Submitted as: model description paper
09 Mar 2022
Submitted as: model description paper | 09 Mar 2022
Status: this preprint is currently under review for the journal GMD.

A Machine Learning Methodology for the Generation of a Parameterization of the Hydroxyl Radical: a Tool to Improve Computational-Efficiency in Chemistry Climate Models

Daniel C. Anderson1,2, Melanie B. Follette-Cook2,3, Sarah A. Strode2,3, Julie M. Nicely2,4, Junhua Liu2,3, Peter D. Ivatt2,4, and Bryan N. Duncan2 Daniel C. Anderson et al.
  • 1GESTAR II, University of Maryland Baltimore County, Baltimore, MD, USA
  • 2Atmospheric Chemistry and Dynamics Laboratory, NASA Goddard Space Flight Center, Greenbelt, MD, USA
  • 3GESTAR II, Morgan State University, Baltimore, MD, USA
  • 4Earth System Science Interdisciplinary Center, University of Maryland, College Park, MD, USA

Abstract. We present a methodology that uses gradient boosted regression trees (a machine learning technique) and a full-chemistry simulation (i.e., training dataset) from a chemistry climate model (CCM) to efficiently generate a parameterization of tropospheric hydroxyl radical (OH) that is a function of chemical, dynamical, and solar irradiance variables. This surrogate model of OH is designed to allow for computationally-efficient simulation of nonlinear feedbacks between OH and tropospheric constituents that have loss by reaction with OH as their primary sinks (e.g., carbon monoxide (CO), methane (CH4), volatile organic compounds (VOCs)). Such a model framework is advantageous for studies that require multi-decadal simulations of CH4 or multi-year sensitivity simulations to understand the causes of trends and variations of CO and CH4. The methodology that we present provides for the relatively easy creation of a new parameterization in response to, for example, changes in the underlying CCM chemistry and/or dynamics schemes. We show that a parameterization of OH generated from a CCM simulation is able to reproduce OH concentrations with a normalized root mean square error of approximately 5 %, as well as capturing the global mean methane lifetime within approximately 1 %. The accuracy of the parameterization is dependent on inputs being within the bounds of the training dataset. However, we show that the parameterization predicts large deviations in OH for an El Niño event that was not part of the training dataset, and that the spatial distribution and strength of these deviations are consistent with the event. This result gives confidence in the fidelity of the parameterization to simulate the spatial and temporal responses of OH to perturbations from large variations in the chemical, dynamical and solar irradiance drivers of OH. In addition, we discuss how two machine learning metrics, Gain feature importance and SHAP values, indicate that the behavior of the parameterization of OH generally comports with our understanding of OH chemistry, even though there are no physics- or chemistry-based constraints on the parameterization.

Daniel C. Anderson et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2022-44', Anonymous Referee #1, 20 Mar 2022
  • CEC1: 'Comment on gmd-2022-44', Juan Antonio Añel, 21 Apr 2022
    • AC1: 'Reply on CEC1', Daniel Anderson, 21 Apr 2022
      • CEC2: 'Reply on AC1', Juan Antonio Añel, 24 Apr 2022
  • RC2: 'Comment on gmd-2022-44', Anonymous Referee #2, 24 Apr 2022

Daniel C. Anderson et al.

Daniel C. Anderson et al.


Total article views: 478 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
380 81 17 478 19 6 4
  • HTML: 380
  • PDF: 81
  • XML: 17
  • Total: 478
  • Supplement: 19
  • BibTeX: 6
  • EndNote: 4
Views and downloads (calculated since 09 Mar 2022)
Cumulative views and downloads (calculated since 09 Mar 2022)

Viewed (geographical distribution)

Total article views: 381 (including HTML, PDF, and XML) Thereof 381 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 20 May 2022
Short summary
The hydroxyl radical (OH) is the most important chemical in the atmosphere for removing certain pollutants, including methane, the second most important greenhouse gas. We present a methodology to create an easily modifiable parameterization that can calculate OH concentrations in a computationally efficient way. The parameterization, which predicts OH within 5 %, can be integrated into larger climate models to allow for calculation of the interactions between OH, methane, and other chemicals.