Dataset for "Component-level seismic responses prediction of subway station from sparse monitoring points using a Transformer-GNN fusion network"
Abstract
The file code.rar contains the training code and the trained model used in this study. All other compressed files correspond to the dataset. Each sample is stored in a .txt file, where the first 12 columns represent the acceleration time histories of 12 monitoring points, and the last 8 columns represent the inter-story drift ratio time histories of 8 structural components.
Fields of Study & Subjects
Structural Health Monitoring Techniques
Seismic Performance and Analysis
Geotechnical Engineering and Underground Structures
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 8 March 2026
- Language
- EN
- Document type
- Dataset