• Aires, F., W. B. Rossow, N. A. Scott, and A. Chédin, 2002: Remote sensing from the infrared atmospheric sounding interferometer instrument 2. Simultaneous retrieval of temperature, water vapor, and ozone atmospheric profiles. J. Geophys. Res., 107, 4620, https://doi.org/10.1029/2001JD001591.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Alley, R. B., K. A. Emanuel, and F. Zhang, 2019: Advances in weather prediction. Science, 363, 342344, https://doi.org/10.1126/science.aav7274.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Anderson, J. L., and S. L. Anderson, 1999: A Monte Carlo implementation of the nonlinear filtering problem to produce ensemble assimilations and forecasts. Mon. Wea. Rev., 127, 27412758, https://doi.org/10.1175/1520-0493(1999)127<2741:AMCIOT>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Blayo, É., M. Bocquet, E. Cosme, and L. F. Cugliandolo, 2014: Advanced data assimilation for geosciences: Lecture notes of the Les Houches School of Physics: Special Issue, June 2012. Oxford University Press, https://doi.org/10.1093/acprof:oso/9780198723844.001.0001.

    • Search Google Scholar
    • Export Citation
  • Blyverket, J., P. D. Hamer, L. Bertino, C. Albergel, D. Fairbairn, and W. A. Lahoz, 2019: An Evaluation of the EnKF vs. EnOI and the assimilation of SMAP, SMOS and ESA CCI Soil moisture data over the contiguous U.S. Remote Sens., 11, 478, https://doi.org/10.3390/rs11050478.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bobylev, L. P., E. V. Zabolotskikh, L. M. Mitnik, and M. L. Mitnik, 2009: Atmospheric water vapor and cloud liquid water retrieval over the Arctic Ocean using satellite passive microwave sensing. IEEE Trans. Geosci. Remote Sens., 48, 283294, https://doi.org/10.1109/TGRS.2009.2028018.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Burgers, G., P. Jan van Leeuwen, and G. Evensen, 1998: Analysis scheme in the ensemble Kalman filter. Mon. Wea. Rev., 126, 17191724, https://doi.org/10.1175/1520-0493(1998)126<1719:ASITEK>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Caron, J.-F., and M. Buehner, 2018: Scale-dependent background error covariance localization: Evaluation in a global deterministic weather forecasting system. Mon. Wea. Rev., 146, 13671381, https://doi.org/10.1175/MWR-D-17-0369.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Casas, C. Q., R. Arcucci, P. Wu, C. Pain, and Y.-K. Guo, 2020: A reduced order deep data assimilation model. Physica D, 412, 132615, https://doi.org/10.1016/j.physd.2020.132615.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • C3S, 2017: ERA5: Fifth generation of ECMWF atmospheric reanalyses of the global climate. Copernicus Climate Change Service Climate Data Store (CDS), accessed 13 March 2021, https://cds.climate.copernicus.eu/.

    • Search Google Scholar
    • Export Citation
  • Dean, J., and Coauthors, 2012: Large scale distributed deep networks. Advances in Neural Information Processing Systems 25: 26th Annual Conf. on Neural Information Processing Systems 2012 (NIPS 2012), Lake Tahoe, NV, Neural Information Processing Systems Foundation, Inc. (NIPS), 12231231, https://papers.nips.cc/paper/2012/hash/6aca97005c68f1206823815f66102863-Abstract.html.

    • Search Google Scholar
    • Export Citation
  • Errico, R. M., P. Bauer, and J.-F. Mahfouf, 2007: Issues regarding the assimilation of cloud and precipitation data. J. Atmos. Sci., 64, 37853798, https://doi.org/10.1175/2006JAS2044.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Fabry, F., and V. Meunier, 2020: Why are radar data so difficult to assimilate skillfully? Mon. Wea. Rev., 148, 28192836, https://doi.org/10.1175/MWR-D-19-0374.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Gaspari, G., and S. E. Cohn, 1999: Construction of correlation functions in two and three dimensions. Quart. J. Roy. Meteor. Soc., 125, 723757, https://doi.org/10.1002/qj.49712555417.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Geer, A. J., and Coauthors, 2018: All-sky satellite data assimilation at operational weather forecasting centres. Quart. J. Roy. Meteor. Soc., 144, 11911217, https://doi.org/10.1002/qj.3202.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Ham, Y. G., J. H. Kim, E. S. Kim, and K. W. On, 2021: Unified deep learning model for El Niño/Southern Oscillation forecasts by incorporating seasonality in climate data. Sci. Bull., 66, 13581366, https://doi.org/10.1016/j.scib.2021.03.009.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Jam, J., C. Kendrick, K. Walker, V. Drouard, J. G. S. Hsu, and M. H. Yap, 2021: A comprehensive review of past and present image inpainting methods. Comput. Vis. Image Underst., 203, 103147, https://doi.org/10.1016/j.cviu.2020.103147.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Jin, J., H. X. Lin, A. Segers, Y. Xie, and A. Heemink, 2019: Machine learning for observation bias correction with application to dust storm data assimilation. Atmos. Chem. Phys., 19, 10 00910 026, https://doi.org/10.5194/acp-19-10009-2019.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Jung, Y., G. Zhang, and M. Xue, 2008: Assimilation of simulated polarimetric radar data for a convective storm using the ensemble Kalman filter. Part I: Observation operators for reflectivity and polarimetric variables. Mon. Wea. Rev., 136, 22282245, https://doi.org/10.1175/2007MWR2083.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Kang, S. K., S. A. Shin, S. Seo, M. S. Byun, D. Y. Lee, Y. K. Kim, D. S. Lee, and J. S. Lee, 2021: Deep learning-based 3D inpainting of brain MR images. Sci. Rep., 11, 1673, https://doi.org/10.1038/s41598-020-80930-w.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Mao, X.-J., C. Shen, and Y.-B. Yang, 2016: Image restoration using convolutional auto-encoders with symmetric skip connections. arXiv, 1606.08921, https://arxiv.org/abs/1606.08921.

