Sustainable structural health assessment of heritage masonry towers using artificial intelligence and data-driven monitoring: Insights from the civic tower of Matelica

This paper presents a data-driven Structural Health Monitoring (SHM) framework for the long-term preservation of heritage masonry towers, based on over two years of continuous monitoring of the Civic Tower of Matelica (Italy). Four triaxial energy efficient Micro Electro-Mechanical Systems (MEMS) accelerometers, permanently installed at the tower's corners, provided continuous data analysed using automated Operational Modal Analysis (OMA) and machine learning techniques. The integrated Artificial Intelligence (AI) -assisted approach enables tracking and predictive modeling of the tower's dynamic behavior under environmental and seismic influences, particularly following the 2016/’17 seismic sequence, while adjusting for environmental effects to ensure accurate assessments. The main objective is to assess structural health, reduce invasive inspections and unnecessary interventions, and extend the service life of the structure, thus promoting environmental sustainability. The findings demonstrate the potential of machine learning and AI-assisted SHM for enhancing the resilience and sustainable preservation of historic masonry buildings, offering a replicable model for cultural heritage conservation.