• Arakawa, A., and W. H. Schubert, 1974: Interaction of a cumulus cloud ensemble with the large-scale environment, Part I. J. Atmos. Sci., 31, 674701, https://doi.org/10.1175/1520-0469(1974)031<0674:IOACCE>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bony, S., and Coauthors, 2017: EUREC4A: A field campaign to elucidate the couplings between clouds, convection and circulation. Surv. Geophys., 38, 15291568, https://doi.org/10.1007/s10712-017-9428-0.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Bony, S., H. Schulz, J. Vial, and B. Stevens, 2020: Sugar, gravel, fish, and flowers: Dependence of mesoscale patterns of trade-wind clouds on environmental conditions. Geophys. Res. Lett., 48, e2019GL085988, https://doi.org/10.1029/2019gl085988.

    • Search Google Scholar
    • Export Citation
  • Bretherton, C. S., 2015: Insights into low-latitude cloud feedbacks from high-resolution models. Philos. Trans. Roy. Soc., 373A, 20140415, https://doi.org/10.1098/rsta.2014.0415.

    • Search Google Scholar
    • Export Citation
  • Chollet, F., and Coauthors, 2015: Keras. https://keras.io/.

  • Denby, L., 2020: Discovering the importance of mesoscale cloud organization through unsupervised classification. Geophys. Res. Lett., 47, e2019GL085190, https://doi.org/10.1029/2019gl085190.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Garay, M. J., R. Davies, C. Averill, and J. A. Westphal, 2004: Actinoform clouds: Overlooked examples of cloud self-organization at the mesoscale. Bull. Amer. Meteor. Soc., 85, 15851594, https://doi.org/10.1175/BAMS-85-10-1585.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hennon, C. C., and Coauthors, 2015: Cyclone center: Can citizen scientists improve tropical cyclone intensity records? Bull. Amer. Meteor. Soc., 96, 591607, https://doi.org/10.1175/BAMS-D-13-00152.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Hong, S., S. Kim, M. Joh, and S.-k. Song, 2017: GlobeNet: Convolutional neural networks for typhoon eye tracking from remote sensing imagery. arXiv, 4 pp., http://arxiv.org/abs/1708.03417.

  • Kurth, T., and Coauthors, 2018: Exascale deep learning for climate analytics. SC18: Int. Conf. for High Performance Computing, Networking, Storage and Analysis, Dallas, TX, IEEE, 649–660, https://doi.org/10.1109/SC.2018.00054.

    • Crossref
    • Export Citation
  • LeCun, Y., Y. Bengio, and G. Hinton, 2015: Deep learning. Nature, 521, 436444, https://doi.org/10.1038/nature14539.

  • Liu, Y., E. Racah, J. Correa, A. Khosrowshahi, D. Lavers, K. Kunkel, M. Wehner, and W. Collins, 2016: Application of deep convolutional neural networks for detecting extreme weather in climate datasets. Advances in Big Data Analytics, H. R. Arabnia and F. G. Tinetti, Eds., CSREA Press, 81–88, http://worldcomp-proceedings.com/proc/p2016/ABD6152.pdf.

  • Medeiros, B., and L. Nuijens, 2016: Clouds at Barbados are representative of clouds across the trade wind regions in observations and climate models. Proc. Natl. Acad. Sci. USA, 113, E3062E3070, https://doi.org/10.1073/pnas.1521494113.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Mudigonda, M., and Coauthors, 2017: Segmenting and tracking extreme climate events using neural networks. 31st Conf. on Neural Information Processing Systems, Long Beach, CA, NIPS, 5 pp., https://dl4physicalsciences.github.io/files/nips_dlps_2017_20.pdf.

