AI Enhances Accuracy of Affordable Air Pollution Sensors, Promising Improved Public Health

How AI is making affordable air pollution sensors more accurate

Clean air is a fundamental right. However, every day, 100 children under the age of five tragically lose their lives in east Asia and the Pacific due to a silent killer - air pollution. In response to this crisis, huge investments have been made in outdoor air pollution monitoring systems. These fridge-sized monitoring stations are expensive costing at least £10,000 each, so scaling this up everywhere isn't financially viable. Now, a new generation of small, roaming air sensors could better inform people about pollution levels in their local area. Currently, these sensors just aren't precise enough. Our recent research shows that AI could enhance their accuracy by up to 67%. These compact devices are the size of a thick mobile phone and cost just a few thousand pounds. They can easily be attached to vehicles such as buses, courier vans and bin lorries that already cruise through our streets. By gathering data wherever people live, work or play, these roaming sensors can build a real-time air quality map that reflects the local environment much more accurately. The main contributor to air pollution is the burning of fossil fuels - this also produces greenhouse gas emissions that contribute to climate change. Alarmingly, air pollution is responsible for 7 million deaths every year. Children are especially vulnerable due to their developing lungs, weaker immune system, and faster breathing rate. Last summer, we spent 12 weeks collecting air pollution data from both inexpensive gas sensors and reference instruments at a UK national facility, the Weybourne Atmospheric Observatory in Norfolk. Every minute, the roaming air sensors transmit pollutant levels to a data centre - that includes particulate matter (such as fine particles of soot), carbon monoxide, ozone, nitrogen dioxide and sulphur dioxide. But we found inconsistencies between data from sensors and data from the national reference instruments. Before this tech can be scaled up, the accuracy of readings from these air sensors needs improving. We have been studying how the problem-solving ability of AI can be used to improve air pollution monitoring. With a clearer understanding of the complex relationships between different gases, pollutants and environmental conditions, AI can correct any measurement errors. Currently, measurements are influenced by the presence of other pollutants and environmental factors, such as temperature and humidity. Understanding how a dozen parameters simultaneously affect a specific gas measurement is a real jigsaw puzzle. Even the manufacturers of these sensors have not managed to crack it yet. During our experiments, we identified the main causes of measurement inaccuracies for each gas sensor. With this information, our AI-driven solution slashed errors by up to 67%. Data science turned flawed, yet promising, sensors into precision tools that can help people seeking cleaner air. With breakthroughs like this, air quality insights could be more quickly scaled up. From stations to sensors Better monitoring will improve our understanding of local air pollution sources, their effects on residents, and help pinpoint the sources responsible, plus lead to more tailored warning systems. In February 2024, the US Environmental Protection Agency committed US$83 million (£64.5 million) to expand and upgrade its air pollution monitoring network. This tech can be used to better understand the threat, shape policies and shape emergency measures. But monitoring stations are expensive, typically £10,000 to £30,000 per unit - and that's without considering installation and maintenance charges. Bangladesh, one of the hardest-hit countries in terms of air pollution, has only 11 monitoring stations. Even a wealthy city like London has fewer than one station per 100,000 residents. This is inadequate because pollution levels may significantly vary between neighbouring streets. Read more: AI is supposed to make us more efficient - but it could mean we waste more energy Remote sensors offer a more affordable and practical solution, if they can be sufficiently accurate. To be commercially feasible, AI mustn't make these sensors more expensive. Transparency about how this system makes decisions is also critical. We used simple AI technology that operates on a microcontroller -- a tiny computer within the device -- to keep the additional cost of incorporating AI to under a few pounds and minimise its energy cost. Imagine joggers checking local readings before choosing a route, or parents scanning the latest updates to find the safest playground for their children. Suddenly, air quality becomes more than a distant worry: it's a practical guide to better health. Gone is the guesswork, replaced by knowledge that helps people make healthier choices. When every breath matters, this tech ensures people no longer have to gamble with their health based on where they live. Don't have time to read about climate change as much as you'd like? Get a weekly roundup in your inbox instead. Every Wednesday, The Conversation's environment editor writes Imagine, a short email that goes a little deeper into just one climate issue. Join the 40,000+ readers who've subscribed so far.

