Keeping water on the radar: Machine learning to aid in essential water cycle measurement – CU Boulder Today

Department of Computer Science assistant professor Chris Heckman and CIRES research hydrologist Toby Minear have been awarded a Grand Challenge Research & Innovation Seed Grant to create an instrument that could revolutionize our understanding of the amount of water in our rivers, lakes, wetlands and coastal areas by greatly increasing the places where we measure it.

The new low-cost instrument would use radar and machine learning to quickly and safely measure water levels in a variety of scenarios.

This work could prove vital as the USDA recently proclaimed the entire state of Colorado to be a "primary natural disaster area" due to an ongoing drought that has made the American West potentially the driest it has been in over a millennium. Other climate records across the globe also continue to be broken, year after year. Our understanding of the changing water cycle has never been more essential at a local, national and global level.

A fundamental part to developing this understanding is knowing changes in the surface height of bodies of water. Currently, measuring changing water surface levels involves high-cost sensors that are easily damaged by floods, difficult to install and time consuming to maintain.

"One of the big issues is that we have limited locations where we take measurements of surface water heights," Minear said.

Heckman and Minear are aiming to change this by building a low-cost instrument that doesn't need to be in a body of water to read its average water surface level. It can instead be placed several meters away safely elevated from floods.

The instrument, roughly the size of two credit-cards stacked on one another, relies on high-frequency radio waves, often referred to as "millimeter wave", which have only been made commercially accessible in the last decade.

Through radar, these short waves can be used to measure the distance between the sensor and the surface of a body of water with great specificity. As the water's surface level increases or decreases over time, the distance between the sensor and the water's surface level changes.

The instrument's small form-factor and potential off-the-shelf usability separate it from previous efforts to identify water through radar.

It also streamlines data transmitted over often limited and expensive cellular and satellite networks, lowering the cost.

In addition, the instrument will use machine learning to determine whether a change in measurements could be a temporary outlier, like a bird swimming by, and whether or not a surface is liquid water.

Machine learning is a form of data analysis that seeks to identify patterns from data to make decisions with little human intervention.

While traditionally radar has been used to detect solid objects, liquids require different considerations to avoid being misidentified. Heckman believes that traditional ways of processing radar may not be enough to measure liquid surfaces at such close proximity.

"We're considering moving further up the radar processing chain and reconsidering how some of these algorithms have been developed in light of new techniques in this kind of signal processing," Heckman said.

In addition to possible fundamental shifts in radar processing, the project could empower communities of citizen scientists, according to Minear.

"Right now, many of the systems that we use need an expert installer. Our idea is to internalize some of those expert decisions, which takes out a lot of the cost and makes this instrument more friendly to a citizen science approach," he said.

By lowering the barrier of entry to water surface level measurement through low-cost devices with smaller data requirements, the researchers broaden opportunities for communities, even in areas with limited cellular networks, to measure their own water sources.

The team is also committing to open-source principles to ensure that anyone can use and build on the technology, allowing for new innovations to happen more quickly and democratically.

Minear, who is a Science Team and Cal/Val Team member for the upcoming NASA Surface Water and Ocean Topography (SWOT) Mission, also hopes that the new instrument could help check the accuracy of water surface level measurements made by satellites.

These sensors could also give local, regional and national communities more insight into their water usage and supply over time and could be used to help make evidence-informed policy decisions about water rights and usage.

"I'm very excited about the opportunities that are presented by getting data in places that we don't currently get it. I anticipate that this could give us better insight into what is happening with our water sources, even in our backyard," said Heckman.

See the original post here:
Keeping water on the radar: Machine learning to aid in essential water cycle measurement - CU Boulder Today