  • Muhlbauer, A., I. L. McCoy, and R. Wood, 2014: Climatology of stratocumulus cloud morphologies: Microphysical properties and radiative effects. Atmos. Chem. Phys., 14, 66956716, https://doi.org/10.5194/acp-14-6695-2014.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Nicholls, S. D., and G. S. Young, 2007: Dendritic patterns in tropical cumulus: An observational analysis. Mon. Wea. Rev., 135, 19942005, https://doi.org/10.1175/MWR3379.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Nielsen, M. A., 2015: Neural Networks and Deep Learning. Determination Press, http://neuralnetworksanddeeplearning.com.

  • Norris, J. R., 1998: Low cloud type over the ocean from surface observations. Part II: Geographical and seasonal variations. J. Climate, 11, 383403, https://doi.org/10.1175/1520-0442(1998)011<0383:LCTOTO>2.0.CO;2.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Parishani, H., M. S. Pritchard, C. S. Bretherton, C. R. Terai, M. C. Wyant, M. Khairoutdinov, and B. Singh, 2018: 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, 31393158, https://doi.org/10.1029/2018MS001409.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Racah, E., C. Beckham, T. Maharaj, S. E. Kahou, Prabhat, and C. Pal, 2017: ExtremeWeather: A large-scale climate dataset for semi-supervised detection, localization, and understanding of extreme weather events. 31st Conf. on Neural Information Processing Systems, Long Beach, CA, NIPS, 12 pp., http://arxiv.org/abs/1612.02095.

    • Search Google Scholar
    • Export Citation
  • Rasp, S., 2020a: Sugar, flower, fish or gravel - Example human labels. figshare, https://doi.org/10.6084/m9.figshare.12141264.v1.

    • Crossref
    • Export Citation
  • Rasp, S., 2020b: Sugar, flower, fish or gravel - Example ml predictions. figshare, https://doi.org/10.6084/m9.figshare.8236289.v2.

    • Crossref
    • Export Citation
  • Rasp, S., 2020c: Sugar, flower, fish or gravel - Global predictions. figshare, https://doi.org/10.6084/m9.figshare.8236298.v2.

    • Crossref
    • Export Citation
  • Rasp, S., M. S. Pritchard, and P. Gentine, 2018: Deep learning to represent subgrid processes in climate models. Proc. Natl. Acad. Sci. USA, 115, 96849689, https://doi.org/10.1073/pnas.1810286115.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Rauber, R. M., and Coauthors, 2007: Rain in shallow cumulus over the ocean: The RICO campaign. Bull. Amer. Meteor. Soc., 88, 19121928, https://doi.org/10.1175/BAMS-88-12-1912.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Reichstein, M., G. Camps-Valls, B. Stevens, M. Jung, J. Denzler, N. Carvalhais, and Prabhat, 2019: Deep learning and process understanding for data-driven Earth system science. Nature, 566, 195204, https://doi.org/10.1038/s41586-019-0912-1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Rieck, M., L. Nuijens, and B. Stevens, 2012: Marine boundary layer cloud feedbacks in a constant relative humidity atmosphere. J. Atmos. Sci., 69, 25382550, https://doi.org/10.1175/JAS-D-11-0203.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Scher, S., and G. Messori, 2019: Weather and climate forecasting with neural networks: Using general circulation models (GCMs) with different complexity as a study ground. Geosci. Model Dev., 12, 27972809, https://doi.org/10.5194/gmd-12-2797-2019.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Stevens, B., and Coauthors, 2016: The Barbados Cloud Observatory: Anchoring investigations of clouds and circulation on the edge of the ITCZ. Bull. Amer. Meteor. Soc., 97, 787801, https://doi.org/10.1175/BAMS-D-14-00247.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Stevens, B., and Coauthors, 2019: A high-altitude long-range aircraft configured as a cloud observatory: The NARVAL expeditions. Bull. Amer. Meteor. Soc., 100, 10611077, https://doi.org/10.1175/BAMS-D-18-0198.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Stevens, B., and Coauthors, 2020: Sugar, gravel, fish, and flowers: Mesoscale cloud patterns in the tradewinds. Quart. J. Roy. Meteor. Soc., 146, 141152, https://doi.org/10.1002/qj.3662.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Tobin, I., S. Bony, and R. Roca, 2012: Observational evidence for relationships between the degree of aggregation of deep convection, water vapor, surface fluxes, and radiation. J. Climate, 25, 68856904, https://doi.org/10.1175/JCLI-D-11-00258.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Wood, R., and D. L. Hartmann, 2006: Spatial variability of liquid water path in marine low cloud: The importance of mesoscale cellular convection. J. Climate, 19, 17481764, https://doi.org/10.1175/JCLI3702.1.

