Comparing storm resolving models and climates via unsupervised machine learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
15 Dec 2023
15 Dec 2023
Historique:
received:
29
06
2023
accepted:
08
12
2023
medline:
16
12
2023
pubmed:
16
12
2023
entrez:
15
12
2023
Statut:
epublish
Résumé
Global storm-resolving models (GSRMs) have gained widespread interest because of the unprecedented detail with which they resolve the global climate. However, it remains difficult to quantify objective differences in how GSRMs resolve complex atmospheric formations. This lack of comprehensive tools for comparing model similarities is a problem in many disparate fields that involve simulation tools for complex data. To address this challenge we develop methods to estimate distributional distances based on both nonlinear dimensionality reduction and vector quantization. Our approach automatically learns physically meaningful notions of similarity from low-dimensional latent data representations that the different models produce. This enables an intercomparison of nine GSRMs based on their high-dimensional simulation data (2D vertical velocity snapshots) and reveals that only six are similar in their representation of atmospheric dynamics. Furthermore, we uncover signatures of the convective response to global warming in a fully unsupervised way. Our study provides a path toward evaluating future high-resolution simulation data more objectively.
Identifiants
pubmed: 38102176
doi: 10.1038/s41598-023-49455-w
pii: 10.1038/s41598-023-49455-w
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
22365Subventions
Organisme : National Science Foundation
ID : 1633631
Organisme : Office of Advanced Cyberinfrastructure
ID : OAC-1835863
Organisme : Division of Atmospheric and Geospace Sciences
ID : AGS-1912134
Organisme : Defense Advanced Research Projects Agency
ID : HR001120C0021
Organisme : Enabling Aerosol-cloud interactions at GLobal convection-permitting scalES (EAGLES) project
ID : 74358
Informations de copyright
© 2023. The Author(s).
Références
Brient, F. & Bony, S. Interpretation of the positive low-cloud feedback predicted by a climate model under global warming. Clim. Dyn. 40, 05. https://doi.org/10.1007/s00382-011-1279-7 (2012).
doi: 10.1007/s00382-011-1279-7
Blossey, P. N. et al. Cgils phase 2 les intercomparison of response of subtropical marine low cloud regimes to co2 quadrupling and a CMIP3 composite forcing change. J. Adv. Model. Earth Syst. 8(4), 1714–1726. https://doi.org/10.1002/2016MS000765 (2016).
doi: 10.1002/2016MS000765
Schneider, T. et al. Climate goals and computing the future of clouds. Nat. Clim. Change 7(1), 3–5. https://doi.org/10.1038/nclimate3190 (2017).
doi: 10.1038/nclimate3190
Stevens, B. et al. Dyamond: The dynamics of the atmospheric general circulation modeled on non-hydrostatic domains. Prog. Earth Planet Sci. 6(1), 61. https://doi.org/10.1186/s40645-019-0304-z (2019).
doi: 10.1186/s40645-019-0304-z
Randall, D., Khairoutdinov, M., Arakawa, A. & Grabowski, W. Breaking the cloud parameterization deadlock. Bull. Am. Meteorol. Soc. 84(11), 1547–1564. https://doi.org/10.1175/BAMS-84-11-1547 (2003).
doi: 10.1175/BAMS-84-11-1547
Christensen, H. M., Moroz, I. M. & Palmer, T. N. Simulating weather regimes: Impact of stochastic and perturbed parameter schemes in a simple atmospheric model. Clim. Dyn. 44(7), 2195–2214. https://doi.org/10.1007/s00382-014-2239-9 (2015).
doi: 10.1007/s00382-014-2239-9
Daleu, C. L. et al. Intercomparison of methods of coupling between convection and large-scale circulation: 1 comparison over uniform surface conditions. J. Adv. Model. Earth Syst. 7(4), 1576–1601. https://doi.org/10.1002/2015MS000468 (2015).
doi: 10.1002/2015MS000468
pubmed: 27642500
pmcid: 5006259
Li, Z. et al. Long-term impacts of aerosols on the vertical development of clouds and precipitation. Nat. Geosci. 4(12), 888–894. https://doi.org/10.1038/ngeo1313 (2011).
