Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning
The adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3471 |
| _version_ | 1797502805570748416 |
|---|---|
| author | Peter Damilola Ogunjinmi Sung-Sik Park Bubryur Kim Dong-Eun Lee |
| author_facet | Peter Damilola Ogunjinmi Sung-Sik Park Bubryur Kim Dong-Eun Lee |
| author_sort | Peter Damilola Ogunjinmi |
| collection | DOAJ |
| description | The adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein, we present the effectiveness of automated deep learning in enhancing the assessment of damage caused by the 2017 Pohang earthquake. Six classical pre-trained convolutional neural network (CNN) models are implemented through transfer learning (TL) on a small dataset, comprising 1780 manually labeled images of structural damage. Feature extraction and fine-tuning TL methods are trained on the image datasets. The performances of various CNN models are compared on a testing image dataset. Results confirm that the MobileNet fine-tuned model offers the best performance. Therefore, the model is further developed as a web-based application for classifying earthquake damage. The severity of damage is quantified by assigning damage assessment values, derived using the CNN model and gradient-weighted class activation mapping. The web-based application can effectively and automatically classify structural damage resulting from earthquakes, rendering it suitable for decision making, such as in resource allocation, policy development, and emergency response. |
| first_indexed | 2024-03-10T03:41:22Z |
| format | Article |
| id | doaj.art-bf6148ac68144e05a81c1cbebfb7c377 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:41:22Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bf6148ac68144e05a81c1cbebfb7c3772023-11-23T09:19:01ZengMDPI AGSensors1424-82202022-05-01229347110.3390/s22093471Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer LearningPeter Damilola Ogunjinmi0Sung-Sik Park1Bubryur Kim2Dong-Eun Lee3School of Architecture, Civil, Energy, and Environment Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, KoreaDepartment of Civil Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, KoreaDepartment of Robot and Smart System Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, KoreaSchool of Architecture, Civil, Energy, and Environment Engineering, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, KoreaThe adoption of artificial intelligence in post-earthquake inspections and reconnaissance has received considerable attention in recent years, owing to its exponential increase in computation capabilities and inherent potential in addressing disadvantages associated with manual inspections. Herein, we present the effectiveness of automated deep learning in enhancing the assessment of damage caused by the 2017 Pohang earthquake. Six classical pre-trained convolutional neural network (CNN) models are implemented through transfer learning (TL) on a small dataset, comprising 1780 manually labeled images of structural damage. Feature extraction and fine-tuning TL methods are trained on the image datasets. The performances of various CNN models are compared on a testing image dataset. Results confirm that the MobileNet fine-tuned model offers the best performance. Therefore, the model is further developed as a web-based application for classifying earthquake damage. The severity of damage is quantified by assigning damage assessment values, derived using the CNN model and gradient-weighted class activation mapping. The web-based application can effectively and automatically classify structural damage resulting from earthquakes, rendering it suitable for decision making, such as in resource allocation, policy development, and emergency response.https://www.mdpi.com/1424-8220/22/9/3471transfer learningconvolutional neural networkearthquakeimage classificationdamage detection |
| spellingShingle | Peter Damilola Ogunjinmi Sung-Sik Park Bubryur Kim Dong-Eun Lee Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning Sensors transfer learning convolutional neural network earthquake image classification damage detection |
| title | Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning |
| title_full | Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning |
| title_fullStr | Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning |
| title_full_unstemmed | Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning |
| title_short | Rapid Post-Earthquake Structural Damage Assessment Using Convolutional Neural Networks and Transfer Learning |
| title_sort | rapid post earthquake structural damage assessment using convolutional neural networks and transfer learning |
| topic | transfer learning convolutional neural network earthquake image classification damage detection |
| url | https://www.mdpi.com/1424-8220/22/9/3471 |
| work_keys_str_mv | AT peterdamilolaogunjinmi rapidpostearthquakestructuraldamageassessmentusingconvolutionalneuralnetworksandtransferlearning AT sungsikpark rapidpostearthquakestructuraldamageassessmentusingconvolutionalneuralnetworksandtransferlearning AT bubryurkim rapidpostearthquakestructuraldamageassessmentusingconvolutionalneuralnetworksandtransferlearning AT dongeunlee rapidpostearthquakestructuraldamageassessmentusingconvolutionalneuralnetworksandtransferlearning |