PSI - Issue 78

Available online at www.sciencedirect.com

ScienceDirect

Procedia Structural Integrity 78 (2026) 1839–1846

© 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of XX ANIDIS Conference organizers Keywords: Structural health monitoring · Post earthquake vulnerability analysis · Bridge network · Bayesian network · Bayesian model updating · Transfer learning. Markov Chain Monte Carlo (MCMC) Abstract Safety assessment of infrastructural systems after an earthquake is crucial for informed decision-making regarding emergency actions, rehabilitation, strengthening, and reconstruction, as well as prioritization in budget allocation for post-earthquake recon struction. This is particularly pivotal for critical infrastructure such as the transportation networks, as damage or loss of functionality in these structures can lead to severe human and economic consequences, particularly following a disaster such as an earthquake. A widely adopted approach to analytically estimate the safety of a structure involves the comparison between seismic demand and structural capacity. The accuracy in the estimation of these two components can be highly improved using data collected from structural health monitoring systems. However, in most cases, the number of assets equipped with sensors is limited due to eco nomic and logistical constraints. To address this challenge, a machine learning-based methodology is proposed for the reliability assessment of highway bridge networks. The methodology presented in this paper focuses on estimating the seismic capacity of reinforced concrete (RC) bridges and introduces a transfer learning framework that enables the extrapolation of information from sensor-equipped (monitored) bridges to those without instrumentation (non-monitored), utilizing a Bayesian network architecture. XX ANIDIS Conference A new transfer-learning methodology for seismic capacity among similar structures in a network after an earthquake Pooria Mesbahi a , Enrique Garc´ıa-Mac´ıas b , Laura Ierimonti a , Marco Breccolotti a , Filippo Ubertini a, ∗ a Department of Civil and Environmental Engineering, University of Perugia (UNIPG), Via G. Duranti, 93, 06125 Perugia, Italy b Department of Structural Mechanics and Hydraulic Engineering, University of Granada, Campus Universitario de Fuentenueva s / n, 18071 Granada, Spain

1. Introduction

The rapid and reliable assessment of structural capacity in the aftermath of an earthquake is a key requirement for ensuring public safety and guiding emergency response and recovery operations. In particular, the seismic resilience of transportation infrastructure, such as highway bridge networks, plays a critical role in minimizing disruption and supporting post-disaster logistics. A common strategy for safety evaluation involves comparing seismic demand with

∗ Corresponding author. Tel.: + 390755853954 ; fax: + 390755853897. E-mail address: filippo.ubertini@unipg.it

2452-3216 © 2025 The Authors. Published by ELSEVIER B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of XX ANIDIS Conference organizers 10.1016/j.prostr.2025.12.234