ASSIMILATE: Seismic Risk Assessment through Artificial Intelligence and Vibrations

ASSIMILATE — Seismic risk assessment through artificial intelligence and vibrations was an FCT research project that combined low-cost monitoring devices with machine learning to build a platform for vulnerability and damage assessment of buildings. It was coordinated by the University of Aveiro, with the Faculty of Engineering of the University of Porto (FEUP) and Fundação Ensino e Cultura Fernando Pessoa (UFP) as partners.

What the project did

After an earthquake, civil protection needs a quick picture of which buildings are damaged; before one, engineers need reliable models of how buildings will respond. ASSIMILATE addressed both:

• monitored a large number of buildings with low-cost vibration sensors;
• used the recorded data and machine learning to calibrate numerical models of those buildings;
• used data from past earthquakes to extend the framework, so that damage and losses can be estimated from near-real-time monitoring data.

The consortium brought together experience in seismic monitoring, vulnerability assessment and processing of large datasets with machine learning. The project had the support of the Portuguese Civil Protection Authority, the Portuguese Institute of the Sea and Atmosphere (IPMA), the National Laboratory for Civil Engineering (LNEC), the Global Earthquake Model Foundation and SafeHub, and contributes to the Sendai Framework for Disaster Risk Reduction and the UN Sustainable Development Goals.

Team at UFP

• Prof. Vítor Silva
• Prof. Feliz Gouveia
• Prof. Rui Silva Moreira
• Prof. José Torres
• André Costa, MSc student

At FEUP, the team was led by Prof. Humberto Varum.

Funding

Project PTDC/ECI-EGC/7244/2020, funded by national funds through FCT — Fundação para a Ciência e a Tecnologia, I.P. It ran from March 2021 to January 2024. DOI: 10.54499/PTDC/ECI-EGC/7244/2020.