doi: 10.1038/ngeo1313
Li, G. & Xie, S.-P. Origins of tropical-wide sst biases in cmip multi-model ensembles. Geophys. Res. Lett. 39, 22. https://doi.org/10.1029/2012GL053777 (2012).
doi: 10.1029/2012GL053777
Kooperman, G. J., Pritchard, M. S., Burt, M. A., Branson, M. D. & Randall, D. A. Impacts of cloud superparameterization on projected daily rainfall intensity climate changes in multiple versions of the community earth system model. J. Adv. Model. Earth Syst. 8(4), 1727–1750 (2016).
doi: 10.1002/2016MS000715
Judt, F. Insights into atmospheric predictability through global convection-permitting model simulations. J. Atmos. Sci. 75(5), 1477–1497. https://doi.org/10.1175/JAS-D-17-0343.1 (2018).
doi: 10.1175/JAS-D-17-0343.1
Bretherton, C. S. & Khairoutdinov, M. F. Convective self-aggregation feedbacks in near-global cloud-resolving simulations of an aquaplanet. J. Adv. Model. Earth Syst. 7(4), 1765–1787. https://doi.org/10.1002/2015MS000499 (2015).
doi: 10.1002/2015MS000499
Mapes, B., Tulich, S., Nasuno, T. & Satoh, M. Predictability aspects of global aqua-planet simulations with explicit convection. J. Meteorol. Soc. Jpn. Ser. II II(86), 175–185. https://doi.org/10.2151/jmsj.86A.175 (2008).
doi: 10.2151/jmsj.86A.175
Blumenthal, M. B. Predictability of a coupled ocean-atmosphere model. J. Clim. 4(8), 766–784. https://doi.org/10.1175/1520-0442(1991)004<0766:POACOM>2.0.CO (1991).
doi: 10.1175/1520-0442(1991)004<0766:POACOM>2.0.CO
Yan Xue, M. A., Cane, S. E. Z. & Blumenthal, M. B. On the prediction of enso: A study with a low-order markov model. Tellus A Dyn. Meteorol. Oceanogr. 46(4), 512–528. https://doi.org/10.3402/tellusa.v46i4.15641 (1994).
doi: 10.3402/tellusa.v46i4.15641
Wilks, D. S. Statistical Methods in the Atmospheric Sciences (Elsevier, 2006).
Palmer, T. N. A personal perspective on modelling the climate system. Proc. Math. Phys. Eng. Sci. 472(2188), 20150772. https://doi.org/10.1098/rspa.2015.0772 (2016).
doi: 10.1098/rspa.2015.0772
pubmed: 27274686
pmcid: 4892275
Marat, K. & David, R. Cloud resolving modeling of the arm summer 1997 iop: Model formulation, results, uncertainties, and sensitivities. J. Atmos. Sci. 60, 607–625. https://doi.org/10.1175/1520-0469(2003)060<0607:CRMOTA>2.0.CO;2 (2003).
doi: 10.1175/1520-0469(2003)060<0607:CRMOTA>2.0.CO;2
Khairoutdinov, M. F. & Kogan, Y. L. A large eddy simulation model with explicit microphysics: Validation against aircraft observations of a stratocumulus-topped boundary layer. J. Atmos. Sci. 56(13), 2115–2131. https://doi.org/10.1175/1520-0469(1999)056<2115:ALESMW>2.0.CO;2 (1999).
doi: 10.1175/1520-0469(1999)056<2115:ALESMW>2.0.CO;2
Khairoutdinov, M., Randall, D. & DeMott, C. Simulations of the atmospheric general circulation using a cloud-resolving model as a superparameterization of physical processes. J. Atmos. Sci. 62(7), 2136–2154. https://doi.org/10.1175/JAS3453.1 (2005).
doi: 10.1175/JAS3453.1
Kingma, D. P. & Welling, M. Auto-encoding variational bayes. arXiv:abs/1312.6114 [CoRR] (2014).
Alemi, A. A., Poole, B., Fischer, I. S., Dillon, J. V., Saurous. R. A., & Murphy, K. Fixing a broken elbo. In ICML (2018).
