Articles | Volume 15, issue 10
Geosci. Model Dev., 15, 4225–4237, 2022
https://doi.org/10.5194/gmd-15-4225-2022
Geosci. Model Dev., 15, 4225–4237, 2022
https://doi.org/10.5194/gmd-15-4225-2022
Model evaluation paper
01 Jun 2022
Model evaluation paper | 01 Jun 2022

A comparative analysis for a deep learning model (hyDL-CO v1.0) and Kalman filter to predict CO concentrations in China

Weichao Han et al.

Download

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on gmd-2021-420', Anonymous Referee #1, 28 Feb 2022
    • AC1: 'Reply on RC1', Zhe Jiang, 18 Apr 2022
  • RC2: 'Comment on gmd-2021-420', Anonymous Referee #2, 06 Apr 2022
    • AC2: 'Reply on RC2', Zhe Jiang, 18 Apr 2022

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Zhe Jiang on behalf of the Authors (19 Apr 2022)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (11 May 2022) by Volker Grewe

Post-review adjustments

AA: Author's adjustment | EA: Editor approval
AA by Zhe Jiang on behalf of the Authors (31 May 2022)   Author's adjustment   Manuscript
EA: Adjustments approved (31 May 2022) by Volker Grewe
Download
Short summary
We present an application of a hybrid deep learning (DL) model on prediction of surface CO in China from 2015 to 2020, which utilizes both convolutional neural networks and long short-term memory neural networks. The DL model performance is better than a Kalman filter (KF) system in the training period (2005–2018). Furthermore, the DL model demonstrates good temporal extensibility: the mean bias and correlation coefficients are 95.7 ppb and 0.93 in the test period (2019–2020) over eastern China.