Show-Me State Times

A research team at the University of Missouri has developed a cost-effective method to track the spread of invasive Callery pear trees in mid-Missouri. The approach uses freely available satellite imagery and machine learning to identify and map these trees, offering an alternative to more expensive tracking methods such as drones or aircraft.

Callery pear trees have been spreading rapidly across the Midwest and Eastern United States, causing ecological harm by outcompeting native species and posing risks due to their tendency to break during storms. Their spread has prompted several states, including Missouri, to ban their sale.

Justin Krohn, a research project analyst and graduate student at the University of Missouri, became interested in this issue after noticing the trees encroaching on Mark Twain National Forest. Krohn used a GPS device to record the locations of Callery pear trees around Columbia, Missouri. He then trained a machine learning model on satellite images to distinguish these trees from others based on how they reflect light.

Krohn’s findings indicate that suburban areas with more open land contain higher numbers of Callery pear trees compared to denser urban areas where there is less space for them to grow.

“These trees like moving into disturbed areas, such as near new housing developments and alongside roads,” Krohn said. “As Columbia continues to grow, we may be able to use the trends we noticed to better predict where these trees are likely to spread. If the areas where they might spread are treated proactively — whether that’s roadside clearings or growing native plants — that may help stop these invasive trees from taking over, better protecting our ecosystem.”

The research suggests that this method could be adapted for tracking other invasive species or even monitoring disease outbreaks in trees.

“My long-term goal is to have an online interface where people can download either the models themselves or the code behind them so they can apply it to different invasive species in different regions of the world,” Krohn said. “I want to help those focused on plant management and invasive species to be able to benefit from this technology without having to spend a lot of money on imagery.”

The project involves collaboration between multiple entities at Mizzou: the Center for Applied Research and Engagement Systems; MU Extension; the U.S. Forest Service; and the MU Institute for Data Science and Informatics. This work supports Mizzou’s mission as a land-grant institution dedicated to serving Missouri through environmental protection efforts.

“There is a lot of potential for this technology to be used to ultimately protect the environment, and it feels great to be doing this work at Mizzou,” Krohn said. “Making things cheaper and more accessible ultimately helps more people benefit from research, not just those who are AI experts.”

The study was published in Remote Sensing under the title “Detecting the distribution of Callery pear (Pyrus calleryana) in an urban U.S. landscape using high spatial resolution satellite imagery and machine learning.”