Kansas State University scientists are enlisting the help of artificial intelligence in the effort to conserve what’s left of North America’s shrinking grasslands.

Zak Ratajczak, an assistant professor and grassland biologist, says K-State scientists have trained a computer model to map in detail different kinds of woody vegetation affecting prairies, such as the aggressively spreading evergreens called eastern red cedars.

“You have to give it lots of samples,” Ratajczak said. “Then it figures out what the general characteristics are of eastern red cedar based on height and how it absorbs and reflects different types of light back to the camera.”

The K-State team uses high-resolution imagery and data captured by airplanes and feeds it into the model, which can distinguish between deciduous trees, shrubs and eastern red cedars.

They used open-source machine learning and publicly available aerial data. Ratajczak and graduate student Brynn Noble laid out the project in the July issue of the journal Remote Sensing.

The U.S. Department of Agriculture and the National Science Foundation use planes to gather detailed data that they then make available for free to the public.

The National Science Foundation plane has camera equipment that takes in 1,000 wavelengths of light. It also sweeps the grassland at the Konza Prairie Biological Station with lasers in thousands of frequencies that bounce off the ground and return to the plane’s sensor. This allows K-State to build a three-dimensional map of the vegetation.

The Konza station is an 8,600-acre tallgrass property near Manhattan used for long-term research.

“ We visited the (National Science Foundation) plane that gathers the data and it’s really impressive,” Ratajczak said. “They do a lot of the hard steps and then we get all this data for free.”

K-State scientists built their model using the free coding language R, frequently used by scientists for data analysis. They trained it by giving it many aerial images of each type of vegetation.

The scientists then had the model try to identify further images on its own, and they double-checked whether the model was interpreting the images correctly. The model gave the right answer more than 97% of the time.

The K-State team has focused so far on the Konza property. But it hopes to expand the work — mapping out the prevalence of deciduous trees, eastern red cedars and shrubs across the Flint Hills tallgrass region.

This would help them see the full extent of the problem.

For decades, woody plants have been spreading across the Great Plains, to the point that they are transforming grassland into woodland and shrubland. Scientists in Oklahoma have dubbed the phenomenon the Green Glacier.

Common invaders in the Flint Hills include eastern red cedars, wild plum, roughleaf dogwood and smooth sumac. (These last three are shrubs or thickets.)

The Green Glacier is fueled by a host of human changes to the Great Plains since European colonization of North America.

A few examples include planting millions of trees in grasslands since that time and severely reducing the application of fire that Native Americans had long used to support grasslands.

Additionally, the realities of modern-day landownership pose a challenge. The continent’s remaining grasslands are divided among many different landowners with varying priorities for how to use the land and varying capacities for maintaining it.

Another key change is the increase of carbon dioxide in the atmosphere since the Industrial Revolution. This helps woody plants grow faster on prairies, shading out grasses around them and surviving prescribed burns.

Mapping woody plants in great detail could help pinpoint how much forage for cattle and bison is lost each year to this transformation.

Already, scientists have estimated that the Flint Hills would grow about a billion more pounds of grass annually if not for trees and shrubs overtaking so much space.

K-State’s use of machine learning could also help researchers better track the relationship between this habitat transformation and declining grassland bird species, such as grasshopper sparrows and eastern meadowlarks.

Those species disappear from areas of grassland once low levels of shrubs and trees have invaded.

Eventually, K-State scientists hope that their advancements in mapping out woody plants with AI will help conserve swaths of grassland currently free of woody plants but likely to face that threat in coming years.

“One of the things we are thinking about using this for is early detection and intervention,” he said.

Nearly one-third of North America was once grassland. More than half of it disappeared for development such as row crops, cities and suburbs. And for tallgrass prairie — the kind of grassland in the Flint Hills — the statistics are even worse. Scientists estimate that less than 5% of the continent’s tallgrass remains.

The Flint Hills is the biggest remaining stretch of tallgrass prairie. That’s another reason for the urgency to deal with shrubs and trees there.

Some parts of the Flint Hills are already awash in these plants, but other areas still have a chance to proactively hold the hardest-to-control woody species at bay.

“ If you can catch encroachment (the spread of woody plants) when it’s in the early stages,” Ratajczak said, “it’s potentially easier to either halt or reverse using prescribed fire.”

It was 1874 when a large influx of Russian immigrants settled in Kansas bringing with them a hard red variety of wheat.

This wheat variety grew well in the harsh summers and dry winters.

Hard red winter wheat swallowed the Plains, and when you drive across Kansas in June you see it turn the land gold. Kansas has even been known in the past as the “breadbasket of the world.”

