Assessing the performance and accuracy of invasive plant habitat suitability models in detecting new observations in Wisconsin
Open Access
- 6 September 2021
- journal article
- research article
- Published by Cambridge University Press (CUP) in Invasive Plant Science and Management
- Vol. 14 (4), 214-222
- https://doi.org/10.1017/inp.2021.27
Abstract
Land managers require tools that improve understanding of suitable habitat for invasive plants and be incorporated into survey efforts to improve efficiency. Habitat suitability models contain attributes that can meet these requirements, but it is not known how well they perform as they are rarely field tested for accuracy. We developed ensemble habitat suitability models in the state of Wisconsin for 15 species using five algorithms (boosted regression trees, generalized linear models, multivariate regression splines, MaxEnt, and random forests), evaluated performance, determined variables that drive suitability, and tested accuracy. All models had good model performance during the development phase (AUC>0.7 and TSS>0.4). While variable importance and directionality was species specific, the most important predictor variables across all of the species’ models were mean winter minimum temperatures, total summer precipitation and tree canopy cover. Post model development we obtained 5,005 new occurrence records from community science observations for all 15 focal species to test the models’ abilities to accurately predict results. Using a correct classification rate of 80%, just 8 of the 15 species correctly predicted suitable habitat (α≤0.05). Exploratory analyses found the number of reporters of these new data and the total number of new occurrences reported per species contributed to increasing correct classification. Results suggest that while some models perform well on evaluation metrics, relying on these metrics alone is not sufficient and can lead to errors when utilized for surveying. We recommend any model should be tested for accuracy in the field prior to use to avoid this potential issue.Keywords
This publication has 45 references indexed in Scilit:
- Biological invaders are threats to human health: an overviewEthology Ecology & Evolution, 2013
- VisTrails SAHM: visualization and workflow management for species habitat modelingEcography, 2013
- Developing cost-effective early detection networks for regional invasionsBiological Invasions, 2012
- Comparison of Transect-Based Standard and Adaptive Sampling Methods for Invasive Plant SpeciesInvasive Plant Science and Management, 2012
- Aquatic Invasive Species Transport via Trailered Boats: What is Being Moved, Who is Moving it, and What Can Be DoneFisheries, 2010
- Controlling invasive species in complex social landscapesFrontiers in Ecology and the Environment, 2009
- Land Manager and Researcher Perspectives on Invasive Plant Research Needs in the Midwestern United StatesInvasive Plant Science and Management, 2009
- Modelling invasion for a habitat generalist and a specialist plant speciesDiversity and Distributions, 2008
- AUC: a misleading measure of the performance of predictive distribution modelsGlobal Ecology and Biogeography, 2007
- Mechanisms underlying the impacts of exotic plant invasionsProceedings. Biological sciences, 2003