Abstract: Natural disasters present multifaceted challenges that necessitate swift and accurate responses. In the realm of post-earthquake safety assessments, the rapid and precise evaluation of damages is pivotal to ensure the optimal allocation of resources and facilitate effective emergency management. Many earthquake-prone nations employ standardized forms, such as the Italian AeDES, New Zealand Earthquake Rapid Assessment, and American ATC-20 Rapid Evaluation Safety Assessment, to capture and analyze damage data during inspections. However, the manual compilation of these forms can be error-prone, leading to potential misrepresentations of the actual damage scenario. The lecture introduces a Deep Learning-based methodology designed to enhance the accuracy and efficiency of these assessments. The tool can recognize, localize, and quantify damages by processing and analyzing drone photos of the affected buildings. Participants will gain insights into the methodology of this approach, its real-world applications, and its potential to reshape the future of natural disaster management using big data analytics.

Lecturer Short CV: Chief Technology Officer and Research Engineer at Latitudo 40 with over a decade of experience in the tech sector. He is currently finishing his PhD program at the PICUS Lab at the University of Naples Federico II. His main research field of interest is the application of Artificial Intelligence techniques for Earth Observation applications, in particular, combining Geospatial Data Analytics, Machine Learning, and Deep Learning.

Video:  Deep Learning for Post-Earthquake Safety Evaluation of Masonry Buildings