Groundwater Contamination Source Identification (GCSI) is a crucial prerequisite for conducting comprehensive pollution risk assessments, formulating effective groundwater contamination control strategies, and devising remediation plans. In previous GCSI studies, various boundary conditions were typically assumed to be known variables. However, in many practical scenarios, these boundary conditions are exceedingly complex and difficult to accurately pre-determine. This practice of presuming boundary conditions as known may significantly deviate from reality, leading to errors in identification results. Moreover, the outcomes of GCSI may be influenced by multiple factors or conditions, including the fundamental information about the contamination source boundary conditions of the polluted area. This study primarily focuses on contamination source information and unknown boundary conditions. Innovatively, three deep learning surrogate models, the Deep Belief Neural Network (DBNN), Bidirectional Long Short-Term Memory Networks (BiLSTM), and Deep Residual Neural Network (DRNN), are employed for identification and validation and to simulate the highly no-linear simulation model and directly establish a mapping relationship between the outputs and inputs of the simulation model. This approach enables the direct acquisition of the inverse identification results of the variables based on actual monitoring data, thereby facilitating rapid inverse identification. Furthermore, to account for the uncertainty of noise in monitoring data, the inversion accuracy of these three deep learning methods is compared, and the method with higher accuracy is selected for uncertainty analysis. Multiple experiments were conducted, such as accuracy identification tests, robustness tests, and cross-comparative ablation studies. The results demonstrate that all three deep learning models effectively complete the research tasks, with DBNN showing the most exceptional performance in the experiments. DBNN achieved an R² value of 0.982, an RMSE of 3.77, and an MAE of 7.56%. Subsequent uncertainty analysis, model robustness, and ablation study further affirm DBNN adaptability to GCSI research tasks.

Wheat flour transportation involves extended transit periods, which present considerable challenges for safety risk oversight. Therefore, it is essential to develop an efficient anomaly detection method to support risk assessment during this stage. However, existing anomaly detection methods often neglect the coupling effects across different time scales and the spatial clustering of hazard factors. To address this limitation, we propose a multi-scale spatial–temporal graph model-based unsupervised anomaly detection framework (MSTUAD), which can simultaneously capture the spatial–temporal correlations between importance and hazard factors across multiple time scales. Specifically, feature maps are first constructed for each hazard factor within a given time window to represent coupling effects. Secondly, a multi-scale spatial–temporal graph model is designed to extract spatial–temporal characteristics from these feature maps. Finally, a reconstruction model based on a variational autoencoder learns latent representations of spatial–temporal features of hazard factors, thereby capturing the intrinsic characteristics of normal wheat flour. Experimental validation on the wheat flour transportation hazard factor dataset and three public industrial datasets demonstrates that MSTUAD significantly outperforms state-of-the-art anomaly detection methods, achieving an average F1-score greater than 84.55%. This approach provides valuable decision support and technical guidance for relevant regulatory authorities.