Overtraffic is one of the main keys to air pollution in urban areas. The aim of the present work is to review the approaches and explore the potentiality of AI in reducing traffic pollution in urban areas, ranging over three main areas: the optimization of traffic lights timing to reduce delays, the use of AI-powered drones to monitor pollution levels in real-time, and the use of fixed AI-based sensors to detect the levels of pollutants in the air with the use of AI models to identify patterns in the collected data and predict air quality in near-real time. Some attention was also dedicated to possible problems arising from privacy protection and data security, and the case study of the Piemonte area and of the city of Turin in the north–west of Italy is presented: the current situation is depicted, and possible local future applications of AI are explored. The use of AI has proven to be very promising in all three areas, particularly in the field of optimization of traffic lights’ timing and coordination in increasingly larger traffic networks.
When it rains or snows over a city, water droplets capture airborne pollutants and transport them to the ground. Prolonged precipitation over the same area can remove a larger amount of pollution; however, rainfall systems vary in duration and tend to move rapidly across regions. Wet deposition sprinklers replicate this natural scavenging process. They can operate for extended periods as needed and can be installed at specific locations where pollution mitigation is most necessary. Despite encouraging experimental results and the widespread use of similar technologies in industrial sectors—such as mining, the construction industry, and waste management—very limited scientific research has focused on their application in urban environments. In particular, their use as an emergency measure during severe pollution episodes as a protective intervention for sensitive subjects, while awaiting the effects of long-term structural solutions, remain largely unexplored. In the present work, we systematically discuss the key elements required to design and implement a network of anti-smog cannons (ASC) to protect sensitive receptors from severe air pollution events in large cities. Based on this analysis, we established a generalized framework that can be applied to any urban context worldwide. We also examine the potential application of the proposed method to the city of Turin (≈850,000 inhabitants, north-western Italy), which is considered a representative case study for other cities in Western Europe. Our findings indicate that such a network is both technically feasible and economically sustainable for local government authorities.
Ammonia (NH3) emissions from intensive livestock farming are a major contributor to the formation of secondary particulate matter (PM2.5) in northern Italy, particularly during winter, when high humidity and low temperatures promote ammonium nitrate formation. This phenomenon is further exacerbated by the extensive use of maize monoculture, which leaves the soil bare for most of the winter season, thereby reducing aerodynamic roughness and limiting dry deposition processes. This study evaluates the potential of winter cover crops to enhance atmospheric ammonia removal by increasing dry deposition velocities. Drawing on established deposition models and regional air-quality data, we estimate that replacing bare soil with autumn–winter vegetation can increase deposition velocities by up to an order of magnitude (from <0.1 to ≈1 cm s−1). In hotspot areas of the Cuneo–Turin plain, where winter NH3 concentrations regularly exceed 30 µg m−3, cover crops can generate additional deposition fluxes of approximately 30–70 kg NH3 ha−1 yr−1. Applied to the 90,000 ha of intensive monoculture identified in the study area, this corresponds to a potential removal of ~2800 t NH3 yr−1, equivalent to 8–9% of total agricultural emissions in Piedmont. These reductions would also decrease the availability of precursors for secondary PM2.5 formation. Existing regional rural-development measures provide a suitable policy framework, but they are currently underutilized, indicating substantial potential for large-scale implementation.
Advanced biofuels represent a key option for transport decarbonization, particularly in sectors where electrification is constrained by technical and economic barriers. Their compatibility with existing vehicle fleets and fuel distribution infrastructure enables rapid deployment without the need for major capital investments. In local public transport, biodiesel (FAME), hydrotreated vegetable oil (HVO), and biomethane are mature solutions capable of delivering greenhouse gas emission reductions of 60–90% compared with fossil fuels. Among these, HVO is particularly promising, as an extensive body of literature has consistently shown its potential to significantly reduce engine-out emissions, especially particulate matter (PM) and nitrogen oxides (NOx). This study reports the results of an experimental campaign carried out on a diesel-powered local public transport bus equipped with a Euro III engine and lacking particulate matter and NOx after-treatment systems. Emissions were measured using a portable emissions measurement system (PEMS) under real driving conditions, operating the vehicle with neat diesel, a 15% HVO blend, and a 70% HVO blend. Tests were conducted over urban and extra-urban routes. The results show that NOx emissions decrease proportionally with increasing HVO content, with high-blend ratios (HVO70) yielding estimated reductions of approximately 13–18%, and up to 23% under carefully controlled and comparable urban driving conditions. Based on these findings and the existing literature, HVO proves to be a useful instrument to meet 2025–2030 climate and air quality targets (particularly NOx and PM emission reductions), alongside electrification and modal shift measures, if used in public transport fleets.