    • Search Google Scholar
    • Export Citation
  • Mayer, R., and H.-A. Jacobsen, 2020: Scalable deep learning on distributed infrastructures: Challenges, techniques, and tools. ACM Comput. Surv., 53, 137, https://doi.org/10.1145/3363554.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Miyoshi, T., and K. Kondo, 2013: A multi-scale localization approach to an ensemble Kalman filter. SOLA, 9, 170173, https://doi.org/10.2151/sola.2013-038.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Pathak J., and Coauthors, 2022: FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators. arXiv, 2202.11214, https://arxiv.org/abs/2202.11214.

    • Search Google Scholar
    • Export Citation
  • Pu, Z., and E. Kalnay, 2019: Numerical weather prediction basics: Models, numerical methods, and data assimilation. Handbook of Hydrometeorological Ensemble Forecasting, Q. Duan, Eds., Springer, 6797.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Sakov, P., and P. R. Oke, 2008: Implications of the form of the ensemble transformation in the ensemble square root filters. Mon. Wea. Rev., 136, 10421053, https://doi.org/10.1175/2007MWR2021.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Simmons, A. J., and A. Hollingsworth, 2002: Some aspects of the improvement in skill of numerical weather prediction. Quart. J. Roy. Meteor. Soc., 128, 647677, https://doi.org/10.1256/003590002321042135.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Sodhi, J. S., and F. Fabry, 2020: Multiscale assimilation of radar reflectivity. 24th Conf. on Integrated Observing and Assimilation Systems for the Atmosphere, Oceans, and Land Surface (IOAS-AOLS), Boston, MA, Amer. Meteor. Soc., 4A.4, https://ams.confex.com/ams/2020Annual/meetingapp.cgi/Paper/363970.

    • Search Google Scholar
    • Export Citation
  • Tippett, M. K., J. L. Anderson, C. H. Bishop, T. M. Hamill, and J. S. Whitaker, 2003: Ensemble square root filters. Mon. Wea. Rev., 131, 14851490, https://doi.org/10.1175/1520-0493(2003)131<1485:ESRF>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Vallis, G. K., E. P. Gerber, P. J. Kushner, and B. A. Cash, 2004: A mechanism and simple dynamical model of the North Atlantic Oscillation and annular modes. J. Atmos. Sci., 61, 264280, https://doi.org/10.1175/1520-0469(2004)061<0264:AMASDM>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Wang, Z., E. P. Simoncelli, and A. C. Bovik, 2003: Multiscale structural similarity for image quality assessment. The Thrity-Seventh Asilomar Conf. on Signals, Systems & Computers, Institute of Electrical and Electronics Engineers, Vol. 2, 13981402.

    • Search Google Scholar
    • Export Citation
  • Weyn, J. A., D. R. Durran, and R. Caruana, 2020: Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere. J. Adv. Model. Earth Syst., 12, e2020MS002109, https://doi.org/10.1029/2020MS002109.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Whitaker, J. S., and T. M. Hamill, 2002: Ensemble data assimilation without perturbed observations. Mon. Wea. Rev., 130, 19131924, https://doi.org/10.1175/1520-0493(2002)130<1913:EDAWPO>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Xie, J., L. Xu, and E. Chen, 2012: Image denoising and inpainting with deep neural networks. Adv. Neural Info. Process. Syst., 25, 341349.

