Harnessing AI to unmask Copenhagen's invisible air pollutants: A study on three ultrafine particle metrics

Heresh Amini, Marie L Bergmann, Seyed Mahmood Taghavi Shahri, Shali Tayebi, Thomas Cole-Hunter, Jules Kerckhoffs, Jibran Khan, Kees Meliefste, Youn-Hee Lim, Laust H Mortensen, Ole Hertel, Rasmus Reeh, Christian Gaarde Nielsen, Steffen Loft, Roel Vermeulen, Zorana J Andersen, Joel Schwartz

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

14 Downloads (Pure)

Abstract

Ultrafine particles (UFPs) are airborne particles with a diameter of less than 100 nm. They are emitted from various sources, such as traffic, combustion, and industrial processes, and can have adverse effects on human health. Long-term mean ambient average particle size (APS) in the UFP range varies over space within cities, with locations near UFP sources having typically smaller APS. Spatial models for lung deposited surface area (LDSA) within urban areas are limited and currently there is no model for APS in any European city. We collected particle number concentration (PNC), LDSA, and APS data over one-year monitoring campaign from May 2021 to May 2022 across 27 locations and estimated annual mean in Copenhagen, Denmark, and obtained additionally annual mean PNC data from 6 state-owned continuous monitors. We developed 94 predictor variables, and machine learning models (random forest and bagged tree) were developed for PNC, LDSA, and APS. The annual mean PNC, LDSA, and APS were, respectively, 5523 pt/cm 3, 12.0 μm 2/cm 3, and 46.1 nm. The final R 2 values by random forest (RF) model were 0.93 for PNC, 0.88 for LDSA, and 0.85 for APS. The 10-fold, repeated 10-times cross-validation R 2 values were 0.65, 0.67, and 0.60 for PNC, LDSA, and APS, respectively. The root mean square error for final RF models were 296 pt/cm 3, 0.48 μm 2/cm 3, and 1.60 nm for PNC, LDSA, and APS, respectively. Traffic-related variables, such as length of major roads within buffers 100-150 m and distance to streets with various speed limits were amongst the highly-ranked predictors for our models. Overall, our ML models achieved high R 2 values and low errors, providing insights into UFP exposure in a European city where average PNC is quite low. These hyperlocal predictions can be used to study health effects of UFPs in the Danish Capital.

OriginalsprogEngelsk
Artikelnummer123664
TidsskriftEnvironmental Pollution
Vol/bind346
Antal sider11
ISSN0269-7491
DOI
StatusUdgivet - 2024

Bibliografisk note

Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.

Citationsformater