Related Experiment Video
Updated: Sep 20, 2025

Setup of Consumer Wearable Devices for Exposure and Health Monitoring in Population Studies
Published on: February 3, 2023
Machine Learning and Meteorological Normalization for Assessment of Particulate Matter Changes during the COVID-19
Mario Lovrić1,2, Mario Antunović3, Iva Šunić2
1Know-Center, Inffeldgasse 13, 8010 Graz, Austria.
The COVID-19 lockdown in Zagreb did not significantly alter long-term particulate matter (PM) levels. Air quality monitoring showed no substantial changes in PM2.5 and PM10 concentrations during the lockdown or the subsequent "new normal" period.
Area of Science:
- Environmental Science
- Atmospheric Chemistry
- Public Health
Background:
- Particulate matter (PM) concentrations are influenced by various factors, including human activity and meteorological conditions.
- The Coronavirus Disease 2019 (COVID-19) pandemic led to unprecedented reductions in global mobility and industrial activity.
- Understanding the impact of these changes on air quality, specifically PM mass concentrations, is crucial for environmental and health assessments.
Purpose of the Study:
- To investigate the changes in mass concentrations of PM1, PM2.5, and PM10 during the COVID-19 lockdown in Zagreb, Croatia.
- To assess the long-term impact of reduced mobility on urban air quality.
- To differentiate between lockdown effects and the subsequent 'new normal' period.
Main Methods:
- Daily PM1, PM2.5, and PM10 samples were collected at an urban background site in Zagreb from 2009 to late 2020.
- Random Forest (RF) and LightGBM (LGB) models, optimized by Bayesian tuning, were used for meteorological normalization of mass concentrations.
- De-weathering was performed using repeated random resampling, excluding the trend variable, followed by Analysis of Variance (ANOVA) for evaluation.
Main Results:
- No significant differences were observed in PM1, PM2.5, and PM10 concentrations in April 2020 (lockdown) compared to the same periods in 2018 and 2019.
- Similarly, no significant changes were detected during the 'new normal' period (June and July 2020).
- Meteorological normalization models (RF and LGB) effectively adjusted for weather variations, allowing for trend analysis.
Conclusions:
- Reduced mobility during the COVID-19 lockdown in Zagreb did not lead to a significant long-term alteration in particulate matter concentrations.
- The study highlights the complex relationship between mobility, meteorological factors, and urban air quality.
- Further research is needed to understand the specific contributions of different emission sources to PM levels in urban environments.
More Related Videos
09:33Visualizing Field Data Collection Procedures of Exposure and Biomarker Assessments for the Household Air Pollution Intervention Network Trial in India
Published on: December 23, 2022
05:45Composition and Distribution Analysis of Bioaerosols Under Different Environmental Conditions
Published on: January 7, 2019
Related Concept Videos
Precipitation and Co-precipitation
Global Climate Change
Precipitation Processes
What is Weather?
Measurement of Air Content in Concrete
The pressure method,...
Variation of Atmospheric Pressure
Assuming the air temperature is constant at a given altitude and that the ideal gas law of thermodynamics describes the atmosphere to a good approximation, one can find the variation of atmospheric pressure with height.
Let p(y) be the atmospheric pressure at...