Community-Empowered Air Quality Monitoring System (1804.03293v1)

Abstract: Developing information technology to democratize scientific knowledge and support citizen empowerment is a challenging task. In our case, a local community suffered from air pollution caused by industrial activity. The residents lacked the technological fluency to gather and curate diverse scientific data to advocate for regulatory change. We collaborated with the community in developing an air quality monitoring system which integrated heterogeneous data over a large spatial and temporal scale. The system afforded strong scientific evidence by using animated smoke images, air quality data, crowdsourced smell reports, and wind data. In our evaluation, we report patterns of sharing smoke images among stakeholders. Our survey study shows that the scientific knowledge provided by the system encourages agonistic discussions with regulators, empowers the community to support policy making, and rebalances the power relationship between stakeholders.

• The paper presents a participatory web-based system integrating diverse data sources including animated smoke images, PM2.5 sensor readings, crowdsourced smell reports, and wind data to support community advocacy against industrial air pollution.
• The system design is based on a threefold iterative development process and features tools like an interactive timelapse viewer, data visualization, and automated smoke detection to validate and chronicle pollution events.
• Empirical data indicated the system increased users' self-efficacy and sense of community, demonstrating the potential of ICT tools to amplify grassroots environmental activism and inform civic participation.

Community-Empowered Air Quality Monitoring System: A Technical Overview

The paper "Community-Empowered Air Quality Monitoring System" presents a robust investigation into the application of information technology to empower citizen-led community actions, specifically targeting the issue of air pollution emanating from industrial sources. The paper details a participatory design approach in developing a web-based air quality monitoring system that aggregates various data types to serve as evidential support for community advocacy efforts.

The authors, Hsu et al., from Carnegie Mellon University, explore the integration of multiple heterogeneous data sources, including animated smoke images, particulate matter ($\mathrm{PM_{2.5}}$) readings from strategically placed sensors, crowdsourced smell reports, and wind data. This integration allows for comprehensive environmental monitoring at a large spatial and temporal scale, facilitating nuanced advocacy efforts by the affected community near a coke plant in the Pittsburgh area.

Key Findings and System Design

The paper outlines a threefold iterative development process that addresses real-time community needs and technical challenges through community-based participatory design. This iterative approach was essential in dealing with the wicked nature of the problem, which is complex and continuously evolving, and necessitated flexibility in system development.

1. Interactive Timelapse Viewer and Data Visualization: The system's interface includes a web-based interactive timelapse viewer, allowing users to inspect emissions visually alongside a thumbnail generator to create shareable animated images. Additionally, data from local government and community-deployed sensors is visualized, providing a clear representation of air pollution patterns.
2. Automated Smoke Detection: Using computer vision, the system automatically detects smoke emissions. The algorithm's utility in automating detection reduces manual monitoring time and adds a layer of validity and reliability to the collected data, as these computer-generated outputs allow community members to verify and chronicle pollution events effectively.
3. Community Engagement and Impact: Empirical data gathered showed significant increase in users' self-efficacy and sense of community after interaction with the monitoring system. Despite the community's high initial state of awareness, these cognitive shifts underline the system's role in enhancing community agency and empowerment in environmental governance.

Implications and Potential Developments

The paper's implications extend into several domains. Theoretically, it contributes to sustainable HCI by offering a methodological blueprint for adversarial design — confronting unbalanced power structures between communities and regulatory stakeholders. In practice, it substantiates the efficacy of ICT tools in amplifying grassroots environmental activism, which can be replicated or adapted in similar contexts globally.

Future advancements may include enhancing the smoke detection algorithm's robustness through machine learning, supported by crowdsourced labels, to further automate data interpretation. Additionally, scaling the system could involve deploying similar low-cost monitoring frameworks across varying geographical and industrial contexts, fostering a scalable model for citizen-science and environmental monitoring.

In conclusion, the described air quality monitoring system serves not only as a scientifically rigorous tool for community advocacy but also as a beacon for participatory design and sustainable human-computer interaction, potentially revolutionizing grassroots advocacy through informed civic participation and collaboration.