Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks
Contemporary deep learning approaches for post-earthquake damage assessments based on 2D convolutional neural networks (CNNs) require encoding of ground motion records to transform their inherent 1D time series to 2D images, thus requiring high computing time and resources. This study develops a 1D...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/e2ae3fa7137a4d019489ac7204158710 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:e2ae3fa7137a4d019489ac7204158710 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:e2ae3fa7137a4d019489ac72041587102021-11-11T14:58:57ZFaster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks10.3390/app112198442076-3417https://doaj.org/article/e2ae3fa7137a4d019489ac72041587102021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9844https://doaj.org/toc/2076-3417Contemporary deep learning approaches for post-earthquake damage assessments based on 2D convolutional neural networks (CNNs) require encoding of ground motion records to transform their inherent 1D time series to 2D images, thus requiring high computing time and resources. This study develops a 1D CNN model to avoid the costly 2D image encoding. The 1D CNN model is compared with a 2D CNN model with wavelet transform encoding and a feedforward neural network (FNN) model to evaluate prediction performance and computational efficiency. A case study of a benchmark reinforced concrete (r/c) building indicated that the 1D CNN model achieved a prediction accuracy of 81.0%, which was very close to the 81.6% prediction accuracy of the 2D CNN model and much higher than the 70.8% prediction accuracy of the FNN model. At the same time, the 1D CNN model reduced computing time by more than 90% and reduced resources used by more than 69%, as compared to the 2D CNN model. Therefore, the developed 1D CNN model is recommended for rapid and accurate resultant damage assessment after earthquakes.Xinzhe YuanDustin TanksleyLiujun LiHaibin ZhangGenda ChenDonald WunschMDPI AGarticleseismic damage assessmentconvolutional neural networksfeedforward neural networksground motion recordswavelet transformTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9844, p 9844 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
seismic damage assessment convolutional neural networks feedforward neural networks ground motion records wavelet transform Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 |
| spellingShingle |
seismic damage assessment convolutional neural networks feedforward neural networks ground motion records wavelet transform Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Xinzhe Yuan Dustin Tanksley Liujun Li Haibin Zhang Genda Chen Donald Wunsch Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| description |
Contemporary deep learning approaches for post-earthquake damage assessments based on 2D convolutional neural networks (CNNs) require encoding of ground motion records to transform their inherent 1D time series to 2D images, thus requiring high computing time and resources. This study develops a 1D CNN model to avoid the costly 2D image encoding. The 1D CNN model is compared with a 2D CNN model with wavelet transform encoding and a feedforward neural network (FNN) model to evaluate prediction performance and computational efficiency. A case study of a benchmark reinforced concrete (r/c) building indicated that the 1D CNN model achieved a prediction accuracy of 81.0%, which was very close to the 81.6% prediction accuracy of the 2D CNN model and much higher than the 70.8% prediction accuracy of the FNN model. At the same time, the 1D CNN model reduced computing time by more than 90% and reduced resources used by more than 69%, as compared to the 2D CNN model. Therefore, the developed 1D CNN model is recommended for rapid and accurate resultant damage assessment after earthquakes. |
| format |
article |
| author |
Xinzhe Yuan Dustin Tanksley Liujun Li Haibin Zhang Genda Chen Donald Wunsch |
| author_facet |
Xinzhe Yuan Dustin Tanksley Liujun Li Haibin Zhang Genda Chen Donald Wunsch |
| author_sort |
Xinzhe Yuan |
| title |
Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| title_short |
Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| title_full |
Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| title_fullStr |
Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| title_full_unstemmed |
Faster Post-Earthquake Damage Assessment Based on 1D Convolutional Neural Networks |
| title_sort |
faster post-earthquake damage assessment based on 1d convolutional neural networks |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/e2ae3fa7137a4d019489ac7204158710 |
| work_keys_str_mv |
AT xinzheyuan fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks AT dustintanksley fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks AT liujunli fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks AT haibinzhang fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks AT gendachen fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks AT donaldwunsch fasterpostearthquakedamageassessmentbasedon1dconvolutionalneuralnetworks |
| _version_ |
1718437936987373568 |