Software developed at the University of Massachusetts Amherst is enabling scientists and water managers to have information on both the quantity and quality of water flowing through rivers across the globe. The open-source software framework, Confluence, transforms satellite data into usable estimates of river discharge and suspended sediment for all rivers wider than 50 meters.
The platform is the first to combine river flow volume and sediment estimates in a single, freely available system, supporting applications ranging from drought and flood prediction to water resource management, infrastructure planning and environmental monitoring.
Producing global river discharge data has been successfully achieved through the inaugural run of Confluence
“From a societal standpoint, it’s important to know how much water’s in the river, but really, total river knowledge comes from knowing both its quantity and quality,” said Colin Gleason, Armstrong Professor of civil and environmental engineering at UMass Amherst and the project’s lead investigator.
Confluence leverages data from three satellite missions: Surface Water and Ocean Topography (SWOT), a $1.2 billion satellite mission launched by NASA and France’s Centre National d'Études Spatiales (CNES), which measures river discharge, along with LANDSAT and Sentinel-2, which provide imagery used to estimate suspended sediment. NASA recently announced that producing global river discharge data—a key mission requirement—has been successfully achieved through the inaugural run of Confluence.
“We don’t have all the water quality pieces we might want in Confluence, but it is unique in that it’s observationally driven software that is producing both estimates of river quantity and quality at the same time globally—and that’s never been done,” Gleason said.
A major advance behind the platform is its use of artificial intelligence and computer vision to analyse satellite images. Where previous sediment models relied on external data inputs, such as elevation maps, heavily influenced by factors like cloud cover and surrounding terrain, “the current algorithm doesn’t need any of that,” said Subhransu Maji, a professor involved in the project. “This allows us to isolate the pixels where sediment concentration can be reliably estimated.”
According to Gleason, “These are independent observations that we make from space. Confluence is unencumbered by what you think the river should be.”
With NASA now running Confluence regularly, the data are accessible worldwide. “Everyone with a computer can access these river data and understand all global rivers regardless of access to ground-based data,” Gleason said.
