TY - JOUR

T1 - Harnessing AI to unmask Copenhagen's invisible air pollutants

T2 - A study on three ultrafine particle metrics

AU - Amini, Heresh

AU - Bergmann, Marie L

AU - Taghavi Shahri, Seyed Mahmood

AU - Tayebi, Shali

AU - Cole-Hunter, Thomas

AU - Kerckhoffs, Jules

AU - Khan, Jibran

AU - Meliefste, Kees

AU - Lim, Youn-Hee

AU - Mortensen, Laust H

AU - Hertel, Ole

AU - Reeh, Rasmus

AU - Gaarde Nielsen, Christian

AU - Loft, Steffen

AU - Vermeulen, Roel

AU - Andersen, Zorana J

AU - Schwartz, Joel

N1 - Copyright © 2024 The Authors. Published by Elsevier Ltd.. All rights reserved.

PY - 2024

Y1 - 2024

N2 - 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.

AB - 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.

U2 - 10.1016/j.envpol.2024.123664

DO - 10.1016/j.envpol.2024.123664

M3 - Journal article

C2 - 38431246

VL - 346

JO - Environmental Pollution

JF - Environmental Pollution

SN - 0269-7491

M1 - 123664

ER -