A machine learning framework to estimate a simple seismic vulnerability index from a photograph: the VULMA project

The paper presents the VULMA project as a machine learning framework for estimating a simplified seismic vulnerability index for existing buildings by exploiting photographs. In detail, VULMA, the acronym of VULnerability analysis using MAchine learning, is characterized by four consecutive modules, organized to be part of a specific processing pipeline that allows to train, test, and use the tool. The first module is Street VULMA, which allows to systematically download photographs from web services (e.g., Google Street View). The second module is Data VULMA, a tool for detecting structural features in the photographs and storing them in a database. The third module is Bi VULMA, which allows the training of different machine-learning models on the previously collected data. The fourth module is In VULMA, which assigns a vulnerability index to a building based on the detected features. The methodology has been applied to an initial database of photographs regarding reinforced concrete and masonry buildings, showing to be a good and fast way to perform a first screening of existing building portfolios and providing an alternative new method for developing risk mitigation strategies.