Improving Low‐Cloud Fraction Prediction Through Machine Learning

Zhang, Haipeng; Zheng, Youtong; Li, Zhanqing

doi:10.1029/2024GL109735

Title: Improving Low‐Cloud Fraction Prediction Through Machine Learning

Journal Article · 03 August 2024 · Geophysical Research Letters

DOI: https://doi.org/10.1029/2024GL109735 · OSTI ID:2429055

^[1];

^[2];

^[1]

Department of Atmospheric and Oceanic Science University of Maryland College Park MD USA, Earth System Science Interdisciplinary Center University of Maryland College Park MD USA
Department of Earth and Atmospheric Science University of Houston Houston TX USA, Institute of Climate and Atmospheric Science University of Houston Houston TX USA

Abstract In this study, we evaluated the performance of machine learning (ML) models (XGBoost) in predicting low‐cloud fraction (LCF), compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. ML models show a substantial enhancement in predicting LCF regarding root mean squared errors and correlation coefficients. The good performance is consistent across the full spectrums of atmospheric stability and large‐scale vertical velocity. Employing an explainable ML approach, we revealed the importance of including the amount of available moisture in ML models for representing spatiotemporal variations in LCF in the midlatitudes. Also, ML models demonstrated marked improvement in capturing the LCF variations during the stratocumulus‐to‐cumulus transition (SCT). This study suggests ML models' great potential to address the longstanding issues of “too few” low clouds and “too rapid” SCT in global climate models.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE

Grant/Contract Number:: SC0022919; SC0024185

OSTI ID:: 2429055

Journal Information:: Geophysical Research Letters, Journal Name: Geophysical Research Letters Journal Issue: 15 Vol. 51; ISSN 0094-8276

Publisher:: American Geophysical Union (AGU)Copyright Statement

Country of Publication:: United States

Language:: English

References (37)

