Efficient Interdependent Systems Recovery Modeling with DeepONets
This work addresses the challenge of quantifying societal resilience to disruptive events for infrastructure planners, but it is incremental as it applies an existing ML method to a new domain with limited scale.
The paper tackled the computationally expensive problem of simulating recovery in large-scale interdependent critical infrastructure systems by applying Deep Operator Networks (DeepONets) to accelerate modeling, achieving satisfactory prediction performance for out-of-sample data in a simple case with four systems and sixteen states.
Modeling the recovery of interdependent critical infrastructure is a key component of quantifying and optimizing societal resilience to disruptive events. However, simulating the recovery of large-scale interdependent systems under random disruptive events is computationally expensive. Therefore, we propose the application of Deep Operator Networks (DeepONets) in this paper to accelerate the recovery modeling of interdependent systems. DeepONets are ML architectures which identify mathematical operators from data. The form of governing equations DeepONets identify and the governing equation of interdependent systems recovery model are similar. Therefore, we hypothesize that DeepONets can efficiently model the interdependent systems recovery with little training data. We applied DeepONets to a simple case of four interdependent systems with sixteen states. DeepONets, overall, performed satisfactorily in predicting the recovery of these interdependent systems for out of training sample data when compared to reference results.