• Barratt, Benjamin Malyon
• Beddows, Andrew
• Analitis, Antonis
• Green, David
• Katsouyanni, Klea
• Schwartz, Joel
• Samoli, Evangelia

Abstract

<p>The adverse health effects of air pollutants, especially those of PM_2.5, are well documented. However, a lack of adequate monitoring and weaknesses in modelling approaches do not allow a good assessment of health effects in many areas of the World. Advances in computational methods and the availability of new data sets, e.g. satellite remote observations, have enlarged the possibilities of modelling for application in large scale health effects studies. However, PM_2.5 monitoring is very recent in most of the World and more limited compared to other pollutants, and understanding how to use PM₁₀ monitors to estimate PM_2.5 exposure is therefore important. Since interest in these methods is relatively recent, there is a need for testing their performance against ambient measurements, but long term PM_2.5 datasets are less readily available than PM₁₀ in many regions. In the present study we report the methodology and results of using regression modelling and a machine learning method (Random Forest-RF), as well as a combination of the two, to enhance a PM_2.5 measurement data base in London using PM₁₀ and NO_x measurements as well as other predictors and compare the relative performance of each method. We found that the combination of predictions by the regression model and the RF performs best and we obtain a cross-validation R² of 99.29% and 98.22% for the 5-year periods 2004–2008 and 2009–2013, respectively, and a Mean Square Error near 1. Our enhanced data base for PM_2.5 is available for use by other researchers.</p>

Topics

• impedance spectroscopy
• laser emission spectroscopy
• random
• machine learning