Optimal layout design of groundwater pollution monitoring network using parameter iterative updating strategy-based ant colony optimization algorithm.

The scientific layout design of the groundwater pollution monitoring network (GPMN) can provide high quality groundwater monitoring data, which is essential for the timely detection and remediation of groundwater pollution. The simulation optimization approach was effective in obtaining the optimal design of the GPMN. The ant colony optimization (ACO) algorithm is an effective method for solving optimization models. However, the parameters used in the conventional ACO algorithm are empirically adopted with fixed values, which may affect the global searchability and convergence speed. Therefore, a parameter-iterative updating strategy-based ant colony optimization (PIUSACO) algorithm was proposed to solve this problem. For the GPMN optimal design problem, a simulation-optimization framework using PIUSACO algorithm was applied in a municipal waste landfill in BaiCheng city in China. Moreover, to reduce the computational load of the design process while considering the uncertainty of aquifer parameters and pollution sources, a genetic algorithm-support vector regression (GA-SVR) method was proposed to develop the surrogate model for the numerical model. The results showed that the layout scheme obtained using the PIUSACO algorithm had a significantly higher detection rate than ACO algorithm and random layout schemes, indicating that the designed layout scheme based on the PIUSACO algorithm can detect the groundwater pollution occurrence timely. The comparison of the iteration processes of the PIUSACO and conventional ACO algorithms shows that the global searching ability is improved and the convergence speed is accelerated significantly using the iteration updating strategy of crucial parameters. This study demonstrates the feasibility of the PIUSACO algorithm for the optimal layout design of the GPMN for the timely detection of groundwater pollution.

Review of machine learning-based surrogate models of groundwater contaminant modeling.

Heavy computational load inhibits the application of groundwater contaminant numerical model to groundwater pollution source identification, remediation design, and uncertainty analysis, since a large number of model runs are required for these applications. Machine learning-based surrogate models are an effective approach to enhance the efficiency of the numerical models, and have recently attracted considerable attention in the field of groundwater contaminant modeling. Here, we review 120 research articles on machine learning-based surrogate models for groundwater contaminant modeling that were published between 1994 and 2022. We outline the state of the art method, identify the most significant research challenges, and suggest potential future directions. The six major applications of machine learning-based surrogate models are groundwater pollution source identification, groundwater remediation design, coastal aquifer management, uncertainty analysis of groundwater, groundwater monitoring network design, and groundwater transport parameters inversion. Together, these account for more than 90% of the studies we review. Latin hypercube sampling (LHS) is the most widely used sampling method, and artificial neural networks (ANNs) and Kriging are the two most widely used methods for constructing surrogate model. No method is universally superior, the advantages and disadvantages of different methods, as well as the applicability of these methods for different application purposes of groundwater contaminant modeling were analyzed. Some recommendations on the method selection for various application fields are given based on the reviews and experiences. Based on our review of the state-of-the-art, we suggest several future research directions to enhance the feasibility of the machine learning-based surrogate models of groundwater contaminant modeling: the alleviation of the curse of dimensionality, enhancing transferability, practical applications for real case studies, multi-source dada fusion, and real-time monitoring and prediction.