Tulich, S. N., Randall, D. A. & Mapes, B. E. Vertical-mode and cloud decomposition of large-scale convectively coupled gravity waves in a two-dimensional cloud-resolving model. J. Atmos. Sci. 64(4), 1210–1229. https://doi.org/10.1175/JAS3884.1 (2007).
doi: 10.1175/JAS3884.1
Johnson, R. H., Rickenbach, T. M., Rutledge, S. A., Ciesielski, P. E. & Schubert, W. H. Trimodal characteristics of tropical convection. J. Clim. 12(8), 2397–2418. https://doi.org/10.1175/1520-0442(1999)012<2397:TCOTC>2.0.CO;2 (1999).
doi: 10.1175/1520-0442(1999)012<2397:TCOTC>2.0.CO;2
Rabanser, S., Günnemann, S., & Lipton, Z. Failing loudly: An empirical study of methods for detecting dataset shift. In Advances in Neural Information Processing Systems (Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E. & Garnett, R. editors, ), Vol. 32 (Curran Associates, Inc., 2019). https://proceedings.neurips.cc/paper/2019/file/846c260d715e5b854ffad5f70a516c88-Paper.pdf .
Schonlau, M. The clustergram: A graph for visualizing hierarchical and nonhierarchical cluster analyses. Stand. Genom. Sci. 2(4), 391–402. https://doi.org/10.1177/1536867X0200200405 (2002).
doi: 10.1177/1536867X0200200405
Gray, R. Vector quantization. IEEE Assp Mag. 1(2), 4–29 (1984).
doi: 10.1109/MASSP.1984.1162229
Yibo, Y., Stephan, M., & Lucas, T. An introduction to neural data compression. arxiv:2202.06533 . (2022)
Knutti, R., Masson, D. & Gettelman, A. Climate model genealogy: Generation cmip5 and how we got there. Geophys. Res. Lett. 40(6), 1194–1199. https://doi.org/10.1002/grl.50256 (2013).
doi: 10.1002/grl.50256
Allan, R. P. et al. Physically consistent responses of the global atmospheric hydrological cycle in models and observations. Surv. Geophys. 35(3), 533–552. https://doi.org/10.1007/s10712-012-9213-z (2014).
doi: 10.1007/s10712-012-9213-z
Neelin, J. D., Chou, C. & Su, H. Tropical drought regions in global warming and el nino teleconnections. Geophys. Res. Lett. 30(24), 96. https://doi.org/10.1029/2003GL018625 (2003).
doi: 10.1029/2003GL018625
Chia, C. & Neelin, J. D. Mechanisms of global warming impacts on regional tropical precipitation. J. Clim. 17(13), 2688–2701. https://doi.org/10.1175/1520-0442(2004)017<2688:MOGWIO>2.0.CO;2 (2004).
doi: 10.1175/1520-0442(2004)017<2688:MOGWIO>2.0.CO;2
Parishani, H. et al. Insensitivity of the cloud response to surface warming under radical changes to boundary layer turbulence and cloud microphysics: Results from the ultraparameterized cam. J. Adv. Model. Earth Syst. 10(12), 3139–3158. https://doi.org/10.1029/2018MS001409 (2018).
doi: 10.1029/2018MS001409
Zelinka, M. D., Klein, S. A. & Hartmann, D. L. Computing and partitioning cloud feedbacks using cloud property histograms part ii: Attribution to changes in cloud amount, altitude, and optical depth. J. Clim. 25(11), 3736–3754. https://doi.org/10.1175/JCLI-D-11-00249.1 (2012).
doi: 10.1175/JCLI-D-11-00249.1
Sherwood, S. C. et al. Relative humidity changes in a warmer climate. J. Geophys. Res. Atmos. 115, D9. https://doi.org/10.1029/2009JD012585 (2010).
doi: 10.1029/2009JD012585
Romps, D. M. An analytical model for tropical relative humidity. J. Clim. 27(19), 7432–7449. https://doi.org/10.1175/JCLI-D-14-00255.1 (2014).
doi: 10.1175/JCLI-D-14-00255.1
Lauer, A., Hamilton, K., Wang, Y., Phillips, V. T. J. & Bennartz, R. The impact of global warming on marine boundary layer clouds over the eastern pacific—a regional model study. J. Clim. 23(21), 5844–5863. https://doi.org/10.1175/2010JCLI3666.1 (2010).