How AI is making affordable air pollution sensors more accurate

by Jean-Christophe Nebel and Farzana Rahman, The Conversation Clean air is a fundamental right. However, every day, 100 children under the age of 5 tragically lose their lives in east Asia and the Pacific due to a silent killer -- air pollution. In response to this crisis, huge investments have been made in outdoor air pollution monitoring systems. These fridge-sized monitoring stations are expensive, costing at least £10,000 each, so scaling this up everywhere isn't financially viable. Now, a new generation of small, roaming air sensors could better inform people about pollution levels in their local area. Currently, these sensors just aren't precise enough. Our recent research shows that AI could enhance their accuracy by up to 67%. These compact devices are the size of a thick mobile phone and cost just a few thousand pounds. They can easily be attached to vehicles such as buses, courier vans and bin lorries that already cruise through our streets. By gathering data wherever people live, work or play, these roaming sensors can build a real-time air quality map that reflects the local environment much more accurately. The main contributor to air pollution is the burning of fossil fuels -- this also produces greenhouse gas emissions that contribute to climate change. Alarmingly, air pollution is responsible for 7 million deaths every year. Children are especially vulnerable due to their developing lungs, weaker immune system, and faster breathing rate. Last summer, we spent 12 weeks collecting air pollution data from both inexpensive gas sensors and reference instruments at a UK national facility, the Weybourne Atmospheric Observatory in Norfolk. Every minute, the roaming air sensors transmit pollutant levels to a data center -- that includes particulate matter (such as fine particles of soot), carbon monoxide, ozone, nitrogen dioxide and sulfur dioxide. But we found inconsistencies between data from sensors and data from the national reference instruments. Before this tech can be scaled up, the accuracy of readings from these air sensors needs improving. We have been studying how the problem-solving ability of AI can be used to improve air pollution monitoring. With a clearer understanding of the complex relationships between different gases, pollutants and environmental conditions, AI can correct any measurement errors. Currently, measurements are influenced by the presence of other pollutants and environmental factors, such as temperature and humidity. Understanding how a dozen parameters simultaneously affect a specific gas measurement is a real jigsaw puzzle. Even the manufacturers of these sensors have not managed to crack it yet. During our experiments, we identified the main causes of measurement inaccuracies for each gas sensor. With this information, our AI-driven solution slashed errors by up to 67%. Data science turned flawed, yet promising, sensors into precision tools that can help people seeking cleaner air. With breakthroughs like this, air quality insights could be more quickly scaled up. From stations to sensors Better monitoring will improve our understanding of local air pollution sources, their effects on residents, and help pinpoint the sources responsible, plus lead to more tailored warning systems. In February 2024, the US Environmental Protection Agency committed US$83 million (£64.5 million) to expand and upgrade its air pollution monitoring network. This tech can be used to better understand the threat, shape policies and shape emergency measures. But monitoring stations are expensive, typically £10,000 to £30,000 per unit -- and that's without considering installation and maintenance charges. Bangladesh, one of the hardest-hit countries in terms of air pollution, has only 11 monitoring stations. Even a wealthy city like London has fewer than one station per 100,000 residents. This is inadequate because pollution levels may significantly vary between neighboring streets. Remote sensors offer a more affordable and practical solution, if they can be sufficiently accurate. To be commercially feasible, AI mustn't make these sensors more expensive. Transparency about how this system makes decisions is also critical. We used simple AI technology that operates on a microcontroller -- a tiny computer within the device -- to keep the additional cost of incorporating AI to under a few pounds and minimize its energy cost. Imagine joggers checking local readings before choosing a route, or parents scanning the latest updates to find the safest playground for their children. Suddenly, air quality becomes more than a distant worry: it's a practical guide to better health. Gone is the guesswork, replaced by knowledge that helps people make healthier choices. When every breath matters, this tech ensures people no longer have to gamble with their health based on where they live.

