Articles | Volume 21, issue 12
Atmos. Chem. Phys., 21, 9719–9739, 2021
https://doi.org/10.5194/acp-21-9719-2021
Atmos. Chem. Phys., 21, 9719–9739, 2021
https://doi.org/10.5194/acp-21-9719-2021

Research article 29 Jun 2021

Research article | 29 Jun 2021

Disparities in particulate matter (PM10) origins and oxidative potential at a city scale (Grenoble, France) – Part 2: Sources of PM10 oxidative potential using multiple linear regression analysis and the predictive applicability of multilayer perceptron neural network analysis

Lucille Joanna S. Borlaza 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 acp-2021-57', Anonymous Referee #1, 10 Apr 2021
  • RC2: 'Comment on acp-2021-57', Anonymous Referee #2, 15 Apr 2021
  • AC1: 'Comment on acp-2021-57', Lucille Joanna Borlaza, 26 Apr 2021

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Lucille Joanna Borlaza on behalf of the Authors (26 Apr 2021)  Author's response    Author's tracked changes    Manuscript
ED: Referee Nomination & Report Request started (27 Apr 2021) by James Allan
RR by Anonymous Referee #1 (07 May 2021)
RR by Anonymous Referee #2 (18 May 2021)
ED: Publish subject to minor revisions (review by editor) (18 May 2021) by James Allan
AR by Lucille Joanna Borlaza on behalf of the Authors (27 May 2021)  Author's response    Author's tracked changes    Manuscript
ED: Publish as is (27 May 2021) by James Allan
Short summary
With an enhanced source apportionment obtained in a companion paper, this paper acquires more understanding of the spatiotemporal associations of the sources of PM to oxidative potential (OP), an emerging health-based metric. Multilayer perceptron neural network analysis was used to apportion OP from PM sources. Results showed that such a methodology is as robust as the linear classical inversion and permits an improvement in the OP prediction when local features or non-linear effects occur.
Altmetrics
Final-revised paper
Preprint