doi: 10.1175/2010JCLI3666.1
Dror, T., Koren, I., Altaratz, O. & Heiblum, R. H. On the abundance and common properties of continental, organized shallow (green) clouds. IEEE Trans. Geosci. Remote Sens. 59(6), 4570–4578. https://doi.org/10.1109/TGRS.2020.3023085 (2021).
doi: 10.1109/TGRS.2020.3023085
Mapes, B. E. Convective inhibition, subgrid-scale triggering energy, and stratiform instability in a toy tropical wave model. J. Atmos. Sci. 57(10), 1515–1535. https://doi.org/10.1175/1520-0469(2000)057<1515:CISSTE>2.0.CO;2 (2000).
doi: 10.1175/1520-0469(2000)057<1515:CISSTE>2.0.CO;2
Dror, T., Silverman, V., Altaratz, O., Chekroun, M. D. & Koren, I. Uncovering the large-scale meteorology that drives continental, shallow, green cumulus through supervised classification. Geophys. Res. Lett. 49(8), e2021GL096684. https://doi.org/10.1029/2021GL096684 (2022).
doi: 10.1029/2021GL096684
pubmed: 35866057
pmcid: 9286646
Brenowitz, N. D., Beucler, T., Pritchard, M. & Bretherton, C. S. Interpreting and stabilizing machine-learning parametrizations of convection. J. Atmos. Sci. 77(12), 4357–4375. https://doi.org/10.1175/JAS-D-20-0082.1 (2020).
doi: 10.1175/JAS-D-20-0082.1
Dror, T., Chekroun, M. D., Altaratz, O. & Koren, I. Deciphering organization of goes-16 green cumulus through the empirical orthogonal function (eof) lens. Atmos. Chem. Phys. 21(16), 12261–12272. https://doi.org/10.5194/acp-21-12261-2021 (2021).
doi: 10.5194/acp-21-12261-2021
Zhang, Y. & Klein, S. A. Factors controlling the vertical extent of fair-weather shallow cumulus clouds over land: Investigation of diurnal-cycle observations collected at the arm southern great plains site. J. Atmos. Sci. 70(4), 1297–1315. https://doi.org/10.1175/JAS-D-12-0131.1 (2013).
doi: 10.1175/JAS-D-12-0131.1
Ahlgrimm, M. & Forbes, R. The impact of low clouds on surface shortwave radiation in the ECMWF model. Mon. Weather Rev. 140(11), 3783–3794. https://doi.org/10.1175/MWR-D-11-00316.1 (2012).
doi: 10.1175/MWR-D-11-00316.1
Klocke, D., Brueck, M., Hohenegger, C. & Stevens, B. Rediscovery of the doldrums in storm-resolving simulations over the tropical Atlantic. Nat. Geosci. 10(12), 891–896. https://doi.org/10.1038/s41561-017-0005-4 (2017).
doi: 10.1038/s41561-017-0005-4
Nugent, J. M., Turbeville, S. M., Bretherton, C. S., Blossey, P. N. & Ackerman, T. P. Tropical cirrus in global storm-resolving models: 1 role of deep convection. Earth Sp. Sci. 9(2), e2021EA001965. https://doi.org/10.1029/2021EA001965 (2022).
doi: 10.1029/2021EA001965
Atlas, R. & Bretherton, C. Aircraft observations of gravity wave activity and turbulence in the tropical tropopause layer: Prevalence, influence on cirrus and comparison with global-storm resolving models. Atmos. Chem. Phys. Discuss. 1–30, 2022. https://doi.org/10.5194/acp-2022-491 (2022).
doi: 10.5194/acp-2022-491
Mangipudi, H., Mooers, G., Pritchard, M., Beucler, T., & Mandt, S. Analyzing high-resolution clouds and convection using multi-channel vaes (2021).
