Fast Seismic Assessment of Built Urban Areas with the Accuracy of Mechanical Methods Using a Feedforward Neural Network

Capacity curves obtained from nonlinear static analyses are widely used to perform seismic assessments of structures as an alternative dynamic analysis. This paper presents a novel ‘en masse’ method assess the vulnerability urban areas swiftly and with accuracy mechanical methods. At core this methodology is calculation capacity low-rise reinforced concrete buildings using neural networks, where no modeling building required. The predicted minimal error, needing only basic geometric material parameters be specified. As first implementation, typology prismatic defined training set more than 7000 generated. calculated through push-over analysis SAP2000. results feature prediction 100-point in single run network while maintaining very low mean absolute error. proposes that improves current assessment tools by providing fast accurate large sets environments.