Plate Nº 97 · recorded November 16, 2026

Biology & EvolutionReported finding

Satellite AI Tracks Leafy Spurge's 570% Surge Across Minnesota

Leafy spurge surged 570% in Minnesota over two decades. University of Minnesota researchers used AI and NASA-assisted Landsat imagery to track it from orbit and predict where it invades next.

By Elena Vasquez3 min read646 words

In brief

  1. Leafy spurge abundance in Minnesota increased 570% between 2000 and 2021.
  2. The weed caused roughly $1 billion in losses to farmers and ranchers from 1960 to 2000.
  3. Researchers trained a deep-learning model on iNaturalist observations and 20 years of Landsat satellite imagery.
  4. The biggest abundance increases clustered around Fargo-Moorhead and Minneapolis-Saint Paul.
  5. Findings appear in Ecological Applications (2026), DOI: 10.1002/eap.70331.
From 400 miles above Earth, AI tracks invasive leafy spurge
Plate Nº 97From 400 miles above Earth, AI tracks invasive leafy spurge — 5827444 / pixabay

Leafy spurge abundance in Minnesota jumped 570% between 2000 and 2021, and researchers at the University of Minnesota tracked every step of that surge from 400 miles above Earth. Their deep-learning model, described in the journal Ecological Applications, pairs two decades of satellite imagery with citizen-submitted plant observations, and it can now predict where the noxious weed will invade next.

The stakes are economic, not just ecological. Leafy spurge, accidentally introduced from Europe in the late 19th century, secretes a sap toxic to livestock when damaged. Dense patches can stretch for acres. From 1960 to 2000, the plant caused roughly $1 billion in losses for farmers and ranchers.

How did the researchers do it?

The team, based in the Department of Plant and Microbial Biology in the College of Biological Sciences, trained a predictive deep-learning model — a type of artificial intelligence that learns patterns from large datasets — on real observations of leafy spurge. Those observations included sightings submitted through iNaturalist, a community science app where the public logs photos of plants and animals.

The model then fused that ground-truth data with open-source Landsat imagery supplied by the U.S. Geological Survey, with help from NASA satellites. Across the full 20-year window, the researchers could track the plant accurately.

The weed itself made the work easier. "When leafy spurge flowers, it's like someone took a yellow highlighter to the landscape," said Thomas Lake, a University of Minnesota Ph.D. graduate and now a postdoctoral researcher at the Center for Geospatial Analytics at North Carolina State University. "It's so bright yellow, satellites can see it too."

What did the study find?

The findings, published in Ecological Applications, point to concrete patterns in the invasion:

  • Leafy spurge abundance rose 570% over two decades, from 2000 to 2021.
  • While climate shapes many plant ranges, the biggest abundance changes clustered around Fargo-Moorhead and Minneapolis-Saint Paul.
  • The plant often appears near roadways, suggesting proactive roadway management could slow its spread.
  • During intense drought, leafy spurge produced fewer flowers, making it harder to detect — a limitation managers should account for.
  • Detecting newly invaded areas from satellite imagery improved forecasts of future invasion, information that can guide state and federal agencies.

The road finding is actionable. If spurge hitches rides along transportation corridors, targeted management along roadsides could choke off new fronts. Simple takeaway: where the weed travels, pavement leads.

Why does satellite tracking matter?

Traditional monitoring depends on people noticing and reporting plants on the ground, which leaves blind spots. Satellites don't blink.

"Tracking invasive species from satellites vastly improves our capacity to dynamically monitor invasive spread and prioritize limited resources for management," said David Moeller, a professor in the College of Biological Sciences. "Remote sensing significantly reduces bias by allowing detection in areas where observers often miss."

That bias reduction matters for agencies working with limited budgets. Instead of surveying blindly, land managers can direct crews to locations the model flags as newly invaded or at high risk.

"Having a fuller picture of how plants invaded and where they actually occur will help us to make better predictions about where it might eventually end up," said Ryan Runquist, senior research associate in the College of Biological Sciences.

What comes next?

With Minnesota's leafy spurge documented, the team plans to map the plant across a seven-state area. They also intend to study how climate change, insects and rapid plant evolution affect the species.

The method itself travels. In the future, the researchers plan to apply the same satellite-and-AI approach to detect the spread of other invasive species. Farmers, ranchers and state agencies — the groups absorbing the economic damage — stand to benefit first.

The bottom line: a toxic weed that once spread unseen now broadcasts its location from orbit, and the forecasts built on that data are getting sharper.

via phys.org/rss-feed/ (Source)

Filed under

  • leafy-spurge
  • invasive-species
  • satellite-imagery
  • remote-sensing
  • artificial-intelligence
Share this article:

More from Elena Vasquez

Elena Vasquez

Show full bio

Correspondent covering money, funding and market shifts around general science news at SciBeat.

455 articles

Nearby plates

« Previous articleNext article »