Redirigiendo al acceso original de articulo en 23 segundos...
Inicio  /  Applied Sciences  /  Vol: 10 Par: 2 (2020)  /  Artículo
ARTÍCULO
TITULO

Discrimination of Earthquake-Induced Building Destruction from Space Using a Pretrained CNN Model

Min Ji    
Lanfa Liu    
Rongchun Zhang and Manfred F. Buchroithner    

Resumen

The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned VGGNet model outperformed the VGGNet model trained from scratch with increasing overall accuracy (OA) from 83.38% to 85.19% and Kappa from 60.69% to 67.14%. By taking advantage of dataset augmentation, OA and Kappa went up to 88.83% and 75.33% respectively, and the collapsed buildings were better recognized with a larger producer accuracy of 86.31%. The present study showed the potential of using the pretrained Convolutional Neural Network (CNN) model to identify collapsed buildings caused by earthquakes using very high-resolution satellite imagery.

 Artículos similares

       
 
Martina Hauser, Stefan Reinstaller, Martin Oberascher, Dirk Muschalla and Manfred Kleidorfer    
Owing to climate change, heavy rainfall events have increased in recent years, often resulting in urban flooding. Urban flood models usually consider buildings to be closed obstacles, which is not the case in reality. To address this research gap, an exi... ver más
Revista: Water

 
Jun Dong, Qingqing Chen, Guangxiang Yuan and Kaiyan Xie    
In large-scale water conservancy and hydropower projects, complex rock structures are considered to be the main factor controlling the stability of hydraulic structures. The classification of rock mass structure plays an important role in the safety of a... ver más
Revista: Applied Sciences

 
Srdan ?ivkovic, Nenad Stojkovic, Dragana Turnic, Marko Milo?evic and Marija Spasojevic ?urdilovic    
Welded structural hollow sections are becoming increasingly used in contemporary civil engineering buildings. More specific design techniques are needed for connections in steel structures with welded structural hollow sections than for traditional conne... ver más
Revista: Applied Sciences

 
Barbara Cardone, Valeria D?Ambrosio, Ferdinando Di Martino and Vittorio Miraglia    
One of the issues of greatest interest in urban planning today concerns the evaluation of the most vulnerable urban areas in the presence of different types of climate hazards. In this research, a hierarchical fuzzy MCDA model is implemented on a GIS-bas... ver más
Revista: Applied Sciences

 
Subin Kim, Heejin Hwang, Keunyeong Oh and Jiuk Shin    
The seismically deficient column details in existing reinforced concrete buildings affect the overall behavior of the building depending on the failure type of the column. The purpose of this study is to develop and validate a machine-learning-based pred... ver más
Revista: Applied Sciences