Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies
arXiv:2606.18567v1 Announce Type: cross Abstract: This paper presents a methodology-centered transfer learning framework for fragility adaptation under domain shift, class imbalance, and scarce target labels while preserving engineering interpretability and supporting decision-making under uncertainty. Four transfer learning strategies (instance-based, parameter-based, hierarchical Bayesian, and multi-source) are demonstrated through three complementary case studies: (i) instance-based transfer learning via importance weighting, demonstrated on coastal bridge fragility using Hurricane Katrina
This paper addresses a growing need for robust AI methods to handle real-world data challenges in critical infrastructure modeling, leveraging advancements in transfer learning.
Improved fragility modeling through advanced AI can lead to more resilient infrastructure and better disaster preparedness, directly impacting economic stability and public safety.
The application of sophisticated AI, particularly transfer learning, can make structural modeling more adaptive and accurate, especially where data is sparse or imbalanced.
- · Civil Engineering
- · Insurance Industry
- · Disaster Management Agencies
- · AI/ML researchers
- · Static Modeling Approaches
- · Regions unprepared for climate impacts
More accurate predictive models for infrastructure vulnerability are developed and deployed.
Reduced economic losses from natural disasters due to improved preventative measures and reconstruction planning.
Enhanced resilience of global supply chains and urban centers against environmental and structural stresses.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG