Operator-based machine learning framework for generalizable prediction of unsteady treatment dynamics in stormwater infrastructure

2025-07-07

AI Summary

To address the low prediction accuracy and high computational cost of urban stormwater infrastructure modeling under unsteady hydraulic and pollutant loading conditions, this paper proposes a Composite Physics-Informed Neural Network (CPNN) framework integrating deep operator learning with automatic differentiation. It is the first work to introduce operator learning into dynamic modeling of urban stormwater systems, achieving high-fidelity coupling of hydrodynamics and particulate transport while balancing the efficiency of CSTR models and the physical fidelity of CFD simulations. The CPNN achieves R² > 0.8 for hydraulic predictions in 95.2% of test cases and for particle concentration predictions in 72.6%, significantly outperforming conventional lumped-parameter models. Moreover, it enables gradient-based sensitivity analysis of pollutant transport via automatic differentiation, enhancing model interpretability. The framework supports long-term continuous performance assessment and climate-resilient infrastructure planning.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Reasoning under Uncertainty: Stochastic Optimization
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

Stormwater infrastructures are decentralized urban water-management systems that face highly unsteady hydraulic and pollutant loadings from episodic rainfall-runoff events. Accurately evaluating their in-situ treatment performance is essential for cost-effective design and planning. Traditional lumped dynamic models (e.g., continuously stirred tank reactor, CSTR) are computationally efficient but oversimplify transport and reaction processes, limiting predictive accuracy and insight. Computational fluid dynamics (CFD) resolves detailed turbulent transport and pollutant fate physics but incurs prohibitive computational cost for unsteady and long-term simulations. To address these limitations, this study develops a composite operator-based neural network (CPNN) framework that leverages state-of-the-art operator learning to predict the spatial and temporal dynamics of hydraulics and particulate matter (PM) in stormwater treatment. The framework is demonstrated on a hydrodynamic separator (HS), a common urban treatment device. Results indicate that the CPNN achieves R2 > 0.8 for hydraulic predictions in 95.2% of test cases; for PM concentration predictions, R2 > 0.8 in 72.6% of cases and 0.4 < R2 < 0.8 in 22.6%. The analysis identifies challenges in capturing dynamics under extreme low-flow conditions, owing to their lower contribution to the training loss. Exploiting the automatic-differentiation capability of the CPNN, sensitivity analyses quantify the influence of storm event loading on PM transport. Finally, the potential of the CPNN framework for continuous, long-term evaluation of stormwater infrastructure performance is discussed, marking a step toward robust, climate-aware planning and implementation.

Problem

• Predict unsteady treatment dynamics in stormwater infrastructure
• Overcome limitations of traditional and CFD models for stormwater
• Develop operator-based neural network for hydraulic and PM predictions

Innovation

• Operator-based neural network for stormwater dynamics
• Combines operator learning with neural networks
• Enables long-term unsteady hydraulic predictions