Microplastics (MPs) are ubiquitous environmental contaminants with urban landscapes as major source areas of MPs and stormwater runoff as an important transport pathway to receiving aquatic environments. To better delineate the drivers of urban stormwater MP loads, we created a global dataset of stormwater MP concentrations extracted from 107 stormwater catchments (SWCs). Using this dataset, we trained and tested three optimized gradient boosting Machine Learning (ML) models. Twenty hydrometeorological and socioeconomic variables, as well as the MP size definitions considered in the individual SWCs, were included as potential predictors of the observed MP concentrations. CatBoost emerged as the best-performing ML model. Shapley additive explanations revealed that features related to hydrometeorological conditions, watershed characteristics and human activity, and plastic waste management practices contributed 34, 25, and 4.8%, respectively, to the model's predictive performance. The MP size definition, that is, the lower size limit and the width of the size range, accounted for the remaining 36% variability in the predicted MP concentrations. The lack of a consistent definition of the MP size range among studies therefore represents a major source of uncertainty in the comparative analysis of urban stormwater MP concentrations. The proposed ML modeling approach can generate first estimates of MP concentrations in urban stormwater when data are sparse and serve as a quantitative tool for benchmarking the added value of including further data layers and applying uniform definitions of size classes of environmental MPs.