Improving air quality in London through data science and machine learning

This DT story focuses on the utilization of city-wide air quality sensors and the development of machine learning algorithms and data science platforms to understand and improve air quality in London. By integrating heterogeneous data sources and leveraging advanced technologies, the project aims to provide accurate air quality estimates and forecasts. It also aims to identify optimal sensor placement, inform targeted interventions, and assist individuals in finding low-pollution routes. Through this DT story, the project seeks to raise awareness, foster collaboration, and enhance air quality in London.

Problem or opportunity

Air quality in London has improved in recent years due to emissions reduction policies, but certain areas still exceed NO2 EU Limit Values. This poses a significant threat to public health, with thousands of Londoners experiencing premature deaths each year. Similar air quality challenges are prevalent in cities across the UK and Europe. The project recognizes the need to address these issues by utilizing advanced technologies and data-driven approaches to monitor, analyze, and improve air quality in London.

Expected benefits

The project aims to bring together data from various networks into a single platform for analysis, allowing comprehensive monitoring and evaluation of interventions. By providing accurate estimates and forecasts, web applications can inform Londoners about air quality conditions. Additionally, individuals will have access to low-pollution routes for walking, cycling, or running. Machine learning algorithms, statistical methodologies, and data science platforms should be employed to enhance air quality understanding and forecasting. The integration of heterogeneous sensors and real-time monitoring will inform optimal sensor placement and targeted interventions to reduce pollution levels. Alongside these goals, APIs and mobile apps will provide reliable, localized air quality data and forecasts. Graph optimization algorithms will aid pedestrians and cyclists in finding less polluted routes. The project's technological infrastructure includes cloud-based systems, big data storage in Azure, and the use of Kubernetes for scheduled tasks and API deployment. Through these efforts, the project aims to improve air quality, enhance public health, and promote environmental sustainability in London.