Each node in the Array of Things is equipped with an Nvidia graphics processing unit (or GPU) to perform computations on the images in the field and send only processed data to the network — a form of edge computing. As an added privacy measure, the buttons are designed for temporary installation. “I don’t want to see advanced computers all over the city, where everywhere you go there’s a camera analyzing what you’re doing,” says Catlett. “That was more confusing to me than what I wanted to see. But I think these advanced devices have room for diagnostics. You put that ability on a purpose, and then you take it out. ”
Between 2016 and 2019, the team attached 140 AoT nodes to Chicago street lights. In a participatory process, the team at Argonne and local universities worked with Chicagoans and city departments to decide where to place the sensors.
Dozens of studies have used sensor data. The nodes have been used to assess the safety of synchronous rail crossings, monitor pedestrian crossing use, and detect flooding along the Chicago River. Kathleen Cagney, a collaborator on the project who directs the Institute for Social Research at the University of Michigan, used environmental data from sensors for a public health study that found asthma rates higher where the sensor detects more air pollution.
Catlett’s team has since worked on lower-tech projects. Last year, for example, he and his colleagues collaborated with Microsoft Research installed 115 low-cost solar-powered air quality sensors on bus shelters across the city. The resulting data shows pollution hotspots near industrial corridors on the South and West Sides of Chicago in unprecedented high resolution. Environmental and community groups are now pressuring the city to change its policy. The team plans to expand to thousands of air quality nodes in the coming years.
Array of Things is also expanding beyond Chicago through a project called SAGE. Unlike other urban sensing systems, which tend to be proprietary, SAGE allows anyone to write software for its nodes, which house high-resolution hyperscale cameras, lidars, and voice recorders.
Catlett said the team is now entering the rollout phase. By the end of the year, they plan to install 50 nodes out of $10,000 in Chicago, replacing the previous generation Array of Things nodes. Dozens of them have been deployed across Southern California to detect wildfires and on towers across the country to analyze weather and climate change. The National Science Foundation wants 80, one for each tower in their National Ecological Observatory Network. Oregon wants 100 to help detect earthquakes. The Australian scientific agency CSIRO placed an order. The library of open-source applications, available on GitHub, is constantly growing and includes programs to identify birds by their songs and classify funnel clouds from images.
“The fitness tracker for the city” has been developed globally — just in time to study our changing world.
Christian Elliott is a freelance science journalist based in Chicago, Illinois.