|KAPLER, EMILY - Iowa State University|
|DIXON, PHILIP - Iowa State University|
|THOMPSON, JANETTE - Iowa State University|
Submitted to: Journal of Environmental Horticulture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/13/2011
Publication Date: 3/15/2012
Citation: Kapler, E.J., Widrlechner, M.P., Dixon, P.M., Thompson, J.R. 2012. Performance of five models to predict the naturalization of non-native woody plants in Iowa. Journal of Environmental Horticulture. 30:35-41.
Interpretive Summary: Nursery and landscape professionals introduce many new non-native plants, but sometimes these introductions escape from cultivation, naturalize, and invade. This is a concern to many stakeholders, from members of the nursery industry itself to land managers who must deal with invasive species encroaching on natural areas. As new plants continue to be introduced, there is the possibility of inadvertently ushering in new invasive plants. Given the many benefits of introducing new plants, researchers have worked to develop methods to discern potential invaders from benign introductions through risk-assessment modeling. Plants screened by these models are then recommended for acceptance, rejection, or further study based on plant attributes, such as life-history traits or geographic origin. Errors produced by risk-assessment models represent potential costs, both biologically and horticulturally. This paper focuses on the validation of four existing risk-assessment models for woody plants in Iowa, and the application and validation of a new (and potentially more accurate) "random forest" modeling technique to predict naturalizing and non-naturalizing plants. Validation, which represents a “real world” test of the models, indicates that there is room for improvement in their power and accuracy. Still, the new random forest modeling technique shows promise for the future development of a regional-scale model for the Upper Midwest that could be applied by land-use managers, the green industry, and regulatory agencies alike.
Technical Abstract: Use of risk-assessment models that can predict the naturalization and invasion of non-native woody plants is a potentially beneficial approach for protecting human and natural environments. This study validates the power and accuracy of four risk-assessment models previously tested in Iowa, and examines the performance of a new random forest modeling approach. The random forest model was fitted with the same data used to develop the four earlier risk-assessment models. The validation of all five models was based on a new set of 11 naturalizing and 18 non-naturalizing species in Iowa. The fitted random forest model had a high classification rate (92.0%), no biologically significant errors, and few horticulturally limiting errors (8.7%). Classification rates for validation of all five models ranged from 62.1 to 93.1%. Horticulturally limiting errors for the four models previously developed for Iowa ranged from 11.1 to 38.5%, and biologically significant errors from 4.2 to 18.5%. Because of the small sample size, few classification and error rate results were significantly different from the original tests of the models. Overall, the random forest model shows promise for powerful and accurate risk-assessment, but mixed results for the other models suggest a need for further refinement.