How we prioritize clean air in an AI-powered world

The Equal Air Collaborative is bringing leaders together to drive collective action for clean air solutions. Smoking has long been recognized as hazardous - no parent would encourage it for their child for a long and healthy life. Yet, few realize that air pollution has now surpassed tobacco and poor diet as a leading cause of death. With technological advancements accelerating and wildfires intensifying due to deforestation and rising global temperatures, are we dedicating enough attention to how innovations such as artificial intelligence (AI) can help safeguard clean air and other vital resources for the future? Coupa and NationSwell are launching the Equal Air Collaborative to bring together leaders from across sectors to champion solutions to combat air pollution, ensuring that everyone, regardless of their background or where they live, has access to clean air and essential natural resources and we are looking for other innovators to join us. Every year, air pollution contributes to more than 10 million deaths globally. Ninety-nine percent of us are exposed but some are more vulnerable to the health consequences or are over-exposed. For example, low-income and indigenous communities, children and older adults all experience greater pollution damage to their lungs and overall health. Despite shifts toward more sustainable processes and electric vehicles, the US Environmental Protection Agency reported that the combined emissions from industry, electric power and transportation contribute 76% of carbon air pollution. In addition, increased wildfires, caused by excessive deforestation and rising planetary temperatures are creating untenable levels of smoke. This is a global issue as air particles move across borders, disproportionately affecting lower-income families more likely to live near highways and factories, exposing them to a greater risk of illness. We need innovation to ensure everyone has access to clean air. Coupa is an AI native, industry-leading total spend management platform for businesses seeking to address the clean air emergency. In addition to their net zero carbon and climate reduction goals (validated by the Science Based Targets initiative), in 2022, Coupa launched the Equal Air Project in partnership with Earth Watch, Sustainable Silicon Valley and Yale School of Public Health. Coupa volunteers placed specialized sensors across the San Francisco Bay Area to test and monitor air quality. Yale School of Public Health monitored and analyzed two months of data to better understand local-level exposures. The results proved that the quality of the air we breathe differs dramatically by zip code. Why should businesses such as Coupa address access to clean air? Because it makes business sense. Skilled, reliable talent is hard to find but if employees breathe polluted air they are more likely to get sick and experience reduced cognitive performance. Globally, 1.2 billion workdays are lost due to air pollution, projected to reach 3.8 billion days by 2060. As billions of dollars are pumped into AI development, we should consider how these powerful new tools can solve systemic issues, some of which are completely unknown - so-called hidden pollutants. Car tyres, for example, are a highly dangerous pollutant that governments have yet to regulate. AI and big data can help us create inventive new ways to monitor and understand emissions. For example, a Penn State-led research team used AI and mobility data to improve the accuracy of air pollution predictive models by an average of 17.5%, allowing for more targeted interventions and mitigation for vulnerable areas. This type of improved modelling could make a significant impact when used at scale in industries. Dr Krystal Pollitt at the Yale School of Public Health has created a wristband that allows individuals to understand their exposure to environmental chemicals around them utiizing AI. However, while AI and other technology can significantly increase the monitoring and detection of air molecules, it can also negatively impact air quality if we don't consider the entire life cycle of its development. What's more, the rapid expansion of data centres and energy use are leading some to warn of an oncoming energy crisis in the United States. China offers us insight into what this means for the air we breathe - studies show that increases in electricity consumption are associated with decreases in the air quality index. As AI becomes an evermore integrated presence in every aspect of our lives, particularly in business, members of this community need to consider how their AI-powered products and services influence the air being breathed every day by their employees, partners and customers. We invite you to join the Equal Air Collaborative for a conversation on "The Bottom Line: Collective Action for Clean Air" on 23 April to learn more and discuss solutions for a more responsible path forward.