Eclipse: An End-to-End Platform for Low-Cost, Hyperlocal Environmental Sensing in Cities

This paper presents Eclipse, a platform for low-cost urban environmental sensing using solar-powered and cellular-connected devices. Dense sensor networks promise to monitor pollution at fine spatial and temporal resolutions, yet few cities have actually implemented such networks due to high costs and limited accuracy. We address these barriers by developing an end-to-end framework for urban air quality sensing with minimal infrastructure requirements. We designed an unobtrusive device that collects data on fine particulate matter (PM2.5), temperature, relative humidity, and barometric pres-sure. A modular design further includes four low-cost gas sensors - Ozone (03), Nitrogen Dioxide (NO2), Sulfur Dioxide (SO2), and Carbon Monoxide (CO) - selected based on local priorities. We deployed 115 devices across Chicago, reliably collecting data for over 90% of expected sensor-hours from July 2 - September 30, 2021. We further developed a calibration strategy that reduced errors by 41.2 – 98.8%, improving accuracy to levels recommended for hotspot detection (PM2.5 and 03) or education (NO2 and SO2). Through this work, we offer insights on the real-world deployment of a replicable, large-scale, end-to-end platform for hyperlocal urban environmental sensing.

1. Introduction

Over 4 billion people - more than 55% of the world's population - live in cities, and this number is expected to grow to nearly 70% by the year 2050 [58]. Although rapid urbanization has economic and other social benefits, it has also exposed more people to environmental hazards including air pollution - the largest environmental contributor to mortality [60]. Poor air quality is linked to a number of adverse health effects, including heart and lung disease, as well as asthma [19], [36], [61]. To monitor environmental pollutants, regu-lators and policymakers rely on data from regulatory equipment managed by government agencies and research institutes. How-ever, highly accurate regulatory monitors are expensive, large, and require special expertise for maintenance. As a result, regulatory networks are geographically sparse and thus unable to capture known variability that occurs at finer spatial resolution [30], [48]. For urban public health and planning applications - which require an understanding of intra-urban spatial inequities and evaluations of policies over time - there is a strong need to collect real-time data at finer spatial resolutions.