TL;DR:
- CAMS introduces a new air quality forecast product merging AI and observations.
- The “European Air Quality Forecasts Optimised at Observation Sites” provides precise predictions for regulated pollutants across Europe.
- Utilizes AI and real-time observations from air quality monitoring networks.
- CAMS-MOS enhances forecast accuracy, especially in areas influenced by local sources.
- Combines CAMS regional ensemble forecasts with air quality and meteorological observations.
- Offers tailored information at sites with routine measurements, focusing on surface-level data.
- Quality scores of CAMS-MOS product are routinely monitored for reliability.
Main AI News:
The latest forecast from CAMS merges data from observations with artificial intelligence, enhancing the current European air quality predictions. Known as “European Air Quality Forecasts Optimised at Observation Sites,” this innovative product utilizes an AI-driven approach leveraging real-time observations from air quality monitoring networks across Europe, collected by the European Environment Agency. Providing forecast timeseries for numerous monitoring site locations, CAMS-MOS augments the existing CAMS gridded forecast, delivering more precise predictions of regulated pollutants, even in areas heavily influenced by local sources. Powered by a numerical approach known as Model Output Statistics (MOS), this new offering represents a significant advancement in air quality forecasting.
Previously, CAMS offered gridded air quality forecasts through a unique multi-model approach, drawing on eleven top-tier models operated by institutions across Europe. These forecasts, based on advanced chemistry-transport models, are quality assured regularly, with all data freely available for scrutiny. Despite its merits, the spatial resolution of the legacy CAMS forecasts limits their ability to capture local air pollution nuances. However, the CAMS-MOS product fills this gap by providing tailored information at sites where in-situ measurements are routinely conducted.
Utilizing an innovative machine learning post-processing algorithm, CAMS-MOS combines CAMS regional ensemble forecasts with air quality observations and meteorological forecasts. This automated learning methodology adjusts forecasts based on recent observations and specific meteorological conditions, ensuring accuracy even in areas where the gridded CAMS forecasts falter. While this approach enhances forecast precision, it is constrained to locations with routine observations and surface-level data.
Moving forward, CAMS users will benefit from enhanced insights into air pollution episodes in Europe, as the combination of CAMS gridded forecasts and CAMS-MOS forecasts offers a comprehensive understanding of air quality dynamics. Regular monitoring of the CAMS-MOS product’s quality scores ensures continued reliability, fostering trust among users.
The integration of advanced statistical post-processing methods not only enhances forecast accuracy but also broadens the scope of possibilities for CAMS users. With access to high-quality information optimized at observation sites, users can better grasp the complexities of air pollution and make informed decisions. For further details on the methodology behind these advancements, interested parties can refer to a scientific paper detailing the work undertaken by INERIS and Météo-France, CAMS contractors for the development and implementation of European air quality products. Daily forecasts optimized at observation sites are readily accessible on the Atmosphere Data Store, available either through manual retrieval or automated scripts, providing users with timely and actionable insights.
Conclusion:
The introduction of CAMS-MOS represents a significant advancement in European air quality forecasting, offering enhanced accuracy and insights into air pollution dynamics. This innovation underscores the growing importance of leveraging AI and real-time observations in environmental monitoring. For businesses operating in sectors sensitive to air quality, such as transportation, energy, and healthcare, access to reliable forecasts provided by CAMS-MOS can inform strategic decision-making, risk management, and resource allocation, ultimately contributing to improved public health and environmental sustainability.
