Examinando por Materia "Seismic risk assessment"

Mostrando 1 - 6 de 6
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Universidad EAFIT. Departamento de Economía y Finanzas; Research in Spatial Economics (RISE)
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Universidad EAFIT. Departamento de Ingeniería de Producción; Materiales de Ingeniería
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Automatic detection of building typology using deep learning methods on street level images
    (PERGAMON-ELSEVIER SCIENCE LTD, 2020-03-20) Duque, J.; Gonzalez, D.; Rueda Plata, Diego; Acevedo, A.; Ramos, R.; Betancourt, A.; García, S.; Mecánica Aplicada
    An exposure model is a key component for assessing potential human and economic losses from natural disasters. An exposure model consists of a spatially disaggregated description of the infrastructure and population of a region under study. Depending on the size of the settlement area, developing such models can be a costly and time-consuming task. In this paper we use a manually annotated dataset consisting of approximately 10,000 photos acquired at street level in the urban area of Medellín to explore the potential for using a convolutional neural network (CNN) to automatically detect building materials and types of lateral-load resisting systems, which are attributes that define a building's structural typology (which is a key issue in exposure models for seismic risk assessment). The results of the developed model achieved a precision of 93% and a recall of 95% when identifying nonductile buildings, which are the buildings most likely to be damaged in an earthquake. Identifying fine-grained material typology is more difficult, because many visual clues are physically hidden, but our model matches expert level performances, achieving a recall of 85% and accuracy scores ranging from 60% to 82% on the three most common building typologies, which account for 91% of the total building population in Medellín. Overall, this study shows that a CNN can make a substantial contribution to developing cost-effective exposure models. © 2020 Elsevier Ltd
  • No hay miniatura disponible
    Ítem
    Detección automática para identificar la tipología de los edificios en Medellín
    (Universidad EAFIT, 2020-12-01) Martinez Guerrero, Christian Alexander; Martinez-Guerrero, Christian Alexander; Gonzalez, Daniela; Rueda Plata, Diego; Acevedo, Ana B.; Duque, Juan C.; Ramos Pollán, Raul; Betancourt, Alejandro; García, Sebastian; Research in Spatial Economics; Mecánica Aplicada
  • No hay miniatura disponible
    Ítem
    Seismic risk assessment for the residential buildings of the major three cities in Colombia: Bogotá, Medellín, and Cali
    (EARTHQUAKE ENGINEERING RESEARCH INST, 2020-01-01) Acevedo A.B.; Yepes-Estrada C.; González D.; Silva V.; Mora M.; Arcila M.; Posada G.; Mecánica Aplicada
    This study presents a seismic risk assessment and a set of earthquake scenarios for the residential building stock of the three largest metropolitan centers of Colombia: Bogotá, Medellín and Cali (with 8.0, 2.5, and 2.4 million inhabitants, respectively). A uniform methodology was followed for the development of the seismic hazard, vulnerability, and exposure models, thus allowing a direct comparison between the seismic risk of the different cities. Risk metrics such as exceedance probability curves and average annual losses were computed for each city. The earthquake scenarios were selected considering events whose direct economic impact is similar to the aggregated loss for a probability of exceedance of 10% in 50 years. Results show a higher mean aggregate loss ratio for Cali and similar mean aggregate loss ratios for Bogotá and Medellín. All of the models used in this study are openly accessible, enabling risk modelers, engineers, and stakeholders to explore them for disaster risk management. © The Author(s) 2020.
  • No hay miniatura disponible
    Ítem
    Seismic risk assessment for the residential buildings of the major three cities in Colombia: Bogotá, Medellín, and Cali
    (EARTHQUAKE ENGINEERING RESEARCH INST, 2020-01-01) Acevedo A.B.; Yepes-Estrada C.; González D.; Silva V.; Mora M.; Arcila M.; Posada G.; Acevedo A.B.; Yepes-Estrada C.; González D.; Silva V.; Mora M.; Arcila M.; Posada G.; Universidad EAFIT. Departamento de Ingeniería de Producción; Materiales de Ingeniería
    This study presents a seismic risk assessment and a set of earthquake scenarios for the residential building stock of the three largest metropolitan centers of Colombia: Bogotá, Medellín and Cali (with 8.0, 2.5, and 2.4 million inhabitants, respectively). A uniform methodology was followed for the development of the seismic hazard, vulnerability, and exposure models, thus allowing a direct comparison between the seismic risk of the different cities. Risk metrics such as exceedance probability curves and average annual losses were computed for each city. The earthquake scenarios were selected considering events whose direct economic impact is similar to the aggregated loss for a probability of exceedance of 10% in 50 years. Results show a higher mean aggregate loss ratio for Cali and similar mean aggregate loss ratios for Bogotá and Medellín. All of the models used in this study are openly accessible, enabling risk modelers, engineers, and stakeholders to explore them for disaster risk management. © The Author(s) 2020.