Eyring, V. et al. Overview of the coupled model intercomparison project phase 6 (cmip6) experimental design and organization. Geosci. Model Dev. 9(5), 1937–1958. https://doi.org/10.5194/gmd-9-1937-2016 (2016).
doi: 10.5194/gmd-9-1937-2016
Haarsma, R. J. et al. High resolution model intercomparison project (highresmip v1.0) for cmip6. Geosci. Model Dev. 9(11), 4185–4208. https://doi.org/10.5194/gmd-9-4185-2016 (2016).
doi: 10.5194/gmd-9-4185-2016
Norman, M. R. et al. Unprecedented cloud resolution in a gpu-enabled full-physics atmospheric climate simulation on olcf’s summit supercomputer. Int. J. High Perform. Comput. Appl. 36(1), 93–105. https://doi.org/10.1177/10943420211027539 (2022).
doi: 10.1177/10943420211027539
Hannah, W. M. et al. Initial results from the super-parameterized e3sm. J. Adv. Model. Earth Syst. 12(1), e2019MS001863. https://doi.org/10.1029/2019MS001863 (2020).
doi: 10.1029/2019MS001863
David, A. R. Beyond deadlock. Geophys. Res. Lett. 40(22), 5970–5976. https://doi.org/10.1002/2013GL057998 (2013).
doi: 10.1002/2013GL057998
Duras, J., Ziemen, F., & Klocke, D. The dyamond winter data collection. In EGU General Assembly Conference Abstracts, EGU21-4687 (2021).
Deardorff, J. W. Closure of second-and third-moment rate equations for diffusion in homogeneous turbulence. Phys. Fluids, 21, 525–530 (1978). https://api.semanticscholar.org/CorpusID:121223716 .
Beucler, T. & Cronin, T. A budget for the size of convective self-aggregation. Q. J. R. Meteorol. Soc. 145(720), 947–966. https://doi.org/10.1002/qj.3468 (2019).
doi: 10.1002/qj.3468
Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M. M, Mohamed, S., & Lerchner, A. beta-vae: Learning basic visual concepts with a constrained variational framework. In ICLR (2017).
Alemi, A., Fischer, I., Dillon, J., & Murphy, K. Deep variational information bottleneck. In ICLR (2017). arXiv:1612.00410 .
Mooers, G., Tuyls, J., Mandt, S., Pritchard, M., & Beucler, T. G. Generative modeling of atmospheric convection. In Proceedings of the 10th International Conference on Climate Informatics, CI2020, New York, NY, USA, 98–105 (Association for Computing Machinery, 2020). ISBN 9781450388481. https://doi.org/10.1145/3429309.3429324 .
Lloyd, S. Least squares quantization in pcm. IEEE Trans. Inf. Theory 28(2), 129–137. https://doi.org/10.1109/TIT.1982.1056489 (1982).
doi: 10.1109/TIT.1982.1056489
Macqueen, J. Some methods for classification and analysis of multivariate observations. In 5-th Berkeley Symposium on Mathematical Statistics and Probability, 281–297 (1967).
Rousseeuw, P. J. Silhouettes: A graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65. https://doi.org/10.1016/0377-0427(87)90125-7 (1987).
doi: 10.1016/0377-0427(87)90125-7
Davies, D. L. & Bouldin, D. W. A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. 1(2), 224–227. https://doi.org/10.1109/TPAMI.1979.4766909 (1979).
doi: 10.1109/TPAMI.1979.4766909
pubmed: 21868852
Denby, L. Discovering the importance of mesoscale cloud organization through unsupervised classification. Geophys. Res. Lett. 47(1), e2019GL085190. https://doi.org/10.1029/2019GL085190 (2020).
doi: 10.1029/2019GL085190
Kurihana, T., Moyer, E., Willett, R., Gilton, D., & Foster, I. Data-driven cloud clustering via a rotationally invariant autoencoder (2021).
Duchi, J. Lecture notes for statistics 311/electrical engineering 377. Stanford 2, 23 (2016).
Student. Probable error of a correlation coefficient. Biometrika, 6(2/3):302–310 (1908). http://www.jstor.org/stable/2331474 .
Van Rossum, G. & Drake, F. L. Python 3 Reference Manual (CreateSpace, 2009).
Met Office. Cartopy: A cartographic python library with a Matplotlib interface. Exeter, Devon, 2010 (2015). https://scitools.org.uk/cartopy .
Hunter, J. D. Matplotlib: A 2d graphics environment. Comput. Sci. Eng. 9(3), 90–95. https://doi.org/10.1109/MCSE.2007.55 (2007).
doi: 10.1109/MCSE.2007.55