CGILS: Results from the first phase of an international project to understand the physical mechanisms of low cloud feedbacks in single column models: CGILS Results On Low Cloud Feedback Zhang, Minghua; Bretherton, Christopher S.; Blossey, Peter N. Journal of Advances in Modeling Earth Systems, Vol. 5, Issue 4 https://doi.org/10.1002/2013MS000246	journal	December 2013
Low cloud reduction in a greenhouse-warmed climate: Results from Lagrangian LES of a subtropical marine cloudiness transition: LAGRANGIAN BOUNDARY-LAYER CLOUD FEEDBACK Bretherton, Christopher S.; Blossey, Peter N. Journal of Advances in Modeling Earth Systems, Vol. 6, Issue 1 https://doi.org/10.1002/2013MS000250	journal	February 2014
Positive tropical marine low‐cloud cover feedback inferred from cloud‐controlling factors Qu, Xin; Hall, Alex; Klein, Stephen A. Geophysical Research Letters, Vol. 42, Issue 18 https://doi.org/10.1002/2015GL065627	journal	September 2015
The GFDL Global Atmosphere and Land Model AM4.0/LM4.0: 1. Simulation Characteristics With Prescribed SSTs Zhao, M.; Golaz, J. -C.; Held, I. M. Journal of Advances in Modeling Earth Systems, Vol. 10, Issue 3 https://doi.org/10.1002/2017MS001208	journal	March 2018
Mechanisms of marine low cloud sensitivity to idealized climate perturbations: A single-LES exploration extending the CGILS cases: LES OF BOUNDARY-LAYER CLOUD FEEDBACK Bretherton, Christopher S.; Blossey, Peter N.; Jones, Christopher R. Journal of Advances in Modeling Earth Systems, Vol. 5, Issue 2 https://doi.org/10.1002/jame.20019	journal	May 2013
Cloud feedback mechanisms and their representation in global climate models: Cloud feedback mechanisms and their representation in GCMs Ceppi, Paulo; Brient, Florent; Zelinka, Mark D. Wiley Interdisciplinary Reviews: Climate Change, Vol. 8, Issue 4 https://doi.org/10.1002/wcc.465	journal	May 2017
History of climate modeling: History of climate modeling Edwards, Paul N. Wiley Interdisciplinary Reviews: Climate Change, Vol. 2, Issue 1 https://doi.org/10.1002/wcc.95	journal	December 2010
Clouds in Shallow Layers at Low, Middle, and High Levels Houze, Jr., Robert A. International Geophysics https://doi.org/10.1016/B978-0-12-374266-7.00005-6	book	July 2014
Long-term change in low-cloud cover in Southeast China during cold seasons Chen, Zhe; Wang, Minghuai; Zhang, Haipeng Atmospheric and Oceanic Science Letters, Vol. 15, Issue 6 https://doi.org/10.1016/j.aosl.2022.100222	journal	November 2022
Application of XGBoost algorithm in the optimization of pollutant concentration Li, Jiangtao; An, Xingqin; Li, Qingyong Atmospheric Research, Vol. 276 https://doi.org/10.1016/j.atmosres.2022.106238	journal	October 2022
A GCSS Boundary-Layer Cloud Model Intercomparison Study Of The First Astex Lagrangian Experiment Bretherton, Christopher S.; Krueger, Steven K.; Wyant, Matthew C. Boundary-Layer Meteorology, Vol. 93, Issue 3 https://doi.org/10.1023/a:1002005429969	journal	December 1999
Marine boundary layer clouds at the heart of tropical cloud feedback uncertainties in climate models Bony, Sandrine Geophysical Research Letters, Vol. 32, Issue 20 https://doi.org/10.1029/2005GL023851	journal	January 2005
The vertical distribution of cloud feedback in coupled ocean-atmosphere models: VERTICAL DISTRIBUTION OF CLOUD FEEDBACK Soden, Brian J.; Vecchi, Gabriel A. Geophysical Research Letters, Vol. 38, Issue 12 https://doi.org/10.1029/2011GL047632	journal	June 2011
The ‘too few, too bright’ tropical low-cloud problem in CMIP5 models: TOO FEW TOO BRIGHT LOW-CLOUDS Nam, C.; Bony, S.; Dufresne, J. -L. Geophysical Research Letters, Vol. 39, Issue 21 https://doi.org/10.1029/2012GL053421	journal	November 2012
Low‐Cloud Feedback in CAM5‐CLUBB: Physical Mechanisms and Parameter Sensitivity Analysis Zhang, Haipeng; Wang, Minghuai; Guo, Zhun Journal of Advances in Modeling Earth Systems, Vol. 10, Issue 11 https://doi.org/10.1029/2018MS001423	journal	November 2018
Assessment of CMIP6 Cloud Fraction and Comparison with Satellite Observations Vignesh, P. Preetham; Jiang, Jonathan H.; Kishore, P. Earth and Space Science, Vol. 7, Issue 2 https://doi.org/10.1029/2019EA000975	journal	February 2020
First Application of Artificial Neural Networks to Estimate 21st Century Greenland Ice Sheet Surface Melt Sellevold, Raymond; Vizcaino, Miren Geophysical Research Letters, Vol. 48, Issue 16 https://doi.org/10.1029/2021GL092449	journal	August 2021
The Southern Ocean Radiative Bias, Cloud Compensating Errors, and Equilibrium Climate Sensitivity in CMIP6 Models Schuddeboom, A. J.; McDonald, A. J. Journal of Geophysical Research: Atmospheres, Vol. 126, Issue 22 https://doi.org/10.1029/2021JD035310	journal	November 2021
Evaluation of Simulated Cloud Diurnal Variation in CMIP6 Climate Models Chen, Guoxing; Wang, Wei‐Chyung; Bao, Qing Journal of Geophysical Research: Atmospheres, Vol. 127, Issue 6 https://doi.org/10.1029/2021JD036422	journal	March 2022
Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles Chen, Yao‐Sheng; Yamaguchi, Takanobu; Bogenschutz, Peter A. Journal of Advances in Modeling Earth Systems, Vol. 13, Issue 11 https://doi.org/10.1029/2021MS002625	journal	November 2021
Improving Seasonal Forecast Using Probabilistic Deep Learning Pan, Baoxiang; Anderson, Gemma J.; Goncalves, André Journal of Advances in Modeling Earth Systems, Vol. 14, Issue 3 https://doi.org/10.1029/2021MS002766	journal	March 2022
Surface‐Atmosphere Decoupling Prolongs Cloud Lifetime Under Warm Advection Due To Reduced Entrainment Drying Zhang, Haipeng; Zheng, Youtong; Lee, Seoung Soo Geophysical Research Letters, Vol. 50, Issue 10 https://doi.org/10.1029/2022GL101663	journal	May 2023
An Updated CLUBB PDF Closure Scheme to Improve Low Cloud Simulation in CAM6 Li, Te; Wang, Minghuai; Guo, Zhun Journal of Advances in Modeling Earth Systems, Vol. 14, Issue 12 https://doi.org/10.1029/2022MS003127	journal	December 2022
Evaluation of Stratocumulus Evolution Under Contrasting Temperature Advections in CESM2 Through a Lagrangian Framework Zhang, Haipeng; Zheng, Youtong; Li, Zhanqing Geophysical Research Letters, Vol. 51, Issue 4 https://doi.org/10.1029/2023GL106856	journal	February 2024
Insights into low-latitude cloud feedbacks from high-resolution models Bretherton, Christopher S. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 373, Issue 2054 https://doi.org/10.1098/rsta.2014.0415	journal	November 2015
XGBoost: A Scalable Tree Boosting System Chen, Tianqi; Guestrin, Carlos Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939785	conference	January 2016
The Atlantic Stratocumulus Transition Experiment—ASTEX Albrecht, Bruce A.; Bretherton, Christopher S.; Johnson, Doug Bulletin of the American Meteorological Society, Vol. 76, Issue 6 https://doi.org/10.1175/1520‐0477(1995)076<0889:TASTE>2.0.CO;2	journal	June 1995
COSP: Satellite simulation software for model assessment Bodas-Salcedo, A.; Webb, M. J.; Bony, S. Bulletin of the American Meteorological Society, Vol. 92, Issue 8 https://doi.org/10.1175/2011BAMS2856.1	journal	August 2011
On the Factors Modulating the Stratocumulus to Cumulus Transitions Sandu, Irina; Stevens, Bjorn Journal of the Atmospheric Sciences, Vol. 68, Issue 9 https://doi.org/10.1175/2011JAS3614.1	journal	September 2011
The Dynamical Core, Physical Parameterizations, and Basic Simulation Characteristics of the Atmospheric Component AM3 of the GFDL Global Coupled Model CM3 Donner, Leo J.; Wyman, Bruce L.; Hemler, Richard S. Journal of Climate, Vol. 24, Issue 13 https://doi.org/10.1175/2011JCLI3955.1	journal	July 2011
The Community Earth System Model: A Framework for Collaborative Research Hurrell, James W.; Holland, M. M.; Gent, P. R. Bulletin of the American Meteorological Society, Vol. 94, Issue 9 https://doi.org/10.1175/BAMS‐D‐12‐00121.1	journal	September 2013
On the Relationship between Stratiform Low Cloud Cover and Lower-Tropospheric Stability Wood, Robert; Bretherton, Christopher S. Journal of Climate, Vol. 19, Issue 24 https://doi.org/10.1175/JCLI3988.1	journal	December 2006
Using Probability Density Functions to Derive Consistent Closure Relationships among Higher-Order Moments Larson, Vincent E.; Golaz, Jean-Christophe Monthly Weather Review, Vol. 133, Issue 4 https://doi.org/10.1175/MWR2902.1	journal	April 2005
PDF Parameterization of Boundary Layer Clouds in Models with Horizontal Grid Spacings from 2 to 16 km Larson, Vincent E.; Schanen, David P.; Wang, Minghuai Monthly Weather Review, Vol. 140, Issue 1 https://doi.org/10.1175/MWR‐D‐10‐05059.1	journal	January 2012
Stratocumulus Clouds Wood, Robert Monthly Weather Review, Vol. 140, Issue 8 https://doi.org/10.1175/MWR‐D‐11‐00121.1	journal	August 2012
ERA5 hourly data on pressure levels from 1940 to present Hersbach, H.; Bell, B.; Berrisford, P. Copernicus Climate Change Service https://doi.org/10.24381/cds.bd0915c6	dataset	January 2023
Practical Bayesian Optimization of Machine Learning Algorithms Snoek, Jasper; Larochelle, Hugo; Adams, Ryan P. arXiv https://doi.org/10.48550/ARXIV.1206.2944	preprint	January 2012

Similar Records

Model Evaluation and Intercomparison of Marine Warm Low Cloud Fractions With Neural Network Ensembles

Journal Article · 2021 · Journal of Advances in Modeling Earth Systems · OSTI ID:1832282

Chen, Yao‐Sheng; Yamaguchi, Takanobu; Bogenschutz, Peter A.; +1 more

Cloud, Aerosol, and Boundary Layer Structure across the Northeast Pacific Stratocumulus–Cumulus Transition as Observed during CSET

Journal Article · 2019 · Monthly Weather Review · OSTI ID:1512838

Bretherton, Christopher S.; McCoy, Isabel L.; Mohrmann, Johannes; +6 more

The Single Column Atmosphere Model Version 6 (SCAM6): Not a Scam but a Tool for Model Evaluation and Development

Journal Article · 2019 · Journal of Advances in Modeling Earth Systems · OSTI ID:1836213

Gettelman, A.; Truesdale, J. E.; Bacmeister, J. T.; +4 more

Title: Improving Low‐Cloud Fraction Prediction Through Machine Learning

Citation Formats

References (37)

Similar Records

Related Subjects