Code and Data for a Real-time Structural Seismic Response Prediction Framework based on Transfer Learning and Unsupervised Learning

Conventional data-driven methods for predicting the seismic response of structures often require extensive data and computational resources. To address these challenges, we here publish a deep learning framework - code and data - that can efficiently and accurately predict the structural seismic responses. The framework overcomes aforementioned limitations by utilizing transfer learning based on the most relevant knowledge determined via the unsupervised learning technique. The framework leverages the seismic information history database to identify the most similar previous earthquake, and subsequently transfers the corresponding knowledge from the Structural Seismic Response network (SSR net) to predict structural responses caused by a new earthquake. This method significantly reduces the need for extensive training and data collection and provides efficient predictions. Case studies demonstrate the framework's ability to predict seismic structural responses effectively. The framework can reliably capture the complex nonlinear dynamics of structures under seismic loads and offer significant potential for advancing seismic fragility analyses and reliability assessments.