Surrogate models replace computationally expensive simulations of physically‐based models to obtain accurate results at a fraction of the time. These surrogate models, also known as metamodels, have been employed for analysis, control, and optimization of water distribution and urban drainage systems. With the advent of machine learning (ML), water engineers have increasingly resorted to these data‐driven techniques to develop metamodels of urban water networks (UWNs). In this article, we review 31 recent articles on ML‐based metamodeling of UWNs to outline the state‐of‐the‐art of the field, identify outstanding gaps, and propose future research directions. For each article, we critically examined the purpose of the metamodel, the metamodel characteristics, and the applied case study. The review shows that current metamodels suffer several drawbacks, including (a) the curse of dimensionality, hindering implementation for large case studies; (b) black‐box deterministic nature, limiting explainability and applicability; and (c) rigid architecture, preventing generalization across multiple case studies. We argue that researchers should tackle these issues by resorting to recent advancements in ML concerning inductive biases, robustness, and transferability. Recently developed neural network architectures, which extend deep learning methods to graph data structures, are preferred candidates for advancing surrogate modeling in UWNs. Furthermore, we foresee increasing efforts for complex applications where metamodels may play a fundamental role, such as uncertainty analysis and multi‐objective optimization. Lastly, the development and comparison of ML‐based metamodels can benefit from the availability of new benchmark datasets for urban drainage systems and realistic complex networks.

This paper aims to stimulate discussion based on the experiences derived from the QUICS project (Quantifying Uncertainty in Integrated Catchment Studies). First it briefly discusses the current state of knowledge on uncertainties in sub-models of integrated catchment models and the existing frameworks for analysing uncertainty. Furthermore, it compares the relative approaches of both building and calibrating fully integrated models or linking separate sub-models. It also discusses the implications of model linkage on overall uncertainty and how to define an acceptable level of model complexity. This discussion includes, whether we should shift our attention from uncertainties due to linkage, when using linked models, to uncertainties in model structure by necessary simplification or by using more parameters. This discussion attempts to address the question as to whether there is an increase in uncertainty by linking these models or if a compensation effect could take place and that overall uncertainty in key water quality parameters actually decreases. Finally, challenges in the application of uncertainty analysis in integrated catchment water quality modelling, as encountered in this project, are discussed and recommendations for future research areas are highlighted.

Over the course of the Corona Virus Disease-19 (COVID-19) pandemic in 2020–2022, monitoring of the severe acute respiratory syndrome coronavirus 2 ribonucleic acid (SARS-CoV-2 RNA) in wastewater has rapidly evolved into a supplementary surveillance instrument for public health. Short term trends (2 weeks) are used as a basis for policy and decision making on measures for dealing with the pandemic. Normalisation is required to account for the dilution rate of the domestic wastewater that can strongly vary due to time- and location-dependent sewer inflow of runoff, industrial discharges and extraneous waters. The standard approach in sewage surveillance is normalisation using flow measurements, although flow based normalisation is not effective in case the wastewater volume sampled does not match the wastewater volume produced. In this paper, two alternative normalisation methods, using electrical conductivity and crAssphage have been studied and compared with the standard approach using flow measurements. For this, a total of 1116 24-h flow-proportional samples have been collected between September 2020 and August 2021 at nine monitoring locations. In addition, 221 stool samples have been analysed to determine the daily crAssphage load per person. Results show that, although crAssphage shedding rates per person vary greatly, on a population-level crAssphage loads per person per day were constant over time and similar for all catchments. Consequently, crAssphage can be used as a quantitative biomarker for populations above 5595 persons. Electrical conductivity is particularly suitable to determine dilution rates relative to dry weather flow concentrations. The overall conclusion is that flow normalisation is necessary to reliably determine short-term trends in virus circulation, and can be enhanced using crAssphage and/or electrical conductivity measurement as a quality check.

While the general principles and modelling approaches for integrated management/modelling of urban water systems already present a decade ago still hold, in recent years aspects like model interfacing and wastewater treatment plant (WWTP) influent generation as complements to sewer modelling have been investigated and several new or improved systems analysis methods have become available. New/improved software tools coupled with the current high computational capacity have enabled the application of integrated modelling to several practical cases, and advancements in monitoring water quantity and quality have been substantial and now allow the collecting of data in sufficient quality and quantity to permit using integrated models for real-time applications too. Further developments are warranted in the field of data quality assurance and efficient maintenance.