How AI can help save hidden ‘biological hotspots’ the planet needs
For the Tulalip Tribes in Washington state, the wetlands nestled in the tribe’s forests and coasts are far from humble swamps and simple ponds. They’re vital for climate resilience and biodiversity — storing carbon, absorbing floodwaters, cooling cities and filtering pollutants while sustaining important foods like huckleberries and salmon.
But wetlands around the world are disappearing to urban growth and agriculture, and the ones that remain are often hidden, making them hard to protect. To solve the problem locally, Tulalip biologists are using a new AI-powered tool to find and restore bogs, marshes and other wetlands across the tribe’s reservation and ancestral territory.
“Much of the tribe’s culture relies on its reciprocity with the land, and you have these beautiful wetlands that are biological hotspots for so many different species of plants and animals,” says Steve Hinton, a conservation scientist with the Tulalip Tribes.
“The tool helps us understand moisture on the landscape in a way that’s crucial for our cultural and environmental resilience. AI enables us to go through those mountains of information, helping us manage our lands and tell our story more effectively.”
The Tulalip Tribes is one of several partners working with TealWaters, a global research team building the tool to give communities a holistic picture of their wetlands and related water dynamics by layering aerial images with colored, digital elevation maps, landscape and hydrologic information, and on-the-ground expertise. With an award from the Microsoft AI for Good Lab, TealWaters will use Azure Machine Learning and explore other AI tools to accelerate its work.
“Increasingly, we understand how vital wetlands are to a healthy planet,” says Juan Lavista Ferres, Microsoft chief data scientist and director of the lab. “TealWaters’ work plays a critical role in shaping a sustainable future and is a great example of how AI can help us better understand rich, diverse ecosystems and help prioritize where action is most urgently needed.”
Wetlands have long been mainly viewed as soggy patches to be drained for farms, roads and buildings, leading to a 21% loss in global wetlands in the last three centuries, according to a 2023 study published in Nature. Other studies show an even higher rate of wetland loss.
But as communities and natural resource managers begin to realize the benefits of wetlands, many are finding existing wetland maps and inventories underfunded, inaccurate and out of date, says Meghan Halabisky, chief scientist for TealWaters and a remote sensing ecologist at the University of Washington (UW) in Seattle.
The black-and-white aerial images of older maps provide limited information that poorly captures the evolving interplay of water and land, Halabisky says. They often miss wetlands in places like Western Washington, where dense forests cover a lot of the ground.
“Wetlands are super important ecosystems that provide a ton of functions for communities, but we don’t know where they are, what they’re doing and how to protect them,” she says.
TealWaters’ solution, called the Wetland Intrinsic Potential tool, incorporates hidden geomorphic and hydrologic features to show information missed on other maps. The information includes hard-to-see wetlands, location of vanished wetlands, how the area is changing over time and benefits like estimated carbon storage. It can also show how wetlands connect to groundwater, lakes and other water sources.
“There are folks like the Tulalip Tribes using this tool to broadly ask how water is held across the landscape, and where wetlands can be restored to store water longer through the season or cool down streams that are salmon-bearing,” says Maureen Ryan, multidisciplinary development lead for TealWaters.
Other organizations and agencies are using the tool to study how wetlands can mitigate floods, increase green spaces, nourish wildlife and support climate goals. For small cities without a wetland ecologist, the tool has become especially helpful for providing much-needed expertise.
“One of the interesting uses coming up is can we speed up the understanding of what wetlands do and the buffer distances required for urban planning and permitting, which can be an expensive process,” Halabisky says.
In addition to using machine learning, TealWaters is exploring Microsoft AI tools for computer vision and convolutional neural networks for finding patterns in geospatial data more accurately and efficiently. It’s also looking into Microsoft’s Planetary Computer, a platform for accessing global environmental data. And it plans to incorporate data on water quality, floodwater absorption, habitats and other information.
The team is initially focused on creating a high-resolution map of wetlands in Washington and the state’s first-ever map of high-carbon wetlands, which tend to be peatlands and forested, hard-to-find wetlands. Halabisky says the diversity of local ecoregions — rainforests, mountains and grasslands, to name a few — makes Washington a “perfect test area” for developing a tool for national and global use.
“We’re working with Microsoft to see how we can improve our models with deep learning and make the tool scalable and easy to deploy for different communities,” she says.
TealWaters is integrating AI with research across many disciplines, ranging from ecology and remote sensing to environmental humanities and art. Its team spans the U.S. and Africa and brings together scientists from UW and a California-based geospatial solutions provider called TerrainWorks. Researchers hope TealWaters’ multidisciplinary approach and work with tribes, local governments and global partners can help change the conversation about wetlands and save them before it’s too late.
“When you drain a wetland, we often don’t realize what we lost, because the land kind of looks the same and feels more ‘useful,’” says Mark Newell, TealWaters business development lead. “But wetlands are a giant battery for all this habitat, carbon, water and cooling.”
Top photo: Rachel Buchler, a University of Washington student working with TealWaters, surveys a wetland in the Skykomish River watershed in Washington state. Photo by Meghan Halabisky, courtesy of TealWaters. Story published on Aug 26, 2025.