gmd-15-2221-2022.en_US
dc.identifier.digitalgmd-15-2221-2022en_US
dc.identifier.doihttps://doi.org/10.5194/gmd-15-2221-2022en_US
dc.identifier.urihttps://hdl.handle.net/1911/112092en_US
dc.language.isoengen_US
dc.publisherCopernicus Publicationsen_US
dc.rightsThis work is distributed under the Creative Commons Attribution 4.0 License.en_US
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_US
dc.titleTowards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5en_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
gmd-15-2221-2022.pdf
Size:
4.16 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Earth, Environmental and Planetary Sciences Publications
Mechanical Engineering Publications