Simultaneous identification of contaminant sources and hydraulic conductivity field by combining geostatistics method with self-organizing maps algorithm

Identification of contaminant source and hydraulic conductivity field based on an ILUES-SOM surrogate model

“…1. A detailed explanation of the original SOM surrogate model can be found in the previous research work (Jiang et al 2021;Xia et al 2019). Considering that the ensemble-based data assimilation methods was the most widely used method for groundwater inverse problems and because of the similarity between the a priori/posterior set and the training data, the ensemble-based data assimilation method was adopted to improve the training data, then the surrogate model was constructed on the basis of posterior samples.…”

“…In recent years, with the enhancement of computer performance, the method of constructing surrogate models using machine learning (ML) has become increasingly popular (Chan and Elsheikh 2020;Tang et al 2020Tang et al , 2021Zhong et al 2019). Among them, Hazrati et al (Hazrati and Datta 2017a,b) used self-organizing map(SOM) to construct surrogate model and identify the intensity of pollution sources where the location of pollution sources were known and slight to mild heterogeneity of the aquifer was considered；On the basis of Hazrati et al 's research, Xia et al (Xia et al 2019)further explored the effect and robustness of SOM-based surrogate model and identify pollution source parameters (location and release history) in more realistic case, the pollution source parameters were unknown and the heterogeneity was much stronger；Jiang et al (Jiang et al 2021) combined the dimensionality reduction idea of pilot points method and applied SOM algorithm to construct surrogate models for simultaneous identification of pollution sources and hydraulic conductivity field.…”

“…The algorithm converts high-dimensional data into lowdimensional by calculating the main features and correlation between the input data, which effectively improves the data processing ability and further improves the computational efficiency (Simula et al 1998). The surrogate model of contaminant transport constructed by the SOM algorithm, not merely replaced the complex original numerical model (groundwater flow and solute transport simulation model), but also had the ability to identify unknown model parameters, which meant that other aforementioned inverse solution methods such as data assimilation methods were no longer needed and a large computational cost was subsequently reduced (Jiang et al 2021).…”

Combining Karhunen–Loève expansion and stochastic modeling for probabilistic delineation of well capture zones in heterogeneous aquifers

“…When dealing with uncertainty in hydraulic conductivity, a more sophisticated and accurate approach involves the use of geostatistical modeling methods (Turcke and Kueper, 1996;Patriarche et al, 2005;Jiang et al, 2021). This technique can generate numerous equiprobable realizations of the hydraulic conductivity by considering the spatial variability of geological data.…”

Identification of contaminant source and hydraulic conductivity field based on an ILUES-SOM surrogate model

“…The algorithm converts high-dimensional data into lowdimensional by calculating the main features and correlation between the input data, which effectively improves the data processing ability and further improves the computational efficiency (Simula et al 1998). The surrogate model of contaminant transport constructed by the SOM algorithm, not merely replaced the complex original numerical model (groundwater flow and solute transport simulation model), but also had the ability to identify unknown model parameters, which meant that other aforementioned inverse solution methods such as data assimilation methods were no longer needed and a large computational cost was subsequently reduced (Jiang et al 2021).…”