Deep learning techniques have been increasingly used in flood management to overcome the limitations of accurate, yet slow, numerical models and to improve the results of traditional methods for flood mapping. In this paper, we review 58 recent publications to outline the state of the art of the field, identify knowledge gaps, and propose future research directions. The review focuses on the type of deep learning models used for various flood mapping applications, the flood types considered, the spatial scale of the studied events, and the data used for model development. The results show that models based on convolutional layers are usually more accurate, as they leverage inductive biases to better process the spatial characteristics of the flooding events. Models based on fully connected layers, instead, provide accurate results when coupled with other statistical models. Deep learning models showed increased accuracy when compared to traditional approaches and increased speed when compared to numerical methods. While there exist several applications in flood susceptibility, inundation, and hazard mapping, more work is needed to understand how deep learning can assist in real-time flood warning during an emergency and how it can be employed to estimate flood risk. A major challenge lies in developing deep learning models that can generalize to unseen case studies. Furthermore, all reviewed models and their outputs are deterministic, with limited considerations for uncertainties in outcomes and probabilistic predictions. The authors argue that these identified gaps can be addressed by exploiting recent fundamental advancements in deep learning or by taking inspiration from developments in other applied areas. Models based on graph neural networks and neural operators can work with arbitrarily structured data and thus should be capable of generalizing across different case studies and could account for complex interactions with the natural and built environment. Physics-based deep learning can be used to preserve the underlying physical equations resulting in more reliable speed-up alternatives for numerical models. Similarly, probabilistic models can be built by resorting to deep Gaussian processes or Bayesian neural networks.

The BATtle of the Attack Detection ALgorithms (BATADAL) is the most recent competition on planning and management of water networks undertaken within the Water Distribution Systems Analysis Symposium. The goal of the battle was to compare the performance of algorithms for the detection of cyber-physical attacks, whose frequency has increased in the last few years along with the adoption of smart water technologies. The design challenge was set for the C-Town network, a real-world, medium-sized water distribution system operated through programmable logic controllers and a supervisory control and data acquisition (SCADA) system. Participants were provided with data sets containing (simulated) SCADA observations, and challenged to design an attack detection algorithm. The effectiveness of all submitted algorithms was evaluated in terms of time-to-detection and classification accuracy. Seven teams participated in the battle and proposed a variety of successful approaches leveraging data analysis, model-based detection mechanisms, and rule checking. Results were presented at the Water Distribution Systems Analysis Symposium (World Environmental and Water Resources Congress) in Sacramento, California on May 21–25, 2017. This paper summarizes the BATADAL problem, proposed algorithms, results, and future research directions.

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.