ECOLOGICAL DETERMINANTS OF PLANT INVASION SUCCESS: INTEGRATING MULTIVARIABLE STATISTICAL INFERENCE AND MACHINE LEARNING PREDICTION
Abstract
Ecological, biogeographical, functional and phylogenetic processes interact in complex ways to drive biological invasions. The identification of strong invasion success determinants and assessment of predictive modelling techniques are critically needed to enhance ecological risk assessment and management. This study investigated the principal ecological determinants of plant invasion success and compared the predictive performance of multivariable logistic regression and Random Forest classification. A quantitative observational analysis was conducted using 735 cultivated naturalized plant taxa, comprising 300 invasive and 435 non-invasive taxa. Group differences were evaluated using Mann–Whitney U, chi-square, or Fisher's exact tests with Benjamini–Hochberg adjustment. Spearman correlation analysis was followed by multivariable logistic regression and a tuned Random Forest model, with predictive performance assessed using accuracy, sensitivity, specificity, precision, F1 score, and ROC-AUC on an independent test set. Invasive taxa exhibited broader native ranges, greater climatic suitability, and lower phylogenetic distances than non-invasive taxa. Logistic regression identified native-range size, climatic suitability, human food use, and poisonous classification as positive predictors, whereas vegetative propagation and minimum phylogenetic distance were negatively associated with invasion success. Logistic regression achieved higher accuracy (0.735), F1 score (0.655), and ROC–AUC (0.758) than Random Forest, which demonstrated substantial overfitting despite similar test discrimination. These findings indicate that plant invasion success is best explained by integrating environmental compatibility, biogeographical breadth, human use, reproductive strategy, and phylogenetic relationships. Logistic regression was the most robust and interpretable model for ecological prediction and Random Forests gave complementary information about the importance of predictors.
Downloads
References
2.Bhattarai, G. P., Meyerson, L. A., Anderson, J., Cummings, D., Allen, W. J., & Cronin, J. T. (2017). Biogeography of a plant invasion: genetic variation and plasticity in latitudinal clines for traits related to herbivory. Ecological Monographs, 87(1), 57-75.
3.Cassey, P., Delean, S., Lockwood, J. L., Sadowski, J. S., & Blackburn, T. M. (2018). Dissecting the null model for biological invasions: A meta-analysis of the propagule pressure effect. PLoS biology, 16(4), e2005987.
4.Dick, J. T., Alexander, M. E., Ricciardi, A., Laverty, C., Downey, P. O., Xu, M., ... & Shaw, R. H. (2017). Functional responses can unify invasion ecology. Biological invasions, 19(5), 1667-1672.
5.Dong, B.-C., Dong, R., Yang, Q., Kinlock, N., Yu, F.-H., & van Kleunen, M. (2025). Data from: Predicting invasion success of cultivated naturalized plants in China [Dataset]. Dryad. https://doi.org/10.5061/dryad.2ngf1vj08
6.Enders, M., Havemann, F., Ruland, F., Bernard‐Verdier, M., Catford, J. A., Gómez‐Aparicio, L., ... & Jeschke, J. M. (2020). A conceptual map of invasion biology: Integrating hypotheses into a consensus network. Global Ecology and Biogeography, 29(6), 978-991.
7.Fontúrbel, F. E., Nespolo, R. F., Amico, G. C., & Watson, D. M. (2021). Climate change can disrupt ecological interactions in mysterious ways: using ecological generalists to forecast community-wide effects. Climate Change Ecology, 2, 100044.
8.Fristoe, T. S., Chytrý, M., Dawson, W., Essl, F., Heleno, R., Kreft, H., ... & Van Kleunen, M. (2021). Dimensions of invasiveness: Links between local abundance, geographic range size, and habitat breadth in Europe’s alien and native floras. Proceedings of the National Academy of Sciences, 118(22), e2021173118.
9.Gioria, M., Hulme, P. E., Richardson, D. M., & Pyšek, P. (2023). Why are invasive plants successful?. Annual Review of Plant Biology, 74(1), 635-670.
10.Gong, X., Chen, Y., Wang, T., Jiang, X., Hu, X., & Feng, J. (2020). Double-edged effects of climate change on plant invasions: Ecological niche modeling global distributions of two invasive alien plants. Science of the total environment, 740, 139933.
11.Jeschke, J. M., & Starzer, J. (2018). Propagule pressure hypothesis. Invasion Biology-Hypothesis and Evidence. CABI Invasives Series, Oxfordshire, UK: CABI, Wallingford.
12.Ketola, T., Saarinen, K., & Lindström, L. (2017). Propagule pressure increase and phylogenetic diversity decrease community’s susceptibility to invasion. BMC ecology, 17(1), 15.
13.Liu, Y. J., Huang, W., Yang, Q., Zheng, Y. L., Li, S. P., Wu, H., ... & Ding, J. Q. (2022). Research advances of plant invasion ecology over the past 10 years.
14.Liu, Y., Oduor, A. M., Zhang, Z., Manea, A., Tooth, I. M., Leishman, M. R., ... & Van Kleunen, M. (2017). Do invasive alien plants benefit more from global environmental change than native plants?. Global Change Biology, 23(8), 3363-3370.
15.Lone, P. A., Dar, J. A., Subashree, K., Raha, D., Pandey, P. K., Ray, T., ... & Khan, M. L. (2019). Impact of plant invasion on physical, chemical and biological aspects of ecosystems: A review. Tropical Plant Research, 6(3), 528-544.
16.Mathakutha, R., Steyn, C., le Roux, P. C., Blom, I. J., Chown, S. L., Daru, B. H., ... & Greve, M. (2019). Invasive species differ in key functional traits from native and non‐invasive alien plant species. Journal of Vegetation Science, 30(5), 994-1006.
17.McMahon, D. E., Urza, A. K., Brown, J. L., Phelan, C., & Chambers, J. C. (2021). Modelling species distributions and environmental suitability highlights risk of plant invasions in western United States. Diversity and Distributions, 27(4), 710-728.
18.Pyšek, P., Hulme, P. E., Simberloff, D., Bacher, S., Blackburn, T. M., Carlton, J. T., ... & Richardson, D. M. (2020). Scientists' warning on invasive alien species. Biological Reviews, 95(6), 1511-1534.
19.Pyšek, P., Pergl, J., Essl, F., Lenzner, B., Dawson, W., Kreft, H., ... & van Kleunen, M. (2017). Naturalized alien flora of the world: species diversity, taxonomic and phylogenetic patterns, geographic distribution and global hotspots of plant invasion.
20.Sittaro, F., Hutengs, C., & Vohland, M. (2023). Which factors determine the invasion of plant species? Machine learning based habitat modelling integrating environmental factors and climate scenarios. International Journal of Applied Earth Observation and Geoinformation, 116, 103158.
21.van Kleunen, M., Bossdorf, O., & Dawson, W. (2018). The ecology and evolution of alien plants. Annual review of ecology, evolution, and systematics, 49(1), 25-47.
22.Vilà, M., & Hulme, P. E. (Eds.). (2017). Impact of biological invasions on ecosystem services (Vol. 12). Cham: Springer.
Copyright (c) 2026 IJRDO - JOURNAL OF BIOLOGICAL SCIENCE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.
