Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models
- 1Department of Plant and Microbial Biology University of Minnesota St. Paul Minnesota USA
- 2Center for Geospatial Analytics North Carolina State University Raleigh North Carolina USA
Abstract
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 km2 in 2000–2002 to 7156 km2 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.
Related
- The invasion of Solenopsis invicta in Italy: wider distribution, penetration into natural habitats, and the surrounding ant fauna
- Temporal changes in genetic variation during the invasion of Lygodium japonicum in North America
- Tracking two decades of global dengue virus lineage dynamics
- Equid population dynamics in Mexico over five decades: Divergence between national census records and FAOSTAT estimates
- Impact of oxygen fluctuation and consumption on the dynamics of a reduced go-or-grow model for tumor cell invasion
BibTeX
@article{lake2026decades,
title = {{Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models}},
author = {Thomas A. Lake and Ryan D. Briscoe Runquist and David A. Moeller},
journal = {Ecological Applications},
year = {2026},
month = nov,
doi = {10.1002/eap.70331},
url = {https://doi.org/10.1002/eap.70331},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Two decades of Landsat images reveal spatial and temporal dynamics of invasion and improve species distribution models
AU - Thomas A. Lake
AU - Ryan D. Briscoe Runquist
AU - David A. Moeller
PY - 2026
DA - 2026/11/04
JO - Ecological Applications
DO - 10.1002/eap.70331
UR - https://doi.org/10.1002/eap.70331
AB - 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 km2 in 2000–2002 to 7156 km2 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.
SN - 1051-0761
ER -