Today, Kansas embraces its wheat identity, and still is one of the top wheat producing states. But wheat acres have continued to trend downward, falling away to other crops like corn and sorghum.

For over a century, wheat hasn’t changed too much from when it first took over. Other crops have been improved and hybridized. But scientists now think hybrid varieties will create a new wheat era.

Agronomist Logan Simon wipes his brow with a cloth as he walks through test plots used to experiment with corn, cotton and wheat just outside Garden City.

The success of Kansas agriculture relies on research like this.

“It gives us some greater optimism as we move into a potentially drier future,” Simon said.

Hybrid varieties can bring better bread to your stores, healthy livestock that you eat and biofuels for your cars. And it is becoming increasingly crucial as climate change produces challenging environments for Kansas farmers.

These hybrids usually take good traits from different varieties of a crop and combine them to make a plant that’s healthier, hardier or produces more, even in harsh environments.

But it hasn’t been so easy with wheat. Scientists have racked their brains trying to make better wheat hybrids. The plant’s physiology makes hybridizing wheat difficult.

Katherine Frels has worked for years in wheat breeding at the University of Nebraska. She said people witness the scientific success of agriculture without even realizing it.

“Whatever crop they’re looking at as they go to church, go to the grocery store. Someone had to develop that variety,” Frels said.

Farmers have had innovations in corn hybrids since the 1930s. Soybeans followed shortly in the 1940s. Since corn was hybridized, farmers’ yields have increased about 700%, going from 26 bushels per acre to 183 bushels.

But even with the advent of fertilizers and pesticides, wheat has barely doubled its yields in that same time.

With corn, to make hybrids simply cut off the tassel at the top which produces pollen and plant it with another variety to cross the two.

The problem is wheat pollinates itself, which has made creating hybrid varieties nearly impossible.

Frels has worked on a lot of potential solutions, like chemically sterilizing the plant. She said from their research, out of 1700 wheat hybrid variety trials, there is a yield increase on average.

Universities aren’t alone. Seed companies are also diving in as well, studying how to make enough hybrid wheat seeds so it’s consistently available.

Corteva is a global agriculture company that has recently announced a breakthrough with their wheat hybrids.

Jessie Alt is the lead wheat breeder at Corteva. Hybrids have consumed most of her career, and it’s been a challenge.

Back in 2018, after decades of research, scientists mapped out the genome of wheat. That allows people like Alt to find ways to stop wheat from pollinating itself and breed it to make unique hybrids.

“It has been the most exciting thing of my career,” Alt said. “Like, we can do this.”

Alt said combining different field tools such as drones and understanding genetics have allowed for more hybrid innovations on a larger scale.

What this breakthrough means for Kansas farmers is potentially 20% higher yields in water stressed environments, which will be critical as the Ogallala Aquifer runs dry and farmers switch to non-irrigated crops once their water pumps fail.

It will also help farmers transition more smoothly to limited irrigation, while still producing a profitable crop.

Wheat hybrids could use less water, fertilizer or herbicides, and result in a product with more fiber and protein.

But farmers will need to be able to see and feel the crop if they are going to take a chance on it.

“Kick the tires, if you will,” said Jason Gaeddert, a farmer from Buhler, Kansas.

Corteva used Kansas for 70% of their test plots, one of them being on Gaeddert’s land. He said that the hybrid wheat has looked good, and even produced higher yields. He wants to see how much better that wheat will handle dry times when the rains don’t come.

“If it can handle that stress better, then you’re going to clearly get a better yield or better quality product. Then, that becomes more profitable,” Gaeddert said.

Corteva hopes to roll out hybrid wheat on the markets in 2027. But there is a problem with wheat hybrids on the horizon. They will be pretty pricey, and in order to change agriculture, farmers have to actually use the seed.

Farmers are able to salvage wheat seed from harvest, saving some money the next planting season.

With hybrids, the seed won’t be reusable because the offspring won’t be the same as the parents. Can the hybrids make farmers enough money to justify the increased cost?

Gaeddert said he will gladly spend more money to make more money. Other farmers might feel the same.

Mike Krieghauser is an agronomist for Pioneer, a seed brand of Corteva. He works with farmers in northwest Kansas.

Despite the financial challenges for farmers, Krieghauser is optimistic they’ll adopt hybrid wheat.

“I mean, it’s wheat. It should be the easiest adopting hybrid thing that we’ve ever done in the history of agriculture,” he said.

Calen Moore covers western Kansas for High Plains Public Radio and the Kansas News Service. You can email him at [email protected].

The Kansas News Service is a collaboration of KCUR, Kansas Public Radio, KMUW and High Plains Public Radio focused on health, the social determinants of health and their connection to public policy.