Urban air quality and climate protection are two major challenges for future mobility systems. Despite the steady reduction of pollutant emissions from vehicles over past decades, local immission load within cities partially still reaches heights, which are considered potentially hazardous to human health. Although traffic-related emissions account for a major part of the overall urban pollution, modelling the exact interaction remains challenging. At the same time, even lower vehicle emissions can be achieved by using synthetic fuels and the latest exhaust gas cleaning technologies. In the paper at hand, a neural network modelling approach for traffic-induced immission load is presented. On this basis, a categorization of vehicle concepts regarding their immission contribution within an impact scale is proposed. Furthermore, changes in the immission load as a result of different fleet compositions and emission factors are analysed within different scenarios. A final comparison is made as to which modification measures in the vehicle fleet offer the greatest potential for overall cleaner air.