New Method Combines AI and Remote Sensing to Map Air Pollution in the UK

The most comprehensive coverage of air pollution in Britain, like never before, has been achieved by an innovative technique that integrates artificial intelligence with remote sensing satellite technologies.

Image Credit: Coatesy/


The result of a new study under the guidance of the London School of Hygiene & Tropical Medicine (LSHTM) and reported in the Remote Sensing journal, the methodology offers precise evaluations of the concentrations of air pollution throughout Great Britain.

The model provides a magnificent level of details, with daily measurements in a 1 km x 1 km grid throughout the entirety of Great Britain.

The study findings denote that England’s South-East part is the most polluted region, and they find hot spots in industrial and urban regions. Promisingly, the results also demonstrate a cumulative decline in air pollution in Great Britain in the past 10 years.

According to the team, this innovative method could completely transform the evaluation of exposure to air pollution and the insights into the associated health risks, by connecting exposure maps and health databases throughout the country.

At present, researchers depend on ground-based monitors to quantify air pollution. But these are scarcely situated, predominantly concentrated in urban areas, and do not always take measurements constantly.

This implies there are no countrywide air pollution records precise enough to be utilized in epidemiological analyses to assess health risks.

As part of this research, the team employed a novel methodology that involves using artificial intelligence and satellite-based data to evaluate the everyday exposure of humans to fine particles of air pollution from 2008 to 2018.

The researchers merged readings from the present-day ground-based monitors with data received from earth observation satellite instruments, offering information on aerosols suspended in the air, weather patterns, vegetation cover, and land use.

Moreover, they integrated data from other sources, such as road density, population density, and the location of airports.

By making use of advanced machine learning algorithms, the researchers integrated the datasets to generate estimates of the ground-level concentration of fine particulate matter (below 2.5 μm in size, PM2.5), one of the most hazardous air pollutants. They segregated Great Britain into grid cells and acquired daily pollution series for the period 2008 to 2018.

This research uses the power of artificial intelligence to advance environmental modelling and address public health challenges. This impressive air pollution dataset represents PM2.5 records for 4,018 days in a spatial domain of 234,429 grid cells. This provides a remarkable total of 950 million data points that comprehensively quantify the level of air pollution across the whole of Great Britain in an eleven-year period.

Dr Rochelle Schneider, Study First Author, London School of Hygiene & Tropical Medicine

The study findings were cross-validated by matching the estimates generated by the model to measurements obtained from specific ground-based monitors and were determined to be in close agreement.

Currently, the team plans to integrate the data with local health records. This linked data will be utilized in advanced epidemiological analyses to unravel a highly granular picture of the link between air pollution and health outcomes throughout Great Britain.

This study demonstrates how cutting-edge techniques based on artificial intelligence and satellite technologies can benefit public health research. The output reveals the shifting patterns of air pollution across Great Britain and in time with extraordinary detail.

Antonio Gasparrini, Study Senior Author and Professor of Biostatistics and Epidemiology, London School of Hygiene & Tropical Medicine

Gasparrini added, “We now hope to use this information to better understand how pollution is affecting the nation’s health, so we can take steps to minimise the risk. The vast amount of data produced will provide a vital tool for public health researchers investigating the effects of air pollution.”

The World Health Organization reports that seven million deaths occur annually worldwide due to air pollution, which leads to lung cancer, lung disease, strokes, and heart disease.

This innovative method has combined the strengths of different data sources to give accurate and comprehensive estimates of air pollution exposure, including ground-based sensors, satellite data, and model reanalyses developed by ECMWF as part of the EU Copernicus programme.

Dr Vincent-Henri Peuch, Director, Copernicus Atmosphere Monitoring Service, European Centre for Medium-Range Weather Forecasts

Dr Schneider and co-authors convincingly demonstrate its performance over Great Britain, paving the way for many future studies into the health effects of air pollution,” added Dr Peuch.

According to Dr Pierre-Philippe Mathieu, Head of Phi-lab Explore Office at European Space Agency (ESA), “It’s exciting to see data from Earth observation satellites being used in public health research to advance our understanding of the intricate relationship between health and air quality, improving lives in Great Britain, Europe and the rest of the world.”

The research has been restricted by the fact that the technique could not reliably recover air pollution levels from years before 2008, due to the limited number of PM2.5 monitors available.

Besides, the model’s performance can be minimal in remote areas where coverage of ground monitoring network is limited. The LSHTM group intends to expand this model and rebuild high-resolution data of other air pollutants.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.