Air pollution is the world's largest environmental health crisis. According to the World Health Organization, approximately 7 million people die each year from air pollution exposure — more than HIV/AIDS, tuberculosis, and malaria combined. Yet despite this scale, pollution sources are often poorly mapped, making policy enforcement and remediation difficult.
The Solvexoria Air Pollution Source Tracking problem applies distributed computing to this challenge: using atmospheric dispersion modeling to trace PM2.5 and NO₂ pollution back to their origin sources. Once sources are quantified — by type, location, and intensity — regulators can target interventions where they'll have maximum impact, rather than applying broad mandates that impose costs without proportionate benefit.
Air pollutants travel hundreds of kilometers from their sources. A PM2.5 reading in a city's center reflects contributions from dozens of sources: vehicle exhaust, industrial facilities, construction dust, agricultural burning, shipping, and transboundary pollution from neighboring regions. Separating these contributions requires running atmospheric dispersion models backwards — from observation to source — across thousands of sensor readings simultaneously.
Studies from the UK's National Atmospheric Emissions Inventory show that the top 1% of pollution sources account for over 40% of total emissions. Identifying and targeting these sources — rather than imposing uniform standards across all emitters — can achieve 5–10× greater emissions reductions per regulatory dollar spent.
Mine air quality research. Your compute helps identify the sources killing 7 million people per year.
⚡ Start Mining — Air Quality Research