Contaminant Transport Modeling and Source Attribution With Attention-Based Graph Neural Network

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. Groundwater contamination caused by human activities is a longstanding global challenge. Accurately characterizing and modeling the movement of contaminants is crucial for the protection and management of groundwater resources. However, the complexity of the processes, limitations in data availability, and high computational demands pose significant challenges. In the age of big data, machine learning offers new avenues for exploring contaminant transport in groundwater. In this study, we introduce a novel machine learning model called an attention-based graph neural network (aGNN) designed to model contaminant transport with sparse monitoring data and to analyze the causal relationships between contaminant sources and observed concentrations at specific locations. We conducted five synthetic case studies across diverse aquifer systems with varying monitoring setups, where aGNN demonstrated superior performance over models based on other approaches. It also proved highly capable of making inferences about pollution levels at unmonitored sites. Moreover, an explanatory analysis using aGNN effectively quantified the impact of each contaminant source, with results validated by a physics-based model. Overall, this study establishes aGNN as an efficient and robust method for complex spatiotemporal learning in subsurface contaminant transport, making it a valuable tool for groundwater management and contaminant source identification. A novel graph-based deep learning method is proposed for modeling contaminant transport constrained by monitoring data The proposed model quantifies the contribution of each potential contaminant source to the observed concentration at an arbitrary location The deep learning method substantially reduces the computational cost compared with a physics-based contaminant transport model