PulseAugur
EN
LIVE 18:00:55

New transfer learning framework improves structural fragility modeling with scarce data

By PulseAugur Editorial · [2 sources] ·

A new paper introduces a transfer learning framework designed to improve structural fragility modeling, particularly in scenarios with limited data, domain shifts, and class imbalances. The methodology employs four transfer learning strategies, demonstrated across three case studies involving seismic and hurricane-related structural damage. The research highlights that direct transfer of existing models often fails in these challenging conditions, whereas targeted adaptation significantly enhances predictive accuracy and stability. AI

IMPACT Enhances predictive accuracy for structural damage assessment in low-data environments, potentially improving disaster preparedness and response.

RANK_REASON The cluster contains a research paper published on arXiv detailing a new methodology for transfer learning in structural fragility modeling.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New transfer learning framework improves structural fragility modeling with scarce data

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Narges Saeednejad, Jamie Ellen Padgett ·

    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-ma…

  2. arXiv stat.ML TIER_1 English(EN) · Jamie Ellen Padgett ·

    Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies

    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 str…

RELATED ENTITIES

RELATED TOPICS