Natural disasters, such as earthquakes, have always represented a danger to human life. Seismic risk assessment consists of the evaluation of existing buildings and their expected response in case of an earthquake; the exposure model of buildings plays a key role in risk calculations. With this respect, in recent years, advanced techniques have been developed to speed up and automatize the processes of data acquisition to data interpretation, although it is worth mentioning that the visual survey is essential to train and validate Machine Learning (ML) methods. In the present study, the identification of building types is conducted by exploiting the traditional visual survey to implement a Deep Learning (DL) classification model. As a first step, city mapping schemes are obtained by classifying buildings according to the main features (i.e., construction period and height classes). Then, Random Forest (RF), a supervised learning algorithm, is applied to classify different building types by exploiting all their attributes. The RF model is trained and tested on the cities of Neuchatel and Yverdon-Les-Bains. The decent accuracy of the results encourages the application of the method to different cities, with proper adjustments in datasets, features and algorithms.

Building typological classification in Switzerland using deep learning methods for seismic assessment / Casciato, A.; Khodaverdian, A.; Coletta, G.; Scussolini, L.; Lestuzzi, P.; Ceravolo, R.. - In: PROCEDIA STRUCTURAL INTEGRITY. - ISSN 2452-3216. - ELETTRONICO. - 44:(2023), pp. 1522-1529. [10.1016/j.prostr.2023.01.195]

Building typological classification in Switzerland using deep learning methods for seismic assessment

Casciato, A.;Coletta, G.;Scussolini, L.;Ceravolo, R.
2023

Abstract

Natural disasters, such as earthquakes, have always represented a danger to human life. Seismic risk assessment consists of the evaluation of existing buildings and their expected response in case of an earthquake; the exposure model of buildings plays a key role in risk calculations. With this respect, in recent years, advanced techniques have been developed to speed up and automatize the processes of data acquisition to data interpretation, although it is worth mentioning that the visual survey is essential to train and validate Machine Learning (ML) methods. In the present study, the identification of building types is conducted by exploiting the traditional visual survey to implement a Deep Learning (DL) classification model. As a first step, city mapping schemes are obtained by classifying buildings according to the main features (i.e., construction period and height classes). Then, Random Forest (RF), a supervised learning algorithm, is applied to classify different building types by exploiting all their attributes. The RF model is trained and tested on the cities of Neuchatel and Yverdon-Les-Bains. The decent accuracy of the results encourages the application of the method to different cities, with proper adjustments in datasets, features and algorithms.
File in questo prodotto:
File Dimensione Formato  
Procedia-Anidis-Casciato-1-s2.0-S2452321623002032-main.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 1.13 MB
Formato Adobe PDF
1.13 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2977521