Peter Kuma Software and Science

Machine learning of cloud types shows higher climate sensitivity is associated with lower cloud biases

Peter Kuma1, Frida A.-M. Bender1, Alex Schuddeboom2, Adrian J. McDonald2, Øyvind Seland3

1Department of Meteorology (MISU), Stockholm University, Stockholm, Sweden
2University of Canterbury, Christchurch, Aotearoa New Zealand
3Norwegian Meteorological Institute, Oslo, Norway

Abstract

Uncertainty in cloud feedback in climate models is a major limitation in projections of future climate. Therefore, to ensure the accuracy of climate models, evaluation and improvement of cloud simulation is essential. We analyse cloud biases and cloud change with respect to global mean near-surface temperature (GMST) in climate models relative to satellite observations, and relate them to equilibrium climate sensitivity, transient climate response and cloud feedback. For this purpose, we develop a supervised deep convolutional artificial neural network for determination of cloud types from low-resolution (approx. 1°×1°) daily mean top of atmosphere shortwave and longwave radiation fields, corresponding to the World Meteorological Organization (WMO) cloud genera recorded by human observers in the Global Telecommunication System. We train this network on a satellite top of atmosphere radiation observed by the Clouds and the Earth’s Radiant Energy System (CERES), and apply it on the Climate Model Intercomparison Project phase 5 and 6 (CMIP5 and CMIP6) historical and abrupt-4xCO2 experiment model output and the ECMWF Reanalysis version 5 (ERA5) and the Modern-Era Retrospective Analysis for Research and Applications version 2 (MERRA-2) reanalyses. We compare these with satellite observations, link biases in cloud type occurrence derived from the neural network to change with respect to GMST to climate sensitivity, and compare our cloud types with an existing cloud regime classification based on the Moderate Resolution Imaging Spectroradiometer (MODIS) and International Satellite Cloud Climatology Project (ISCCP) satellite data. We show that there is a significant negative linear relationship between the root mean square error of cloud type occurrence derived from the neural network and model equilibrium climate sensitivity and transient climate response (Bayes factor 22 and 17, respectively). This indicates that models with a better representation of the cloud types globally have higher climate sensitivity. Factoring in results from other studies, there are two possible explanations: either high climate sensitivity models are plausible, contrary to combined assessments of climate sensitivity by previous review studies, or the accuracy of representation of present-day clouds in models is negatively correlated with the accuracy of representation of future projected clouds.
Note:
in review in Atmospheric Chemistry and Physics
Journal:
Atmospheric Chemistry and Physics Discussions
Archive:
Zenodo
DOI:
10.5194/acp-2022-184
Submitted:
07 March 2022
PDF:
PDF document
BibTeX: @article{kuma2022,
  journal={Atmospheric Chemistry and Physics Discussions},
  note={in review in Atmospheric Chemistry and Physics},
  doi={10.5194/acp-2022-184},
  url={https://doi.org/10.5194/acp-2022-184},
  author={Kuma, Peter and Bender, Frida A.-M. and Schuddeboom, Alex and McDonald, Adrian J. and Seland, Øyvind},
  title={Machine learning of cloud types shows higher climate sensitivity is associated with lower cloud biases}
}