Physics-Informed Neural Network Modeling of Biodegradable Contaminant Transport through GCL/SL Composite Liners

2026-06-02

AI Summary

This study addresses the challenge of accurately predicting early-stage migration of biodegradable contaminants through geosynthetic clay liner (GCL)/soil liner (SL) composite barriers under high leachate head conditions. To this end, a dual-domain physics-informed neural network (PINN) approach is proposed, wherein the GCL layer is modeled as a steady-state advection–dispersion–biodegradation domain and the underlying geomembrane as a transient transport domain. The method innovatively embeds boundary and initial conditions directly into the trial functions via a hard-constraint strategy, substantially enhancing prediction accuracy and stability of early concentration fields. It also enables robust inversion of biodegradation half-lives even from noisy, sparse observational data. Compared to conventional soft-constraint PINNs, the proposed approach reduces mean absolute errors from 0.058–0.067 to 0.011–0.023 and relative errors from 9.10%–19.16% to 2.08%–3.14%.

Abstract

This study develops a two-domain physics-informed neural network framework for contaminant transport through a GCL/SL composite liner system, in which the thin GCL layer is treated using a steady-state advection-dispersion-biodegradation formulation and the underlying soil liner is modeled as a transient transport domain. Two formulations are evaluated against analytical and finite-element reference solutions under different leachate-head conditions: a standard PINN with soft constraint enforcement (Std-PINN) and a hard-constrained PINN (H-PINN), in which selected boundary and initial conditions are embedded directly into the trial solutions. The Std-PINN captures the overall breakthrough behavior but shows larger errors during the early transport stage, particularly under higher leachate heads where advective transport becomes more pronounced. The H-PINN reduces the optimization burden associated with penalty-based constraint enforcement and provides more accurate and stable concentration predictions, lowering the MAE from approximately 0.058-0.067 for the Std-PINN to about 0.011-0.023 for the H-PINN, while reducing the MRE from approximately 9.10%-19.16% to about 2.08%-3.14%. Parametric analyses confirm that the H-PINN with the tanh activation function and an optimized network structure provides the best predictive accuracy. The H-PINN is further extended to inverse modeling for identifying the SL degradation half-life from limited concentration observations, showing reliable convergence toward prescribed values and acceptable robustness under low-to-moderate observation noise.

Problem

• contaminant transport
• GCL/SL composite liners
• biodegradation
• inverse modeling
• breakthrough behavior

Innovation

• Physics-Informed Neural Networks
• Hard-constrained PINN
• Contaminant transport
• Composite liners
• Inverse modeling