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

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/cm3, 12.0 µm2/cm3, and 46.1 nm. The final R2 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 R2 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/cm3, 0.48 µm2/cm3, 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 R2 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.

Short-term exposure to ultrafine particles and mortality and hospital admissions due to respiratory and cardiovascular diseases in Copenhagen, Denmark.

Ultrafine particles (UFP; particulate matter <0.1 µm in diameter) may be more harmful to human health than larger particles, but epidemiological evidence on their health effects is still limited. In this study, we examined the association between short-term exposure to UFP and mortality and hospital admissions in Copenhagen, Denmark. Daily concentrations of UFP (measured as particle number concentration in a size range 11-700 nm) and meteorological variables were monitored at an urban background station in central Copenhagen during 2002-2018. Daily counts of deaths from all non-accidental causes, as well as deaths and hospital admissions from cardiovascular and respiratory diseases were obtained from Danish registers. Mortality and hospital admissions associated with an interquartile range (IQR) increase in UFP exposure on a concurrent day and up to six preceding days prior to the death or admission were examined in a case-crossover study design. Odds ratios (OR) with 95% confidence intervals (CI) per one IQR increase in UFP were estimated after adjusting for temperature and relative humidity. We observed 140,079 deaths in total, 236,003 respiratory and 342,074 cardiovascular hospital admissions between 2002 and 2018. Hospital admissions due to respiratory and cardiovascular diseases were significantly positively associated with one IQR increase in UFP (OR: 1.04 [95% CI: 1.01, 1.07], lag 0-4, and 1.02 [1.00, 1.04], lag 0-1, respectively). Among the specific causes, the strongest associations were found for chronic obstructive pulmonary disease (COPD) mortality and asthma hospital admissions and two-day means (lag 0-1) of UFP (OR: 1.13 [1.01, 1.26] and 1.08 [1.00, 1.16], respectively, per one IQR increase in UFP). Based on 17 years of UFP monitoring data, we present novel findings showing that short-term exposure to UFP can trigger respiratory and cardiovascular diseases mortality and morbidity in Copenhagen, Denmark. The strongest associations with UFP were observed with COPD mortality and asthma hospital admissions.