Preprints
https://doi.org/10.5194/gmd-2021-299
https://doi.org/10.5194/gmd-2021-299

Submitted as: development and technical paper 29 Sep 2021

Submitted as: development and technical paper | 29 Sep 2021

Review status: this preprint is currently under review for the journal GMD.

Stable climate simulations using a realistic GCM with neural network parameterizations for atmospheric moist physics and radiation processes

Xin Wang1, Yilun Han2, Wei Xue1, Guangwen Yang1, and Guang J. Zhang3 Xin Wang et al.
  • 1Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China
  • 2Department of Earth System Science, Tsinghua University, Beijing, 100084, China
  • 3Scripps Institution of Oceanography, La Jolla, CA USA

Abstract. In climate models, subgrid parameterizations of convection and cloud are one of the main reasons for the biases in precipitation and atmospheric circulation simulations. In recent years, due to the rapid development of data science, Machine learning (ML) parameterizations for convection and clouds have been proven the potential to perform better than conventional parameterizations. At present, most of the existing studies are on aqua-planet and idealized models, and the problems of simulated instability and climate drift still exist. In realistic configurated models, developing a machine learning parameterization scheme remains a challenging task. In this study, a group of deep residual multilayer perceptrons with strong nonlinear fitting ability is designed to learn a parameterization scheme from cloud-resolving model outputs. Multi-target training is achieved to best balance the fits across diverse neural network outputs. The optimal machine learning parameterization, named NN-Parameterization, is further chosen among feasible candidates for both high performance and long-term simulation. The results show that NN-Parameterization performs well in multi-year climate simulations and reproduces reasonable climatology and climate variability in a general circulation model (GCM), with a running speed of about 30 times faster than the cloud-resolving model embedded Superparameterizated GCM. Under real geographical boundary conditions, the hybrid ML-physical GCM well simulates the spatial distribution of precipitation and significantly improves the frequency of precipitation extremes, which is largely underestimated in the Community Atmospheric Model version 5 (CAM5) with the horizontal resolution of 1.9° × 2.5°. Furthermore, the hybrid ML-physical GCM simulates a stronger signal of the Madden-Julian oscillation with a more reasonable propagation speed, which is too weak and propagates too fast in CAM5. This study is a pioneer to achieve multi-year stable climate simulations using a hybrid ML-physical GCM in actual land-ocean boundary conditions. It demonstrates the emerging potential for using machine learning parameterizations in climate simulations.

Xin Wang et al.

Status: open (until 24 Nov 2021)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Xin Wang et al.

Xin Wang et al.

Viewed

Total article views: 333 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
258 72 3 333 2 0
  • HTML: 258
  • PDF: 72
  • XML: 3
  • Total: 333
  • BibTeX: 2
  • EndNote: 0
Views and downloads (calculated since 29 Sep 2021)
Cumulative views and downloads (calculated since 29 Sep 2021)

Viewed (geographical distribution)

Total article views: 333 (including HTML, PDF, and XML) Thereof 333 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 22 Oct 2021
Download
Short summary
In this study, a group of deep neural networks is used to learn a parameterization scheme from a superparameterized GCM (SPCAM). After being embedded in a realistic configurated general circulation model (GCM), the parameterization scheme performs well in long-term climate simulations and reproduces reasonable climatology and climate variability. This success is the first in long-term stable climate simulations using machine learning parameterization under real geographical boundary conditions.