Air, Volume 2, Issue 4 (December 2024) – 2 articles

This paper presents a novel machine learning methodology able to extend the results of detailed local emission inventories to larger domains where emission estimates are not available. The first part of this work consists in the development of an emission inventory of elemental carbon (EC), black carbon (BC), organic carbon (OC), and levoglucosan (LG) obtained from the detailed emission estimates available from the Project LIFE PREPAIR for the Po Basin in north Italy. The emissions of these chemical species in combination with particulate primary emissions and gaseous precursors are very important information in source apportionment and in the impact assessment of the different emission sources in air quality. To gain a better understanding of the origins of atmospheric pollution, it is possible to combine measurements with emission estimates for the particulate matter fractions known as EC, BC, OC, and LG. To identify the sources of emissions, it is usual practice to use the ratio of the measured EC, OC, TC (Total Carbon), and LG. The PREPAIR emission estimates and these new calculations are then used to train the Random Forest (RF) algorithm, considering a large array of local variables, such as taxes, the characteristics of urbanization and dwellings, the number of employees detailed for economic activities, occupation levels and land cover. The outcome of the comparison of the predictions of the machine learning implemented model (ML) with the estimates obtained for the same areas by two independent methods, local disaggregation of the national emission inventory and Copernicus Air Modelling Service (CAMS) emissions estimates, is extremely encouraging and confirms it also as a promising approach in terms of effort saving. The implemented modelling approach identifies the most important variables affecting the spatialization of different pollutants in agreement with the main emission source characteristics and is suitable for harmonization of the results of different local emission inventories with national emission reporting. Full article

Harsh winters, aging infrastructure, and the demand for modern amenities are major factors contributing to the deteriorating air quality in Bishkek. The city meets its winter heating energy needs through coal combustion at the central heating plant, heat-only boilers, and in situ heating equipment, while diesel and petrol fuel its transportation. Additional pollution sources include 30 km² of industrial area, 16 large open combustion brick kilns, a vehicle fleet with an average age of more than 10 years, 7.5 km² of quarries, and a landfill. The annual PM_2.5 emission load for the airshed is approximately 5500 tons, resulting in an annual average concentration of 48 μg/m³. Wintertime daily averages range from 200 to 300 μg/m³. The meteorological and pollution modeling was conducted using a WRF–CAMx system to evaluate PM_2.5 source contributions and to support scenario analysis. Proposed emissions management policies include shifting to clean fuels like gas and electricity for heating, restricting secondhand vehicle imports while promoting newer standard vehicles, enhancing public transport with newer buses, doubling waste collection efficiency, improving landfill management, encouraging greening, and maintaining road infrastructure to control dust emissions. Implementing these measures is expected to reduce PM_2.5 levels by 50–70% in the mid- to long-term. A comprehensive plan for Bishkek should expand the ambient monitoring network with reference-grade and low-cost sensors to track air quality management progress and enhance public awareness. Full article