QUALEARIA-LOCAL
- /
- POC
- /
- QUALEARIA-LOCAL
ARIANET is a consulting company that deals with urban air pollution through meteorological reconstruction, emission treatment, and simulation of processes involving pollutants. Urban air pollution is determined by three factors: regional, urban, and roadway. The first two factors can be simulated through atmospheric chemistry and machine learning models, while the third can be evaluated with microscale dispersion models. ARIANET provides support to public and private clients in environmental impact assessment, air quality prediction and evaluation, and pollution source analysis.
Start date: 01/06/2021
Duration in months: 12
Problem Description
The use-case concerns the use of ML models in the field of air pollution to produce air quality forecasts at high spatial resolutions.
Goals
New services
Challenges
The scientific-technical challenge lies in simulating pollution within the urban area, since this is determined by the following contributions:-regional, due to sources in surrounding areas (essentially uniform over a large portion of the agglomeration),- urban, relating to all sources of pollution within the city whose distribution can be considered uniform (e.g., heating of buildings),- street-level, highly inhomogeneous, higher than the previous two (due to traffic emissions and chemical-physical processes occurring within street canyons),The first two contributions can be simulated by coupling atmospheric chemistry models and machine learning models. The third can be evaluated with microscale dispersion models.So the sifda lies in being able to develop a solzuion that simulates all contributions.
Innovation results
QualeAria-Local is composed of three elements:- Air Quality Forecasting System (AQFS) QualeAria- Random Forest (ML-RF) machine learning algorithm.- μ-scale Parallel-Micro-Swift-Spray (PMSS) modeling suite. The concentration fields of PM10, PM2.5, NO2, and O3 produced by Qualearia for a trial period (year 2021), together with a set of spatiotemporal predictors and available air quality observations, were processed by the ML-RF algorithm to obtain the corresponding highest resolution (1 km) concentration fields over the national territory. The resulting concentration fields provide the regional and urban background fields to the PMSS suite, which is used to produce forecasts of atmospheric particulate matter and nitrogen oxides at very high spatial resolution (4 m) over a selected urban area (Milan conurbation). Figure 1 provides a schematic representation of QualeAria-Local.
Business impact
The project confirmed the potential of ML models in the field of air pollution to produce air quality predictions at high spatial resolutions with lower computational load than required by chemical transport model (CTM) simulations.