Microsoft’s Role in the AI Map Tool for Climate Protection

Microsoft is investing in an ambitious project that’s using AI to hunt down wetlands hiding in plain sight. 

Its AI for Good Lab is handing funding to TealWaters, a research outfit that’s building smart mapping tools to find these vanishing ecosystems before they’re lost forever.

This project has urgency behind it – as wetlands have been disappearing at an alarming rate – with 21% wiped out over the past three centuries, according to a 2023 Nature study. 

The culprits are urban sprawl and agriculture, which have long treated wetlands as inconvenient soggy patches ripe for draining.

The problem is that many wetlands are surprisingly good at hiding. 

Traditional aerial maps struggle to spot them, especially when they’re tucked under dense forest canopy. 

Those grainy black-and-white photos that mapping agencies have relied on for decades are now inadequate for the job.

“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,” says Meghan Halabisky, TealWaters’ Chief Scientist and a remote sensing expert at the University of Washington.

Microsoft’s role in the wetland hunt

Enter TealWaters’ solution: the Wetland Intrinsic Potential tool. 

This is a technology that acts as a sort of detective that layers clues – aerial photos, elevation data, water flow patterns – then uses machine learning (ML) to spot the telltale signs of wetlands that human eyes might miss.

Microsoft’s Azure cloud platform crunches the numbers, while the team is experimenting with computer vision and neural networks that can recognise wetland patterns faster than ever before. 

The tool doesn’t just find wetlands; it estimates how much carbon they’re storing, tracks how they’re changing and even pinpoints where wetlands used to exist before they vanished.

“Increasingly, we understand how vital wetlands are to a healthy planet,” says Juan Lavista Ferres, Microsoft’s Chief Data Scientist who runs the AI for Good 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.”

The real-world applications are already taking shape. 

The Tulalip Tribes in Washington state are using the technology to map wetlands across their ancestral lands, helping restore areas that support everything from huckleberries to salmon runs.

Steve Hinton, a conservation scientist with the tribe, says: “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.”

He adds that “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.”

Why Washington is becoming an AI testing ground

The team has picked Washington state as its testing ground – which is a smart choice since the region’s got everything from rainforests to grasslands – making it perfect for stress-testing algorithms that will eventually work globally.

They’re creating Washington’s first proper high-resolution wetland map, focusing particularly on carbon-rich peatlands and forested wetlands that are notoriously difficult to spot from above.

But it’s not just tribes benefiting. Small cities without wetland experts on staff are finding the tool invaluable for planning decisions. 

No more expensive consultant fees just to figure out where wetlands are and how they should be protected.

“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,” explains Maureen Ryan, who leads TealWaters’ multidisciplinary team.

The collaboration stretches across continents, bringing together researchers from the University of Washington and TerrainWorks, a California geospatial firm. 

Microsoft is sweetening the deal with access to its Planetary Computer platform, which houses massive environmental datasets.

“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,” Meghan says.

Mark Newell, TealWaters Business Development Lead, says: “When you drain a wetland, we often don’t realise what we lost, because the land kind of looks the same and feels more ‘useful’. 

“But wetlands are a giant battery for all this habitat, carbon, water and cooling.”