article · Sustainability
Managing estuarine water quality requires models that incorporate both physical laws and human influences. A physics-informed digital twin framework has been developed to predict dissolved oxygen levels in Morocco's Bouregreg Estuary. The system embeds non-linear advection, diffusion, and reaction transport equations directly into the loss function of a deep residual neural network architecture, ensuring physical realism regarding gravitational circulation and salt wedge dynamics. It couples these physical equations with socio-economic indicators, specifically regional water-pricing indices and daily urban wastewater discharges of approximately 120,000 cubic metres from the Rabat-Salé municipal area. The resulting model outperforms conventional machine learning baselines by reducing predictive error by 89.1 percent while accurately capturing vertical oxygen stratification. Analysis shows urban effluent accounts for 28 percent of the internal attribution in predictions, and scenario tests indicate that reducing discharge volumes by 20 percent could alleviate summer hypoxia.
Conventional data-driven models frequently fail to capture underlying physical processes or the direct impact of human activity on aquatic environments. By embedding hydrodynamic laws alongside socio-economic indicators, this approach offers water managers and policymakers a reliable, physically sound digital twin tool. This improves forecasting accuracy for estuarine dissolved oxygen levels and supports targeted pollution management decisions in line with national water strategies and sustainable development goals.
This work demonstrates an applied, tested digital twin model suitable for municipal authorities, water governance agencies, and environmental regulators overseeing estuarine systems. The framework enables simulated scenario testing for pollution mitigation, such as evaluating wastewater reduction strategies. While validated on the Bouregreg Estuary, real-world deployment would require integration into existing municipal monitoring workflows, positioning it as an applied research tool ready for pilot policy implementation and operational software development.
AI-generated from the published abstract. Always read the original work before citing.
The management of estuarine ecosystem sustainability is a complex problem that requires models that are physically sound, socially meaningful, and interpretable from a mechanistic standpoint. Even though classical AI has demonstrated promise in environmental forecasting, black-box models typically fall short of meeting basic conservation requirements or accounting for anthropogenic stresses that alter water quality. This work introduces a novel framework based on Deep Physics-Informed Neural Networks (Deep PINNs) to predict the dynamics of dissolved oxygen (DO) in the Bouregreg Estuary (Morocco). We advance baseline standards by directly integrating the non-linear advection–diffusion–reaction (ADR) transport equations into the loss function of a deep residual architecture (ResNet with 12–20 layers). This integration ensures that the model takes into account two important aspects of estuarine hydrodynamics: gravitational circulation and the salt wedge effect. The incorporation of a socio–hydro–physical nexus, which uses regional water-pricing indices and urban wastewater discharge volumes from the Rabat-Salé municipal area (∼120,000 m3/day) as proxy variables for anthropogenic pressure, is a unique aspect of this work. The Deep PINN achieves a better coefficient of determination (R2=0.998) and a Nash–Sutcliffe efficiency (NSE=0.997), outperforming the traditional ANFIS and ANN baselines by 89.1% in terms of predictive error reduction (RMSE=0.041±0.002 mg/L). In situations where unconstrained data-driven models fall short, the framework exhibits physical robustness in capturing vertical DO stratification in addition to numerical accuracy. Urban effluent volumes have a significant impact on predictive variance, accounting for 28% of the model internal attribution—more than the relative influence of thermal solubility, according to mechanistic feature attribution analysis using SHAP (Shapley Additive exPlanations). Finally, exploratory management scenarios suggest that summer hypoxia could hypothetically be mitigated through a 20% reduction in discharge volumes. This study bridges the gap between scientific modeling and policy implementation by providing a physics-consistent digital twin framework for environmental stewardship in support of UN SDG 6 and Morocco’s National Water Plan.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/su18168148
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
