A. Garzón1, Z. Kapelan1, J.
Langeveld1,2 and R. Taormina1
1Faculty of Civil Engineering and Geosciences,
Department of Water Management, Delft University of Technology,
Stevinweg 1, 2628 CN Delft, The Netherlands
2Partners4UrbanWater, Graafseweg 274, 6532 ZV
Nijmegen, The Netherlands
Corresponding author: Alexander Garzón (J.A.GarzonDiaz@tudelft.nl)
Key Points:
- Machine Learning surrogate models have been widely employed for a
variety of applications concerning urban water networks.
- New research should focus on machine learning metamodels that account
for inductive biases, robustness, and transferability.
- Further research should focus on complex problems involving
uncertainty and multi-objective optimisation, as well as improved
benchmarking.
Abstract
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 optimisation 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. In this
manuscript, we review 31 recent papers on ML-based metamodeling of urban
water networks to outline the state-of-the-art of the field, identify
outstanding gaps, and propose future research directions. For each
paper, 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 i) the curse
of dimensionality, hindering implementation for large case studies; ii)
black-box deterministic nature, limiting explainability and
applicability; and iii) 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. The recently
developed Graph Neural Network architecture, which extends deep learning
methods to graph data structures, is a preferred candidate for advancing
surrogate modelling in urban water networks. Furthermore, we foresee
increasing efforts for complex applications where metamodels may play a
fundamental role, such as uncertainty analysis and multi-objective
optimisation. Lastly, the development and comparison of ML-based
metamodel can benefit from the availability of new benchmark datasets
for urban drainage systems and realistic complex networks.