Machine learning model to predict vehicle electrification impacts on urban air quality and related human health effects.

Air pollution is a prevailing environmental problem in cities worldwide. The future vehicle electrification (VE), which in Europe will be importantly fostered by the ban of thermal engines from 2035, is expected to have an important effect on urban air quality. Machine learning models represent an optimal tool for predicting changes in air pollutants concentrations in the context of future VE. For the city of Valencia (Spain), a XGBoost (eXtreme Gradient Boosting package) model was used in combination with SHAP (SHapley Additive exPlanations) analysis, both to investigate the importance of different factors explaining air pollution concentrations and predicting the effect of different levels of VE. The model was trained with 5 years of data including the COVID-19 lockdown period in 2020, in which mobility was strongly reduced resulting in unprecedent changes in air pollution concentrations. The interannual meteorological variability of 10 years was also considered in the analyses. For a 70% VE, the model predicted: 1) improvements in nitrogen dioxide pollution (-34% to -55% change in annual mean concentrations, for the different air quality stations), 2) a very limited effect on particulate matter concentrations (-1 to -4% change in annual means of PM2.5 and PM10), 3) heterogeneous responses in ground-level ozone concentrations (-2% to +12% change in the annual means of the daily maximum 8-h average concentrations). Even at a high VE increase of 70%, the 2021 World Health Organization Air Quality Guidelines will be exceeded for all pollutants in some stations. VE has a potentially important impact in terms of reducing NO2-associated premature mortality, but complementary strategies for reducing traffic and controlling all different air pollution sources should also be implemented to protect human health.

On the origin of the highest ozone episodes in Spain.

The 2000-2015 occurrences of the highest ozone (O3) pollution episodes in Spain were evaluated to investigate their origin. To this end, data series available for urban and regional background (UB and RB), traffic (TR) and industrial (IN) sites were analysed separately and intercompared. Results evidenced that during these 16years mean O3 levels in the RB sites did not change significantly, and remained constantly high. However, there is a clear increase at the TR and UB sites. Although sensitivity analysis is needed to interpret the cause of this increasing trend, this might be caused probably by the lower O3 titration intensity due to the preferential abatement of NO vs NO2, as supported from the neutral trend of OX (NO2+O3) at these sites. We found that the exceedances of the hourly information threshold for O3 (>180µg/m3) are recorded mostly at UB and IN sites located in seven areas of Spain (specific hotspots or at the tail end of large urban plumes), and that these increased during summer heatwaves (i.e. 2003 and 2015). Although the external contribution of regional-to-subcontinental transported O3 might be relevant during the highest O3 episodes in the Western Mediterranean, our results evidenced that in the above specific areas, regional-local O3 production decisively contributes to the exceedances of the information threshold. Also that the human protection threshold and the AOT40 are more frequently exceeded in the Central, Southern and Mediterranean sides of the Iberian Peninsula. The design of effective episode abatement measures is quite complex in those conditions, due to both the nonlinearity of the chemical processes of O3 formation and destruction, and to the interplay with the complex meteorological setting, causing frequent recirculation and in situ aging of air masses. However, the combination of meteorological forecasting of the main recirculation processes and sensitivity analysis of NOX/VOC emission abatement measures might be powerful tools to evaluate the effectiveness of potential O3 mitigation strategies. Finally we would like to highlight that the current UB, RB, IN and TR classification (somewhat subjective) is not adequate to interpret the origin of O3 exceedances in complex areas of Southern Europe. Thus, a UB station recording exceedances, and located in a small city in the tail end of an urban plume of a large city, receives not only the contribution from its own UB, but mainly from the specific high O3 RB caused by the urban plume transport.