Vol. 37 No. 1 (2023) | DOI: https://doi.org/10.20937/ATM.53116
Autores: Becerra-Rondón, A., Ducati, J. and Haag, R.
itrogen dioxide (NO2) is one of the most important atmospheric pollutants, affecting human health (increasing susceptibility to respiratory infections) and the environment (soil and water acidification). In many regions of Brazil, NO2 measurements at ground level meet difficulties because monitoring stations are few and unevenly distributed. Satellite observations combined with machine learning models can mitigate this lack of data. This paper report results from an investigation on the ability of a machine learning approach (a non-linear statistical Random Forest algorithm, hereafter RF) to reconstruct the long-term spatiotemporal ground-level NO2 from 2006 to 2019 using as input parameters NO2 data retrieved from the Ozone Monitoring Instrument (OMI) sensor aboard Aura satellite, besides meteorological covariates and localized ground-level NO2 measurements. Results show that the RF model predicts NO2 with an accuracy expressed by an R2 = 0.68 correlation based on a 10-fold cross-validation. The model also predicted a mean NO2 concentration of 18.73 ± 3.86 μg m–3. The total NO2 concentration over the entire region analyzed showed a decreasing trend (2.9 μg m–3 yr–1), being 2006 the year with the higher concentrations and 2017 with the lowest. This study suggests that non-linear statistical algorithm reconstructions using RF can be complementary tools to in situ and satellite observations for NO2 mapping.