Plastic waste is rapidly accumulating in the environment, however research on the causes and consequences of this externality are hampered by a lack of comprehensive data. We seek to quantify the extent to which the international trade in waste contributes to the accumulation of plastic waste in the natural environment. We use novel methods to create a time series of open-air waste site area by country. Our approach takes a sample of unrepresentative crowd-sourced training data to train a machine learning model on satellite imagery. We then verify an optimally chosen subset of predictions to debias our estimates and maximize efficiency. Our results show a dramatic increase in open-air landfills in countries that received increased waste imports after China banned imports of plastic waste in 2018, suggesting that trade plays a role in overwhelming local waste management systems and the subsequent leakage of plastic into the environment. Our methodological contributions are valuable for generating descriptive statistics and measuring causal effects on rare land-use types.