A Deep Learning-Based Data Assimilation Approach to Characterizing Coastal Aquifers Amid Non-Linearity and Non-Gaussianity Challenges

Abstract

Seawater intrusion (SI) poses a substantial threat to water security in coastal regions, where numerical models play a pivotal role in supporting groundwater management and protection. However, the inherent heterogeneity of coastal aquifers introduces significant uncertainties into SI predictions, potentially diminishing their effectiveness in management decisions. Data assimilation (DA) offers a solution by integrating various types of observational data with the model to characterize heterogeneous coastal aquifers. Traditional DA techniques, like ensemble smoother using the Kalman formula (ES_K) and Markov chain Monte Carlo, face challenges when confronted with the non-linearity, non-Gaussianity, and high-dimensionality issues commonly encountered in aquifer characterization. In this study, we introduce a novel DA approach rooted in deep learning (DL), referred to as ES_DL, aimed at effectively characterizing coastal aquifers with varying levels of heterogeneity. We systematically investigate a range of factors that impact the performance of ES_DL, including the number and types of observations, the degree of aquifer heterogeneity, the structure and training options of the DL models. Our findings reveal that ES_DL excels in characterizing heterogeneous aquifers under non-linear and non-Gaussian conditions. Comparison between ES_DL and ES_K under different experimentation settings underscores the robustness of ES_DL. Conversely, in certain scenarios, ES_K displays noticeable biases in the characterization results, especially when measurement data from non-linear and discontinuous processes are used. To optimize the efficacy of ES_DL, attention must be given to the design of the DL model and the selection of observational data, which are crucial to ensure the universal applicability of this DA method.