Preprints
https://doi.org/10.5194/egusphere-2025-1376
https://doi.org/10.5194/egusphere-2025-1376
20 May 2025
 | 20 May 2025

Rethinking Machine Learning Weather Normalisation: A Refined Strategy for Short-term Air Pollution Policies

Yuqing Dai, Bowen Liu, Chengxu Tong, David Carslaw, Robert MacKenzie, and Zongbo Shi

Abstract. Air pollution causes millions of premature deaths annually, driving widespread implementation of clean air interventions. Quantitative evaluation of the efficacy of such interventions is critical in air quality management. Machine learning-based weather normalization (ML-WN) has been employed to isolate meteorological influences from emission-drive changes; however, it has its own limitations, particularly when abrupt emission shifts occur, e.g., after an intervention. Here we developed a logical evaluation framework, based on paired observational datasets and a test of ‘ML algebra’ (i.e., the ‘commutation’ of a normalisation step), to show that ML-WN significantly underestimates the immediate effects of short-term interventions on NOX, with discrepancies reaching up to 42 % for one-week interventions. This finding challenges assumptions about the robustness of ML-WN for evaluating short-term policies, such as emergency traffic controls or episodic pollution events. We propose a refined approach (MacLeWN) that explicitly accounts for intervention timing, reducing underestimation biases by >90 % in idealised but plausible cases studies. We applied both approaches to evaluate the impact of COVID-19 lockdown on NOX as measured at Marylebone Road, London. For the one-week period after the lockdown, ML-WN estimates approximately 17 % smaller NOX reductions compared to MacLeWN, and such underestimation diminishes as policy duration extends, decreasing to ~10 % for one-month and becoming insignificant after three months. Our findings indicate the importance of carefully selecting evaluation methodologies for air quality interventions, suggesting that ML-WN should be complemented or adjusted when assessing short-term policies. Increasing model interpretability is also crucial for generating trustworthy assessments and improving policy evaluations.

Competing interests: At least one of the (co-)authors is a member of the editorial board of Atmospheric Chemistry and Physics.

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
Yuqing Dai, Bowen Liu, Chengxu Tong, David Carslaw, Robert MacKenzie, and Zongbo Shi

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-1376', Anonymous Referee #1, 07 Jul 2025
    • AC1: 'Reply on RC1', Yuqing Dai, 23 Jul 2025
  • RC2: 'Comment on egusphere-2025-1376', Anonymous Referee #2, 12 Jul 2025
    • AC2: 'Reply on RC2', Yuqing Dai, 23 Jul 2025
Yuqing Dai, Bowen Liu, Chengxu Tong, David Carslaw, Robert MacKenzie, and Zongbo Shi
Yuqing Dai, Bowen Liu, Chengxu Tong, David Carslaw, Robert MacKenzie, and Zongbo Shi

Viewed

Total article views: 521 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
449 56 16 521 22 9 17
  • HTML: 449
  • PDF: 56
  • XML: 16
  • Total: 521
  • Supplement: 22
  • BibTeX: 9
  • EndNote: 17
Views and downloads (calculated since 20 May 2025)
Cumulative views and downloads (calculated since 20 May 2025)

Viewed (geographical distribution)

Total article views: 510 (including HTML, PDF, and XML) Thereof 510 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Sep 2025
Download
Short summary
Air pollution causes millions of deaths annually, driving policies to improve air quality. However, assessing these policies is challenging because weather changes can hide their true impact. We created a logical evaluation framework and found that a widely applied machine learning approach that adjusts for weather effects could underestimate the effectiveness of short-term policies, like emergency traffic controls. We proposed a refined approach that could largely reduce such underestimation.
Share