Assessment of Mechanical Robustness and Resilience in Urban Water Networks Under the Impact of Climate Change Using Metamodels and Artificial Intelligence

Urban water networks play a crucial role in urban functionality. These systems are indispensable elements of urban resilience. Nevertheless, these long-established systems are facing challenges due to population growth, urbanization, and climate change. These challenges reduce the mechanical robustness and resilience of these aging systems as an inevitable consequence. This study proposes a metamodeling approach to assess these robustness and resilience indices from a mechanical perspective, examining various 3D soil-pipe configurations under climate change effects. The necessary data were collected thoroughly before conducting the simulation. These configurations are identified using experimental designs, in particular, a central composite design to implement the metamodel, while sensitivity analysis identified the most important inputs. Predictive modeling using machine learning models, providing a more efficient alternative to complex traditional simulations and allowing for the consideration of scenarios not present in the original data. Ultimately, this approach identifies critical nodes and determines the mechanical robustness and resilience of the overall urban water network. The resulting tool offers decision-makers valuable support in managing unforeseen events.