Antibiotic use in crops is an emerging concern, however, human exposure to antibiotics residues through consumption of plant-derived food has generally been neglected. This study is a comprehensive evaluation based on full consideration of exposure sources and analysis for nearly 100 antibiotics. A total of 58 antibiotic compounds were detected in drinking water (n = 66) and 49 in food samples (n = 150) from Shenzhen, China. The probable daily intake from drinking water and food consumption based on the total concentration of all the detected antibiotic compounds was 310, 200, and 130 ng/kg-body weight/day for preschool children, adolescents, and adults, with a maximum of up to 1400, 970 and 530 ng/kg-bw/day, respectively. Consumption of plant-derived food products, rather than animal-derived food, was the main source of the daily intake, and drinking water was a minor source. Risk assessment suggested a potentially unacceptable health risk from daily intake of norfloxacin, lincomycin and ciprofloxacin. Further research is warranted to alleviate food safety concerns related to antibiotic residues in plant-derived and animal-derived food products.

Groundwater contamination induced by anthropogenic activities has long been a global issue. Characterizing and modeling contaminant transport processes is crucial to groundwater protection and management. However, challenges still exist in process complexity, data constraint, and computational cost. In the era of big data, the growth of machine learning has led to new opportunities in studying contaminant transport in groundwater systems. In this work, we introduce a new attention‐based graph neural network (aGNN) for modeling contaminant transport with limited monitoring data and quantifying causal connections between contaminant sources (drivers) and their spreading (outcomes). In five synthetic case studies that involve varying monitoring networks in heterogeneous aquifers, aGNN is shown to outperform LSTM‐based (long‐short term memory) and CNN‐ based (convolutional neural network) methods in multistep predictions (i.e., transductive learning). It also demonstrates a high level of applicability in inferring observations for unmonitored sites (i.e., inductive learning). Furthermore, an explanatory analysis based on aGNN quantifies the influence of each contaminant source, which has been validated by a physics‐based model with consistent outcomes with an R² value exceeding 92%. The major advantage of aGNN is that it not only has a high level of predictive power in multiple scenario evaluations but also substantially reduces computational cost. Overall, this study shows that aGNN is efficient and robust for highly nonlinear spatiotemporal learning in subsurface contaminant transport, and provides a promising tool for groundwater management involving contaminant source attribution.