Random forest meteorological normalisation models for Swiss PM&amp;lt;sub&amp;gt;10&amp;lt;/sub&amp;gt; trend analysis

Grange, Stuart K.; Carslaw, David C.; Lewis, Alastair C.; Boleti, Eirini; Hueglin, Christoph

doi:10.5194/acp-18-6223-2018

Cited by 299 publications

(277 citation statements)

References 34 publications

Supporting

Mentioning

264

Contrasting

Order By: Relevance

“…The PD of BLH shows that the model is able to reproduce the pattern of decreasing particle concentrations with increasing BLH (Gupta & Christopher, ; Wagner & Schäfer, ).The shape of the full‐year PD of BLH shown in Figure a is similar to that provided by Grange et al () for observations in Switzerland. They found a reduction of

\sim

μ

g/m

^{3}

for daily PM10 predictions.…”

Section: Resultssupporting

confidence: 84%

“…This tendency was reduced by the choice of the least squares loss function as describes in chapter 2.5.3 but likely still continues to affect the model accuracy. The model performance is comparable to similar studies, also in its underestimation of PM (Hu et al, ; Grange et al, ; Stafoggia et al, ; Zhang et al, ). Tenfold random train/test splits were conducted, resulting in 10 models.…”

Section: Resultssupporting

confidence: 81%

“…For example, Park et al () used a RF model to predict PM10 in South Korea and found large influence of AOD, day of the year (DOY), wind speed, and solar radiation on the modeled PM concentrations. Similarly, Grange et al () obtained high feature importances for wind speed, back trajectory cluster, DOY, and air temperature, using the RF approach for PM10 measurements in Switzerland. The present study builds upon the approaches applied in these studies but provides a more in‐depth analysis of model‐inherent relationships.…”

Section: Motivation and Research Questionsmentioning

confidence: 91%

“…However, there is indication that very high BLH values (

\sim <

2,500 m) influence PM10 concentrations as well. While the former threshold marks the effects of particle accumulation within a shallow boundary layer, the latter threshold could indicate the formation of a deep boundary layer with stimulated formation of secondary aerosols as suggested by Grange et al (). If BLH is between these thresholds, its explanatory power is limited.…”

Section: Summary Conclusion and Outlookmentioning

confidence: 92%

“…Seasonality was shown to be an important factor in previous studies (Grange et al, 2018). Here, DOY is used as seasonal proxy.…”

Section: Spatiotemporal Informationmentioning

confidence: 97%

See 4 more Smart Citations

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

et al. 2020

View full text Add to dashboard Cite

The quantification of factors leading to harmfully high levels of particulate matter (PM) remains challenging. This study presents a novel approach using a statistical model that is trained to predict hourly concentrations of particles smaller than 10 μm (PM10) by combining satellite‐borne aerosol optical depth (AOD) with meteorological and land‐use parameters. The model is shown to accurately predict PM10 (overall R 2 = 0.77, RMSE = 7.44 μg/m 3) for measurement sites in Germany. The capability of satellite observations to map and monitor surface air pollution is assessed by investigating the relationship between AOD and PM10 in the same modeling setup. Sensitivity analyses show that important drivers of modeled PM10 include multiday mean wind flow, boundary layer height (BLH), day of year (DOY), and temperature. Different mechanisms associated with elevated PM10 concentrations are identified in winter and summer. In winter, mean predictions of PM10 concentrations >35 μg/m 3 occur when BLH is below ∼500 m. Paired with multiday easterly wind flow, mean model predictions surpass 40 μg/m 3 of PM10. In summer, PM10 concentrations seemingly are less driven by meteorology, but by emission or chemical particle formation processes, which are not included in the model. The relationship between AOD and predicted PM10 concentrations depends to a large extent on ambient meteorological conditions. Results suggest that AOD can be used to assess air quality at ground level in a machine learning approach linking it with meteorological conditions.

show abstract

\sim

μ

g/m

^{3}

for daily PM10 predictions.…”

Section: Resultssupporting

confidence: 84%

Section: Resultssupporting

confidence: 81%

Section: Motivation and Research Questionsmentioning

confidence: 91%

“…However, there is indication that very high BLH values (

\sim <

Section: Summary Conclusion and Outlookmentioning

confidence: 92%

“…Seasonality was shown to be an important factor in previous studies (Grange et al, 2018). Here, DOY is used as seasonal proxy.…”

