Preprints
https://doi.org/10.5194/egusphere-2024-4056
https://doi.org/10.5194/egusphere-2024-4056
14 Feb 2025
 | 14 Feb 2025

Machine learning data fusion for high spatio-temporal resolution PM2.5

Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen

Abstract. Understanding PM2.5 variability at fine scale is crucial to assess urban pollution impact on the population and to inform the policy-making process. PM2.5 in-situ measurements at ground level cannot offer gapless spatial coverage, while current satellite retrievals generally cannot offer both high-spatial and high-temporal resolution, with night-time estimation posing further challenges. This study tackles these difficulties, introducing an innovative deep learning data fusion method to estimate hourly PM2.5 maps at 100 m resolution on urban areas. We combine low resolution geophysical model data, high resolution geographical indicators, PM2.5 in-situ ground stations measurements and PM2.5 retrieved at satellite overpass. To simultaneously treat spatial and temporal correlations in our data, we deploy a 3D U-Net based neural network model. To evaluate the model, we select the city of Paris, France, in the year 2019 as our study region and time. Quantitative assessment of the model is carried out using the ground station data with a leave-one-out cross-validation approach. Our method outperforms MERRA-2 PM2.5 estimates, predicting PM2.5 hourly (R2 = 0.51, RMSE = 6.58 μg/m3), daily (R2 = 0.65, RMSE = 4.92 μg/m3), and monthly (R2 = 0.87, RMSE = 2.87 μg/m3). The proposed approach and its possible future developments can be highly beneficial for PM2.5 exposure and regulation studies at fine suburban scale.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share

Journal article(s) based on this preprint

25 Sep 2025
Machine learning data fusion for high spatio-temporal resolution PM2.5
Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen
Atmos. Meas. Tech., 18, 4771–4789, https://doi.org/10.5194/amt-18-4771-2025,https://doi.org/10.5194/amt-18-4771-2025, 2025
Short summary
Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-4056', Anonymous Referee #1, 31 Mar 2025
    • AC1: 'Reply on RC1', Andrea Porcheddu, 23 Jun 2025
  • RC2: 'Comment on egusphere-2024-4056', Anonymous Referee #2, 26 May 2025
    • AC2: 'Reply on RC2', Andrea Porcheddu, 23 Jun 2025

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2024-4056', Anonymous Referee #1, 31 Mar 2025
    • AC1: 'Reply on RC1', Andrea Porcheddu, 23 Jun 2025
  • RC2: 'Comment on egusphere-2024-4056', Anonymous Referee #2, 26 May 2025
    • AC2: 'Reply on RC2', Andrea Porcheddu, 23 Jun 2025

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload
AR by Andrea Porcheddu on behalf of the Authors (04 Jul 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (07 Jul 2025) by Sandip Dhomse
RR by Anonymous Referee #1 (18 Jul 2025)
ED: Publish subject to minor revisions (review by editor) (18 Jul 2025) by Sandip Dhomse
AR by Andrea Porcheddu on behalf of the Authors (28 Jul 2025)  Author's response   Author's tracked changes   Manuscript 
ED: Publish as is (30 Jul 2025) by Sandip Dhomse
AR by Andrea Porcheddu on behalf of the Authors (08 Aug 2025)  Manuscript 

Journal article(s) based on this preprint

25 Sep 2025
Machine learning data fusion for high spatio-temporal resolution PM2.5
Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen
Atmos. Meas. Tech., 18, 4771–4789, https://doi.org/10.5194/amt-18-4771-2025,https://doi.org/10.5194/amt-18-4771-2025, 2025
Short summary
Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen
Andrea Porcheddu, Ville Kolehmainen, Timo Lähivaara, and Antti Lipponen

Viewed

Total article views: 881 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
780 79 22 881 20 35
  • HTML: 780
  • PDF: 79
  • XML: 22
  • Total: 881
  • BibTeX: 20
  • EndNote: 35
Views and downloads (calculated since 14 Feb 2025)
Cumulative views and downloads (calculated since 14 Feb 2025)

Viewed (geographical distribution)

Total article views: 854 (including HTML, PDF, and XML) Thereof 854 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 25 Sep 2025
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
This study proposes a novel machine learning method to estimate pollution levels (PM2.5) on urban areas at fine scale. Our model generates hourly PM2.5 maps with high spatial resolution (100 meters), by combining satellite data, ground measurements, geophysical model data, and different geographical indicators. The model properly accounts for spatial and temporal variability of the urban pollution levels, offering relevant insights for air quality monitoring and health protection.
Share