Articles | Volume 15, issue 4
https://doi.org/10.5194/gmd-15-1677-2022
https://doi.org/10.5194/gmd-15-1677-2022
Development and technical paper
 | 
25 Feb 2022
Development and technical paper |  | 25 Feb 2022

A machine-learning-guided adaptive algorithm to reduce the computational cost of integrating kinetics in global atmospheric chemistry models: application to GEOS-Chem versions 12.0.0 and 12.9.1

Lu Shen, Daniel J. Jacob, Mauricio Santillana, Kelvin Bates, Jiawei Zhuang, and Wei Chen

Download

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2020-425', Mathew Evans, 11 May 2021
  • RC2: 'Comment on gmd-2020-425', Anonymous Referee #2, 21 May 2021

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Lu Shen on behalf of the Authors (23 Aug 2021)  Author's response    Author's tracked changes    Manuscript
ED: Publish subject to technical corrections (26 Sep 2021) by Sergey Gromov
ED: Reconsider after major revisions (18 Nov 2021) by Sergey Gromov
AR by Lu Shen on behalf of the Authors (24 Dec 2021)  Author's response    Author's tracked changes    Manuscript
ED: Reconsider after major revisions (09 Jan 2022) by Sergey Gromov
AR by Polina Shvedko on behalf of the Authors (20 Jan 2022)  Author's response
ED: Publish subject to minor revisions (review by editor) (29 Jan 2022) by Sergey Gromov
AR by Lu Shen on behalf of the Authors (01 Feb 2022)  Author's response    Author's tracked changes    Manuscript
ED: Publish subject to technical corrections (03 Feb 2022) by Sergey Gromov
AR by Lu Shen on behalf of the Authors (03 Feb 2022)  Author's response    Manuscript
Short summary
The high computational cost of chemical integration is a long-standing limitation in global atmospheric chemistry models. Here we present an adaptive and efficient algorithm that can reduce the computational time of atmospheric chemistry by 50 % and maintain the error below 2 % for important species, inspired by machine learning clustering techniques and traditional asymptotic analysis ideas.