    • Crossref
    • Search Google Scholar
    • Export Citation
  • Zheng, F., and Coauthors, 2018: Crowdsourcing methods for data collection in geophysics: State of the art, issues, and future directions. Rev. Geophys., 56, 698740, https://doi.org/10.1029/2018RG000616.

    • Crossref
    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 179 179 67
PDF Downloads 193 193 75

Combining Crowdsourcing and Deep Learning to Explore the Mesoscale Organization of Shallow Convection

View More View Less
  • 1 Technical University of Munich, Munich, Germany
  • 2 Max Planck Institute for Meteorology, Hamburg, Germany
  • 3 Sorbonne Université, LMD/IPSL, CNRS, Paris, France
  • 4 Max Planck Institute for Meteorology, Hamburg, Germany
© Get Permissions
Restricted access

Abstract

Humans excel at detecting interesting patterns in images, for example, those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. However, it is often difficult to gather enough data of subjective features for significant analysis. This paper presents an example of how two tools that have recently become accessible to a wide range of researchers, crowdsourcing and deep learning, can be combined to explore satellite imagery at scale. In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions. Shallow clouds play a large role in the Earth’s radiation balance yet are poorly represented in climate models. For this project four subjective patterns of organization were defined: Sugar, Flower, Fish, and Gravel. On cloud-labeling days at two institutes, 67 scientists screened 10,000 satellite images on a crowdsourcing platform and classified almost 50,000 mesoscale cloud clusters. This dataset is then used as a training dataset for deep learning algorithms that make it possible to automate the pattern detection and create global climatologies of the four patterns. Analysis of the geographical distribution and large-scale environmental conditions indicates that the four patterns have some overlap with established modes of organization, such as open and closed cellular convection, but also differ in important ways. The results and dataset from this project suggest promising research questions. Further, this study illustrates that crowdsourcing and deep learning complement each other well for the exploration of image datasets.

Corresponding author: Stephan Rasp, stephan.rasp@tum.de

Abstract

Humans excel at detecting interesting patterns in images, for example, those taken from satellites. This kind of anecdotal evidence can lead to the discovery of new phenomena. However, it is often difficult to gather enough data of subjective features for significant analysis. This paper presents an example of how two tools that have recently become accessible to a wide range of researchers, crowdsourcing and deep learning, can be combined to explore satellite imagery at scale. In particular, the focus is on the organization of shallow cumulus convection in the trade wind regions. Shallow clouds play a large role in the Earth’s radiation balance yet are poorly represented in climate models. For this project four subjective patterns of organization were defined: Sugar, Flower, Fish, and Gravel. On cloud-labeling days at two institutes, 67 scientists screened 10,000 satellite images on a crowdsourcing platform and classified almost 50,000 mesoscale cloud clusters. This dataset is then used as a training dataset for deep learning algorithms that make it possible to automate the pattern detection and create global climatologies of the four patterns. Analysis of the geographical distribution and large-scale environmental conditions indicates that the four patterns have some overlap with established modes of organization, such as open and closed cellular convection, but also differ in important ways. The results and dataset from this project suggest promising research questions. Further, this study illustrates that crowdsourcing and deep learning complement each other well for the exploration of image datasets.

Corresponding author: Stephan Rasp, stephan.rasp@tum.de
Save