While plastic is convenient, durable, and cheap, 50% of all plastics (about 150 million tons every year, worldwide) are used only once and then thrown away. Even for those who dutifully recycle our plastic water bottles and sandwich bags, we’re only tackling a small part of the problem. That’s because heavy winds and rain carry huge amounts of plastic waste along city streets and into the stormwater system, where it likely flows directly into creeks, rivers, bays, and eventually the ocean, with no treatment to filter out plastics.
“Considering the size of the problem, there’s relatively limited infrastructure in place to capture and treat stormwater,” says Tony Hale, program director for environmental informatics at the nonprofit San Francisco Estuary Institute (SFEI).
That’s where SFEI is looking to use research and data—and most recently, drones—to make a difference. In addition to sending out crews of people on foot to count and collect trash in local waterways, SFEI began using camera-equipped drones to assess that waste on a much larger scale.
The drone research is part of a new project by SFEI and its sister organization Southern California Coastal Water Research Project, through funding from the Ocean Protection Council, to validate trash-monitoring methods, and produce a trash-monitoring playbook that community cleanup groups, municipal programs, environmental agencies, and ecologists can learn from and put to use. The effort studies initiatives such as plastic bag bans to urban rain gardens.
“Our mission is to help city planners find the best ways to filter their stormwater and stop contaminants such as trash and plastics from entering their protected wetlands and public waterways,” Hale says.
By sending drones over the San Francisco Bay and neighboring tributaries, SFEI collected some 35,000 images in its initial foray. The reality of crunching so much data in a reasonable amount of time was sobering: “It took us almost a month to process these images.”
Initially, Kinetica ran SFEI’s deployment from a distributed CPU framework, on its own 4-core machine, using managed Kubernetes. “It took us about 10 days to run the entire simulation,” says Nick Alonso, a solution engineer at Kinetica who works on the SFEI project. Even after moving the application to a server using a single GPU—processors that are well suited to machine learning work—the simulation still took the better part of a week.
Kinetica then decided to run SFEI’s entire workload on Oracle Cloud Infrastructure, using eight V100 GPUs. “We’re no longer talking about days to run this simulation,” Alonso says. “We’re doing it in hours—about 18 hours and 26 minutes, to be exact.”