Copper-based fungicides (Cu f) are used in European (EU) vineyards to prevent fungal diseases. Soil physicochemical properties govern locally the variation of total copper content (Cu t) in EU vineyards. However, variables controlling Cu t distribution at larger scale are poorly known. Here machine learning techniques were used to identify governing variables and to predict the Cu t distribution in EU vineyards. Precipitation, aridity and soil organic carbon are key variables explaining together 45% of Cu t distribution across EU vineyards. This underlines the effect of both climate and soil properties on Cu t distribution. The average net export of Cu at the EU scale is 0.29 kg Cu ha-1 which is two orders of magnitude less than the net accumulation of Cu (24.8 kg Cu ha-1). Four scenarios of Cu f application were compared. The current EU regulation with a maximum of 4 kg Cu ha-1 year-1 may increase by 2% the EU vineyard area exceeding the predicted no-effect concentration (PNEC) in soil in the next 100 years. Overall, our results highlight vineyard areas requiring specific remediation measures and strategies of Cu f use to manage a trade-off between pest control and soil and water contamination.