Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
H. Kotula, G. Peralta, C. Frost, J. Todd, J. Tylianakis
This study uses machine learning to predict direct and indirect non-target impacts of biocontrol agents by analyzing host-parasitoid networks, finding that random forest models outperformed KNN in predicting interactions.
bioRxiv · Nov 24, 2020Ecology