Section: Spatiotemporal Informationmentioning

confidence: 97%

See 3 more Smart Citations

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

et al. 2020

View full text Add to dashboard Cite

show abstract

Impact of Exposure to Environmental Particulate Matter on the Onset of Giant Cell Arteritis

Bond,

Tomelleri,

Reatini

et al. 2024

Arthritis Care & Research

View full text Add to dashboard Cite

ObjectiveAim of the study is to investigate the association between exposure to particulate matter with aerodynamic diameter ≤10μm (PM10) and the development of giant cell arteritis (GCA) and its ischaemic complications.MethodsThis is case‐crossover study on consecutive patients who received a diagnosis of GCA in three hospitals in Northern Italy between 2013 and 2021. The PM10 hourly and daily average concentrations, collected in the Italian monitoring network and archived by ISPRA were determined using European reference. We used a Bayesian hierarchical model to determine patients’ daily exposure to them. We employed conditional logistic regression to estimate the effect of exposure on GCA symptoms onset or ischaemic complications.ResultsWe included 232 patients. A positive association was observed between exposure to PM10 and GCA risk, with an incremental odd of 27.1% (95% CI 5.8‐52.6) for every 10 μg/m3 increase in PM10 concentration within a 60‐day period. We did not find any significant association for shorter periods, nor with ischaemic complications. Subgroup analysis found a significantly higher incremental risk at a 60‐day lag for patients ≥70 years old. Comparing patients who were chronically exposed to high PM10 levels (26.9±13.8 μg/m3) to those who were not (11.9±7.9 μg/m3) revealed that only in the former group there was an association between GCA onset and increased PM10 levels in the preceding 60 days.ConclusionExposure to environmental PM10 in the preceding 60 days seems to be associated with an increased risk of developing GCA, especially in elderly subjects with prolonged exposure to high levels of air pollution.

show abstract

Effects of COVID‐19 lockdown measures on nitrogen dioxide and black carbon concentrations close to a major Italian motorway

Bertazza

Bisignano

Falocchi³

et al. 2023

Meteorological Applications

View full text Add to dashboard Cite

During the first half of 2020, the Italian government imposed several restrictions to limit the spread of the COVID‐19 pandemic: at the beginning of March, a heavy lockdown regime was introduced leading to a drastic reduction of traffic and, consequently, traffic‐related emissions. The aim of this study is to evaluate the effects of these restrictions on pollutant concentrations close to a stretch of the Italian A22 motorway lying in the Alpine Adige valley. In particular, the analysis focuses on measured concentrations of nitrogen dioxide (NO2) and black carbon (BC). Results show that, close to the motorway, NO2 concentrations dropped by around 45% during the lockdown period with respect to the same time period of the previous 3 years. The equivalent analysis for BC shows that the component related to biomass burning, mostly due to domestic heating, was not particularly affected by the restrictions, while the BC component related to fossil fuels, directly connected to traffic, plummeted by almost 60% with respect to the previous years. Since atmospheric concentrations of pollutants depend both on emissions and meteorological conditions, which can mask the variations in the emission regime, a random forest algorithm is also applied to the measured concentrations, in order to better evaluate the effects of the restrictions on emissions. This procedure allows for obtaining business‐as‐usual and meteorologically normalized time series of both NO2 and BC concentrations. The results derived from the random forest algorithm clearly confirm the drop in NO2 emissions at the beginning of the lockdown period, followed by a slow and partial recovery in the following months. They also confirm that, during the lockdown, emissions of the BC component due to biomass burning were not significantly affected, while those of the BC component related to fossil fuels underwent an abrupt drop.

show abstract

Random forest meteorological normalisation models for Swiss PM<sub>10</sub> trend analysis

Cited by 299 publications

References 34 publications

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

Mapping and Understanding Patterns of Air Quality Using Satellite Data and Machine Learning

Impact of Exposure to Environmental Particulate Matter on the Onset of Giant Cell Arteritis

Effects of COVID‐19 lockdown measures on nitrogen dioxide and black carbon concentrations close to a major Italian motorway

Contact Info

Product

Resources

About