Predicting hotspots for invasive species introduction in Europe

Abstract Plant pest invasions cost billions of Euros each year in Europe. Prediction likely places introduction could greatly help focus efforts on prevention and control thus reduce societal costs invasions. Here, we test whether generic data-driven risk maps introduction, valid for multiple species produced by machine learning methods, supplement the costly species-specific analyses currently conducted governmental agencies. An elastic-net algorithm was trained a dataset covering 243 invasive to map new introductions Europe as function climate, soils, water, anthropogenic factors. Results revealed that BeNeLux states, Northern Italy, Balkans, United Kingdom, areas around container ports such Antwerp, London, Rijeka, Saint Petersburg were at higher introductions. Our analysis shows can produce hotspot with high predictive accuracy, but systematically collected data species’ presences absences are required further validate improve these maps.