PSI - Issue 78

Available online at www.sciencedirect.com

ScienceDirect

Procedia Structural Integrity 78 (2026) 1382–1388

© 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: Post-earthquake usability; Machine learning; Masonry buildings; Seismic risk; SHAP interpretability; Abstract This study proposes a machine-learning-assisted approach for developing predictive models of the building usability class following seismic events. The training data used here were derived from surveys conducted after the 2016 2017 Central Italy earthquake, collected via Rapid Post-Earthquake Damage Evaluation (AeDES) forms. These forms document key structural and nonstructural characteristics, along with observed damage, across nine sections. Additionally, seismic intensity measures are incorporated to enhance prediction accuracy, providing physics-based insights into the structural demands experienced by the surveyed buildings. The machine learning models are trained to predict the post-earthquake usability classification of buildings across four classes: immediately accessible (class A), usable only after emergency interventions (class B), partially unusable (class C), and fully unusable (class E). The robustness and interpretability of the resulting ML models are also assessed, considering feature importance SHapley Additive exPlanations (SHAP) functions. Findings from this study underscore the potential of machine learning techniques to support rapid post-emergency response and seismic risk mitigation strategies. XX ANIDIS Conference Machine-Learning-assisted predictors for post-earthquake masonry building usability class Marco Martino Rosso a, *, Angelo Aloisio b , Luca Di Battista c , Berardo Di Giacomantonio d , Massimo Fragiacomo b , Giuseppe C. Marano a , Cristoforo Demartino e , Giuseppe Quaranta f a Department of Structural, Geotechnical and Building Engineering, Politecnico di Torino, Turin, Italy b Department of Civil, Construction-Architectural and Environmental Engineering, University of L'Aquila, L'Aquila, Italy c Provveditorato interregionale per il Lazio, l'Abruzzo e la Sardegna d Special Office for Reconstruction (Ufficio Speciale Ricostruzione Sisma 2016) - Abruzzo, Teramo, Italy e Department of Architecture, Roma Tre University, Rome, Italy f Department of Structural and Geotechnical Engineering, Sapienza University, Rome, Italy

* Corresponding author. Tel.: +39-011-090-4907; E-mail address: marco.rosso@polito.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.2025.12.176