    • Search Google Scholar
    • Export Citation
  • Ying, Y., 2020: Assimilating observations with spatially correlated errors using a serial ensemble filter with a multiscale approach. Mon. Wea. Rev., 148, 33973412, https://doi.org/10.1175/MWR-D-19-0387.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zheng, M., and Coauthors, 2021: Data gaps within atmospheric rivers over the northeastern Pacific. Bull. Amer. Meteor. Soc., 102, E492E524, https://doi.org/10.1175/BAMS-D-19-0287.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 1006 1004 41
Full Text Views 224 222 4
PDF Downloads 281 279 6

Deep Learning Augmented Data Assimilation: Reconstructing Missing Information with Convolutional Autoencoders

Yueya WangaDivision of Environment and Sustainability, Hong Kong University of Science and Technology, Hong Kong, China

Search for other papers by Yueya Wang in
Current site
Google Scholar
PubMed
Close
,
Xiaoming ShiaDivision of Environment and Sustainability, Hong Kong University of Science and Technology, Hong Kong, China

Search for other papers by Xiaoming Shi in
Current site
Google Scholar
PubMed
Close
,
Lili LeibSchool of Atmospheric Sciences, Nanjing University, Nanjing, China

Search for other papers by Lili Lei in
Current site
Google Scholar
PubMed
Close
, and
Jimmy Chi-Hung FungaDivision of Environment and Sustainability, Hong Kong University of Science and Technology, Hong Kong, China
cDepartment of Mathematics, Hong Kong University of Science and Technology, Hong Kong, China

Search for other papers by Jimmy Chi-Hung Fung in
Current site
Google Scholar
PubMed
Close
Restricted access

Abstract

Remote sensing data play a critical role in improving numerical weather prediction (NWP). However, the physical principles of radiation dictate that data voids frequently exist in physical space (e.g., subcloud area for satellite infrared radiance or no-precipitation region for radar reflectivity). Such data gaps impair the accuracy of initial conditions derived from data assimilation (DA), which has a negative impact on NWP. We use the barotropic vorticity equation to demonstrate the potential of deep learning augmented data assimilation (DDA), which involves reconstructing spatially complete pseudo-observation fields from incomplete observations and using them for DA. By training a convolutional autoencoder (CAE) with a long simulation at a coarse “forecast” resolution (T63), we obtained a deep learning approximation of the “reconstruction operator,” which maps spatially incomplete observations to a model state with full spatial coverage and resolution. The CAE was applied to an incomplete streamfunction observation (∼30% missing) from a high-resolution benchmark simulation and demonstrated satisfactory reconstruction performance, even when only very sparse (1/16 of T63 grid density) observations were used as input. When only spatially incomplete observations are used, the analysis fields obtained from ensemble square root filter (EnSRF) assimilation exhibit significant error. However, in DDA, when EnSRF takes in the combined data from the incomplete observations and CAE reconstruction, analysis error reduces significantly. Such gains are more pronounced with sparse observation and small ensemble size because the DDA analysis is much less sensitive to observation density and ensemble size than the conventional DA analysis, which is based solely on incomplete observations.

Significance Statement

Data assimilation plays a critical role in improving the skills of modern numerical weather prediction by establishing accurate initial conditions. However, unobservable regions are common in observation data, particularly those derived from remote sensing. The nonlinear relationship between data from observable regions and the physical state of unobservable regions may impede DA efficiency. As a result, we propose that deep learning be used to improve data assimilation in such cases by reconstructing a spatially complete first guess of the physical state with deep learning and then applying data assimilation to the reconstructed field. Such deep learning augmentation is found effective in improving the accuracy of data assimilation, especially for sparse observation and small ensemble size.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Xiaoming Shi, shixm@ust.hk

Abstract

Remote sensing data play a critical role in improving numerical weather prediction (NWP). However, the physical principles of radiation dictate that data voids frequently exist in physical space (e.g., subcloud area for satellite infrared radiance or no-precipitation region for radar reflectivity). Such data gaps impair the accuracy of initial conditions derived from data assimilation (DA), which has a negative impact on NWP. We use the barotropic vorticity equation to demonstrate the potential of deep learning augmented data assimilation (DDA), which involves reconstructing spatially complete pseudo-observation fields from incomplete observations and using them for DA. By training a convolutional autoencoder (CAE) with a long simulation at a coarse “forecast” resolution (T63), we obtained a deep learning approximation of the “reconstruction operator,” which maps spatially incomplete observations to a model state with full spatial coverage and resolution. The CAE was applied to an incomplete streamfunction observation (∼30% missing) from a high-resolution benchmark simulation and demonstrated satisfactory reconstruction performance, even when only very sparse (1/16 of T63 grid density) observations were used as input. When only spatially incomplete observations are used, the analysis fields obtained from ensemble square root filter (EnSRF) assimilation exhibit significant error. However, in DDA, when EnSRF takes in the combined data from the incomplete observations and CAE reconstruction, analysis error reduces significantly. Such gains are more pronounced with sparse observation and small ensemble size because the DDA analysis is much less sensitive to observation density and ensemble size than the conventional DA analysis, which is based solely on incomplete observations.

Significance Statement

Data assimilation plays a critical role in improving the skills of modern numerical weather prediction by establishing accurate initial conditions. However, unobservable regions are common in observation data, particularly those derived from remote sensing. The nonlinear relationship between data from observable regions and the physical state of unobservable regions may impede DA efficiency. As a result, we propose that deep learning be used to improve data assimilation in such cases by reconstructing a spatially complete first guess of the physical state with deep learning and then applying data assimilation to the reconstructed field. Such deep learning augmentation is found effective in improving the accuracy of data assimilation, especially for sparse observation and small ensemble size.

© 2022 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Xiaoming Shi, shixm@ust.hk
Save