Haochen Li

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.

The dynamic interplay between microbial communities and sediment transport shapes continental landscapes and influences particulate matter fluxes across the Earth’s surface. Microbial colonization transforms individual sediment grains into aggregates with intricate and varied morphologies, complicating sediment transport. However, current models often simplify this morphological complexity, assuming that aggregates experience fluid drag equal to that of smooth spheres or idealized shapes. Here we apply an X-ray micro-computed tomography method combined with computational fluid dynamics simulations to analyse aggregate morphology at high spatial resolution and determine the relationship with drag. Instead of aggregate size or gross shape being the primary controls on drag, we find that microbial colonization alters the fine-scale aggregate morphology and increases drag by factors of 1–3 compared with smooth surfaces. We propose a morphology-corrected drag law that accounts for this complexity, reconciling the differences in drag across diverse aggregates. Our findings suggest that a shift from focusing on gross scale variabilities (size or gross shape) to fine-scale morphologies could enable greater accuracy in transport predictions, and improve understanding of microbially colonized aggregates in fluvial, coastal and oceanic systems.

The dynamic interplay between microbial communities and sediment transport shapes continental landscapes and influences particulate matter fluxes across the Earth’s surface. Microbial colonization, with its ubiquitous presence, transforms individual sediment grains into aggregates with intricate and varied morphologies, making sediment transport prediction difficult. Consequently, current models often simplify this morphological complexity, assuming that aggregates experience fluid drag equal to that of smooth spheres or idealised shapes. To test this hypothesis, we applied a novel microscopic methodology, enabling a high-resolution investigation of drag across diverse aggregates. In contrast to the prevailing paradigm that recognizes the aggregate size or gross shape as the primary controls, we discovered a critical yet previously overlooked mechanism: microbial colonization significantly alters the fine-scale aggregate morphology, increasing drag by factors of 1–4 compared with smooth surfaces. We propose a morphology-corrected drag law that accounts for this complexity, reconciling the differences in drag across diverse aggregates. Our findings shift the focus from size or gross shape variability to fine-scale morphologies, enabling greater accuracy in transport predictions, promoting new measurement strategies, and marking a transformative step in conceptualizing microbially colonized aggregates in fluvial, coastal and oceanic systems.