Enhancing Air Quality Monitoring in India through Dense IoT Deployments (AirIoT): A Multi-faceted Approach

Abstract

Air pollution, primarily driven by particulate matter (PM), significantly threatens public health. India, with three cities ranking among the world's top ten most polluted and with PM concentrations exceeding WHO guidelines by almost 11 times, urgent measures are needed to address this escalating crisis. AirIoT, a densely deployed IoT-based air quality monitoring network in Hyderabad, India, is an evidence-based approach to bringing awareness and increasing public participation by alleviating data scarcity. PM concentration has high spatial variability and is often characterized by data scarcity since traditional monitoring setups fall short due to their bulkiness and cost limitations. To tackle this, our research advocates for an innovative approach—deploying a dense network of IoT-enabled PM monitoring devices equipped with low-cost sensors. The work revolves around two core elements: measurement and modelling. 49 IoT-based PM monitoring devices were developed, calibrated, and deployed across Hyderabad, India, covering urban, semi-urban, and green areas. Calibration, essential for seasonal variations, utilized a precise reference sensor. A web-based spatial data dashboard and an Android app were also developed for dynamic geo-visualization of the data from the IoT network, offering citizens and governments actionable insights for efficient pollution control measures. Spatial interpolation models were also designed to extrapolate measurements at micro and macro levels. Demonstrating the effectiveness of dense deployment, a case study was conducted during the Diwali festival, highlighting the importance of localized information in scenarios with air pollution hotspots. The health impacts of air pollution were also studied, correlating measurements with respiratory, cardiovascular, and psycho-physiological effects. A pilot study utilizing data from AirIoT, health wearables and a questionnaire investigated the long-term health implications for security personnel exposed to air pollution. Computer vision-based methods were developed to scale air pollution monitoring using features like visibility, traffic type and density, eliminating the need for frequent sensor usage. Trained on a large dataset using deep learning, these methods predict air quality in real-time, offering a viable alternative for large-scale implementations. Ensuring citizen engagement and capacity building, we conducted pilot studies in schools, engaging students in understanding and combating air pollution. Public display systems showcasing real-time pollution levels generated excitement and awareness, leading to residents advocating for reforms. Engineering students from various colleges were trained through hackathons and internship programs to develop low-cost air pollution monitoring devices for local measurements at their institutions and localities. Our work extends beyond air quality monitoring, interlinking with broader smart city applications through the Smart City Research Center at IIITH. Utilizing interoperability standards, such as oM2M, we integrate air quality data with other verticles like weather, water, energy, and crowd monitoring, establishing an interoperable environment with scalable prototypes for other smart cities. Finally, embracing the importance of data sharing and management, our live data feeds into the Indian Urban Data Exchange (IUDX), a data exchange platform aligning with the Smart Cities Mission in India. With a blend of IoT technology and social participation, this collaborative initiative ensures a comprehensive and data-driven approach to address the complex challenges of air pollution in India.