Traditional numerical models have been widely employed to simulate the transport of multispecies reactive contaminants in groundwater systems; however, their high computational cost limits their applicability in real-time or large-scale scenarios. Recent advances in artificial intelligence (AI) offer promising alternatives, particularly data-driven machine learning techniques, for accelerating such simulations. This study presents the development of a surrogate model based on artificial neural networks (ANNs) to simulate the transport and decay of interacting multispecies contaminants in groundwater. High-fidelity training datasets are generated through finite difference-based reactive transport simulations across a wide range of environmental and geochemical conditions. The ANN model is trained to learn the complex nonlinear relationships governing the multispecies transport and transformation processes. Model validation reveals that the ANN surrogate accurately reproduces the spatial–temporal concentration profiles of both original and degradation species, capturing key dynamic behaviors with high precision. Notably, the ANN model achieves up to a 100-fold reduction in computational time compared to traditional analytical or semi-analytical solutions. These results highlight the ANN’s potential as an efficient and accurate surrogate modeling tool for groundwater contamination assessment, offering a valuable advancement for decision-making in environmental risk analysis and remediation planning.

Previous studies on contaminant transport models have primarily focused on boundary sources, limiting their applicability to scenarios with multiple internal pollution sources. This study develops a semi-analytical model for multispecies contaminant transport that incorporates advection, dispersion, rate-limited sorption, and first-order degradation, accommodating arbitrary time-dependent pollutant sources. By addressing rate-limited sorption, the model avoids underestimating degradable pollutant concentrations in non-equilibrium scenarios. The model is derived using the Laplace transform, finite cosine Fourier transform, generalized integral transform, and inverse transformations. Results highlight the sensitivity of contaminant and degradation product concentrations to time-dependent source variations. The model's key contribution lies in its ability to simulate dispersion from multiple internal sources under rate-limited sorption conditions, providing more accurate predictions of pollution plume dynamics and offering a robust alternative to boundary-source models for preliminary pollution management.

Chlorinated solvents, common groundwater contaminants, can cause coexistence of the original contaminant and its degradation products during the transport process. Practically applicable analytical models for reactive transport are essential for simulating the plume migration of chlorinated solvent contaminants and their degradation products within a complex chemical mixture. Although several analytical models have been developed to solve advection–dispersion equations coupled with a series of decay reactions for simulating transport of the coexisting chlorinated solvent contaminants, the majority assume static, time-invariant inlet boundary conditions. Such time-invariant inlet boundary conditions may fail to adequately represent the temporal evolution of dissolved source discharge concentration concerning mass reduction, especially in the context of diverse DNAPL source remediation strategies. This study seeks to derive analytical models for three-dimensional reactive transport of multiple contaminants, specifically addressing the challenges posed by dynamical, time-varying inlet boundary conditions. The model development incorporates two distinct inlet functions: exponentially decaying and piecewise constant. Analytical solutions are obtained using three integral transform techniques. The accuracy of the newly developed analytical models is verified by comparing them with solutions derived from existing literature using multiple illustrative examples. By incorporating two distinct time-varying inlet boundary conditions, the models exhibit strong capabilities in capturing the complex transport dynamics and fate of contaminants within groundwater systems. These features make the models valuable tools for improving the understanding of subsurface contaminant behavior and for quantitatively evaluating and optimizing a range of remediation strategies.