UF Study Uses Machine Learning to Find the Most Prolific Burmese Pythons

University of Florida researchers use machine learning to identify the most prolific pythons for removal from the Everglades.Photo: University of Florida

University of Florida researchers using science and computers to tackle the cryptic python invasion in the Florida Everglades.

The new study prioritizes snake removals by reproductive potential.

UF scientists say targeting large reproductive females will likely have the biggest impact on controlling the population.

So, the machine learning research focuses on the age, size, sex and reproductive potential of each snake for the highest likelihood of detecting and removing the key demographic.

“Our previous work treated all Burmese pythons as contributing equally to the population but removing the biggest female we've ever caught is very different from removing a tiny snake that might not survive next year,” said Alex Romer, a quantitative ecologist with the Croc Docs Wildlife Research Team and lead author on the study at the UF/IFAS Fort Lauderdale Research and Education Center (FLREC).

That distinction is important because Burmese pythons have very different survival and reproductive capabilities at different stages of their lives. Young pythons experience high mortality, while mature pythons are more likely to survive and reproduce.

“Every Burmese python removed is a win for the Everglades, but targeting large reproductive females is likely to reduce the population most effectively,” said co-author Melissa Miller, assistant professor of invasive wildlife ecology at FLREC. “This approach is especially valuable at new invasion sites and along the invasion front, where removal efforts should have the greatest impact.”

The researchers developed the Weighted Removal Index (WRI), a demographic weighting system that assigns an ecological value to removing pythons that are more likely to survive and reproduce.