Fast-Track Code-Based Seismic Vulnerability Screening with Machine Learning: Evidence from 300 Italian Buildings

Procedia Structural Integrity 2026 Open access

Read full text
Authors: Angelo Aloisio, Francesco Irti, Marco Martino Rosso, Giuseppe Quaranta, Cristoforo Demartino, Massimo Fragiacomo
DOI: 10.1016/j.prostr.2025.12.001
Cited by: 1
References: 24

Abstract

The study introduces a data-driven method for estimating a code-based seismic vulnerability index for roughly 300 Italian buildings. Detailed surveys, experimental tests, and numerical analyses produced about 15 mixed-type predictors. These inputs fed several predictive algorithms, in particular logistic regression and an artificial neural network (ANN). After rebalancing the classes by adjusting the vulnerability cut-off, the ANN classifies buildings into two risk groups with better than 85% accuracy. SHAP analysis reveals how much each feature influences the prediction, providing a transparent tool to help authorities prioritise seismic-risk mitigation.

Fields of Study & Subjects

Seismic Performance and Analysis Seismology and Earthquake Studies Masonry and Concrete Structural Analysis

Publication details

Journal / source
Procedia Structural Integrity
Publisher
Elsevier BV
Volume
78
Pages
1–8
Publication date
1 January 2026
Language
EN