Accessibility navigation

Machine learning emulation of 3D cloud radiative effects

Meyer, D. ORCID:, Hogan, R. J. ORCID:, Dueben, P. D. ORCID: and Mason, S. L. ORCID: (2022) Machine learning emulation of 3D cloud radiative effects. Journal of Advances in Modeling Earth Systems, 14 (3). ISSN 1942-2466

Text (Open Access) - Published Version
· Available under License Creative Commons Attribution.
· Please see our End User Agreement before downloading.


It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1029/2021ms002550


Abstract: The treatment of cloud structure in numerical weather and climate models is often greatly simplified to make them computationally affordable. Here we propose to correct the European Centre for Medium‐Range Weather Forecasts 1D radiation scheme ecRad for 3D cloud effects using computationally cheap neural networks. 3D cloud effects are learned as the difference between ecRad's fast 1D Tripleclouds solver that neglects them and its 3D SPARTACUS (SPeedy Algorithm for Radiative TrAnsfer through CloUd Sides) solver that includes them but is about five times more computationally expensive. With typical errors between 20% and 30% of the 3D signal, neural networks improve Tripleclouds' accuracy for about 1% increase in runtime. Thus, rather than emulating the whole of SPARTACUS, we keep Tripleclouds unchanged for cloud‐free parts of the atmosphere and 3D‐correct it elsewhere. The focus on the comparably small 3D correction instead of the entire signal allows us to improve predictions significantly if we assume a similar signal‐to‐noise ratio for both.

Item Type:Article
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Meteorology
ID Code:103996
Uncontrolled Keywords:Machine learning application to Earth system modeling, ATMOSPHERIC COMPOSITION AND STRUCTURE, Air/sea constituent fluxes, Volcanic effects, BIOGEOSCIENCES, Climate dynamics, Modeling, COMPUTATIONAL GEOPHYSICS, Neural networks, fuzzy logic, machine learning, Numerical solutions, CRYOSPHERE, Avalanches, Mass balance, GEODESY AND GRAVITY, Ocean monitoring with geodetic techniques, Ocean/Earth/atmosphere/hydrosphere/cryosphere interactions, Global change from geodesy, GLOBAL CHANGE, Earth system modeling, Abrupt/rapid climate change, Climate variability, Global climate models, Impacts of global change, Land/atmosphere interactions, Oceans, Regional climate change, Sea level change, Solid Earth, Water cycles, HYDROLOGY, Climate impacts, Hydrological cycles and budgets, INFORMATICS, Machine learning, MARINE GEOLOGY AND GEOPHYSICS, Gravity and isostasy, ATMOSPHERIC PROCESSES, Clouds and aerosols, Radiative processes, Climate change and variability, Climatology, General circulation, Ocean/atmosphere interactions, Regional modeling, Theoretical modeling, OCEANOGRAPHY: GENERAL, Climate and interannual variability, Numerical modeling, NATURAL HAZARDS, Atmospheric, Geological, Oceanic, Physical modeling, Climate impact, Risk, Disaster risk analysis and assessment, OCEANOGRAPHY: PHYSICAL, Air/sea interactions, Decadal ocean variability, Ocean influence of Earth rotation, Sea level: variations and mean, Surface waves and tides, Tsunamis and storm surges, PALEOCEANOGRAPHY, POLICY SCIENCES, Benefit‐cost analysis, RADIO SCIENCE, Radio oceanography, SEISMOLOGY, Earthquake ground motions and engineering seismology, Volcano seismology, VOLCANOLOGY, Volcano/climate interactions, Atmospheric effects, Volcano monitoring, Effusive volcanism, Mud volcanism, Explosive volcanism, Volcanic hazards and risks, Research Article, Machine Learning, Neural Network, Radiation, Earth System Modeling, Tripleclouds, SPARTACUS
Publisher:American Geophysical Union


Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation