Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models
Ecological Applications · 2026-10 · 36 (7)
DOI: 10.1002/eap.70331 ↗At a glance
Journal article in Ecological Applications, published online on 2026-11-04. Written by Thomas A Lake and 2 co-authors. Institution: Department of Plant and Microbial Biology, University of Minnesota, St. Paul, Minnesota, USA. Major MEDLINE topics: Introduced Species, Satellite Imagery, Models, Biological, Environmental Monitoring. 96 references. The full text is freely available (open access, CC BY 4.0). Funded by: Legislative-Citizen Commission on Minnesota Resources, National Institute of Food and Agriculture, Minnesota Invasive Terrestrial Plants and Pests Center.
Abstract (original language)
Developing accurate and cost‐effective methods to detect and predict the spread of invasive species remains an ongoing challenge. Species distribution models (SDMs) are widely used to predict invasion under current and future climates and inform management strategies. However, occurrence datasets are often spatially and temporally biased due to unstructured and opportunistic data collection. Remote sensing of individual species over broad spatial and temporal scales has become increasingly feasible with the accumulation of satellite images and the development of convolutional neural networks. In this study, we used 21 years of archival Landsat satellite imagery (2000–2020) to train a land use/land cover (LULC) classification algorithm using a temporal convolutional neural network to predict occurrence of the invasive species, leafy spurge ( Euphorbia virgata ), across Minnesota. We validated our predictions with an independent dataset. First, we show that leafy spurge has expanded from 1067 km 2 in 2000–2002 to 7156 km 2 in 2018–2020, a 570% increase. Drought severity modulated the predicted area invaded and was associated with fluctuations over time. Second, we tracked changes in probability over time for individual pixels and showed that invasion has been concentrated in two largely disjunct regions that differ in climate. Third, our remotely sensed predicted occurrence dataset and community science dataset were closer to roadsides, suggesting that roadside disturbance facilitates invasion. Last, we showed that SDMs built using remotely sensed occurrences had higher discrimination, were less overfit, and performed better outside of urban areas. Overall, 21 years of archival satellite imagery showed rapid expansion in two geographically distinct regions, invasion associated with roads, and improved predictions of invasion.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Plant and Microbial Biology, University of Minnesota, St. Paul, Minnesota, USA.
- Center for Geospatial Analytics, North Carolina State University, Raleigh, North Carolina, USA.
ORCID profiles: Thomas A Lake, Ryan D Briscoe Runquist, David A Moeller
Funding
- Legislative-Citizen Commission on Minnesota Resources
- National Institute of Food and Agriculture
- Minnesota Invasive Terrestrial Plants and Pests Center
- Environment and Natural Resources Trust Fund
- Graduate School, University of Minnesota (Doctoral Dissertation Fellowship)
- Minnesota Invasive Terrestrial Plants and Pests Center, University of Minnesota
- Minnesota Environment and Natural Resources Trust Fund
Cite
APA
Lake, T. A., Briscoe Runquist, R. D., & Moeller, D. A. (2026). Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models. Ecological Applications, 36(7). https://doi.org/10.1002/eap.70331
Vancouver
Lake TA, Briscoe Runquist RD, Moeller DA. Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models. Ecological Applications. 2026;36(7). doi:10.1002/eap.70331
BibTeX
@article{Lake2026,
author = {Lake, Thomas A and Briscoe Runquist, Ryan D and Moeller, David A},
title = {Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models},
journal = {Ecological Applications},
year = {2026},
volume = {36},
number = {7},
doi = {10.1002/eap.70331}
}
EUVIMED