Image Courtesy : www.facebook.com/ReachIITM

The Indian Institute of Technology, Madras (IIT Madras) researchers have developed data science and IoT-based practice for mobile pollution monitoring. This framework developed by the researchers permits pollution sensors scaled on public vehicles to monitor the air quality of an extended area at an increased spatial and temporal resolution.

The IIT Madras researchers have developed a network capable of gathering spatiotemporal air quality data by equipping vehicles with low-cost air quality sensors. The Indian Institute of Technology Madras stated that this seeks to allow the mapping of an entire city at high resolution at the cost of a single reference monitoring station.

The project titled Kaatru, meaning air in Tamil, seeks to acquire a pan-India hyper-local air quality map, perform exposure assessments for Indian citizens, and develop data-driven resolutions for policy, intervention, and mitigation techniques.

The paper describes the data science and IoT-based mobile monitoring framework for achieving high-resolution spatiotemporal assessments and effective spikes in PM2.5 pollution during specific times, such as when trucks carrying milk pass via particular areas and during school opening and ending hours.

The affordability and efficacy of the IoT-based mobile monitoring network, integrated with data science principles, deliver exceptional benefits in collecting hyperlocal understandings of air quality, allowing informed mitigation and policy decisions.

The IoT mobile monitoring devices can measure numerous parameters, including PM1, PM2.5, and PM10, as well as gases like NOx and SOx. The devices can consider road roughness, potholes, and UV index, among other elements. The patented IoT side view mirror design facilitates the developed devices to be retrofitted on diverse vehicles, from buses to cars and even two-wheelers.

In order to validate the dependability of the data gathered by the IoT, the researchers performed two case studies. The first case study concentrated on hyperlocal air quality assessments in a carefully chosen area in western Chennai. The case study caught slight variations in PM2.5 concentrations across various locations and roads, delivering beneficial insights into pollution patterns.

The second study examined PM2.5 levels during the high-intensity event of Deepavali. The data accumulated from the IoT devices corresponded to that of a Central Pollution Control Board (CPCB) station, and a high qualitative match was followed, validating the dependability of the mobile monitoring system.