Effective Characterization of Fractured Media with A Novel Deep Learning-Based Data Assimilation Approach

In various research fields such as hydrogeology, environmental science and energy engineering, geological formations with fractures are frequently encountered. Accurately characterizing these fractured media is of paramount importance when it comes to tasks that demand precise predictions of liquid flow and the transport of solutes and energy within them. Since directly measuring fractured media poses inherent challenges, data assimilation (DA) techniques are typically employed to derive inverse estimates of media properties using observed state variables like hydraulic head, concentration, and temperature. Nonetheless, the considerable difficulties arising from the strong heterogeneity and non-Gaussian nature of fractured media have diminished the effectiveness of existing DA methods. In this study, we formulate a novel DA approach known as PEDL (Parameter Estimator with Deep Learning) that harnesses the capabilities of DL to capture non-linear relationships and extract non-Gaussian features. To evaluate PEDLs performance, we conduct two numerical case studies of increasing complexity. Our results unequivocally demonstrate that PEDL outperforms three popular DA methods: Ensemble Smoother with Multiple Data Assimilation (ES-MDA), Iterative Local Updating Ensemble Smoother (ILUES), and ES with DL-based Update (ES-DL). Sensitivity analysis confirms PEDLs validity and adaptability across various ensemble sizes and DL model architectures. Furthermore, even in scenarios where a mismatch exists between the reference model and the forecast models structure, PEDL adeptly identifies the primary characteristics of actual fractures.