EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prioritizing removals of a highly cryptic invasive species using machine learning and demographic weighting

Alexander S Romer iD, Melissa A Miller iD, Sergio A Balaguera-Reina iD, Michelle C Bassis, Brandon Welty, Michael Kirkland, Amy Peters, Edward F Metzger, Jenna Cole, LeRoy Rodgers, Frank J Mazzotti

Ecological Applications · 2026

DOI: 10.1002/eap.70317 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ecological Applications, 2026. Verfasst von Alexander S Romer und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Wildlife Ecology and Conservation, Fort Lauderdale Research and Education Center, University of Florida, Davie, Florida, USA. Hauptthemen laut MEDLINE: Introduced Species, Machine Learning, Boidae, Conservation of Natural Resources. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 100 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: South Florida Water Management District (SFWMD).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Invasive species present substantial challenges to biodiversity conservation, particularly when low detectability and demographic heterogeneity obscure the population‐level consequences of management actions. Invasive Burmese pythons ( Python bivittatus ) in South Florida exemplify this challenge, as metrics based on raw removals or body size alone may not reflect demographic impacts. To address this, we introduce the Weighted Removal Index (WRI), a demographic weighting framework that prioritizes removals based on expected contributions to survival and reproduction. Using survey data from the South Florida Water Management District's Python Elimination Program, we quantified operational and environmental conditions associated with higher survey WRI, defined as the summed WRI of all pythons captured on a single survey, and evaluated three forecasting approaches: Generalized Additive Models (GAMs), Boosted Regression Trees (BRT), and Neural Networks (NN). Survey WRI was highest under waning lunar phases, when surveys were assisted, and under warmer and more humid conditions. Additionally, survey WRI was elevated on warm days early in the wet season and cool dry‐season days. In held‐out test evaluation, the NN achieved the highest balanced accuracy for predicting survey success (0.703), and the lowest error for predicting survey WRI (root mean squared error [RMSE] = 5.50). Contractor performance was highly heterogeneous, with contractor‐specific effects positively associated with mean survey WRI ( R 2 = 0.589) and capture rate ( R 2 = 0.596). Notably, model‐based predictions of survey success fell within the upper tail of the contractor capture‐rate distribution, indicating that near‐term forecasting can match the performance of the highest performing contractors. Together, demographic weighting and near‐term forecasting provide a practical decision‐support framework for guiding effort toward high‐impact removals in cryptic invader management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Introduced SpeciesMachine LearningBoidaeConservation of Natural ResourcesAnimalsFloridaModels, BiologicalPredictive Learning ModelsDemography

Stichwörter der Autor:innen

Burmese pythonartificial intelligenceboosted regression treescontractor performanceecological modelingeverglades ecosystemgeneralized additive modelsinvasion ecologypredictive analyticsreproductive weightingreptile demographysurvivorship curve

Autor:innen und Institutionen

  • Department of Wildlife Ecology and Conservation, Fort Lauderdale Research and Education Center, University of Florida, Davie, Florida, USA.
  • South Florida Water Management District, West Palm Beach, Florida, USA.

ORCID-Profile: Alexander S Romer, Melissa A Miller, Sergio A Balaguera-Reina

Förderung

  • South Florida Water Management District (SFWMD)

Zitieren

APA

Romer, A. S., Miller, M. A., Balaguera-Reina, S. A., Bassis, M. C., Welty, B., Kirkland, M., Peters, A., Metzger, E. F., Cole, J., Rodgers, L., & Mazzotti, F. J. (2026). Prioritizing removals of a highly cryptic invasive species using machine learning and demographic weighting. Ecological Applications. https://doi.org/10.1002/eap.70317

Vancouver

Romer AS, Miller MA, Balaguera-Reina SA, Bassis MC, Welty B, Kirkland M, et al. Prioritizing removals of a highly cryptic invasive species using machine learning and demographic weighting. Ecological Applications. 2026. doi:10.1002/eap.70317

BibTeX
@article{Romer2026,
  author = {Romer, Alexander S and Miller, Melissa A and Balaguera-Reina, Sergio A and Bassis, Michelle C and Welty, Brandon and Kirkland, Michael and Peters, Amy and Metzger, Edward F and Cole, Jenna and Rodgers, LeRoy and Mazzotti, Frank J},
  title = {Prioritizing removals of a highly cryptic invasive species using machine learning and demographic weighting},
  journal = {Ecological Applications},
  year = {2026},
  doi = {10.1002/eap.70317}
}
Kostenlos starten →