Building Damage Detection Using Deep Learning Architecture with Satellite Images: The Case of the 6 February 2023 Kahramanmaraş Earthquake

##plugins.themes.academic_pro.article.sidebar##

Published Dec 24, 2024
https://doi.org/10.56158/jpte.2024.94.3.02
Download
FULL ARTICLE - PDF
Statistic
Vol. 3 No. 02 (2024): December

##plugins.themes.academic_pro.article.main##

Zeynep Aygün
Department of Computer Engineering, Engineering Faculty, Amasya University, Amasya, Turkey
https://orcid.org/0009-0000-8032-3333
Merve Kocaman
Department of Computer Engineering, Engineering Faculty, Amasya University, Amasya, Turkey
https://orcid.org/0009-0002-9662-6659
Salih Aydemir
Department of Computer Engineering, Engineering Faculty, Amasya University, Amasya, Turkey
https://orcid.org/0000-0003-0069-3479
Berkant Konakoğlu
Department of Architecture and Urban Planning, Vocational School of Technical Sciences, Amasya University, Amasya
https://orcid.org/0000-0002-8276-587X

Abstract

Turkey is located in a region with a high density of fault lines, which makes it susceptible to a significant earthquake risk. The Kahramanmaraş earthquake on February 6, 2023, was one of the most devastating in recent years, causing extensive damage and loss. This study aims to support post-disaster rapid response and rescue operations by using deep learning techniques to detect and classify damaged and intact buildings from satellite images. Satellite images of the Kahramanmaraş and Antakya regions, with a resolution of 8192x4537, were obtained via Google Earth Pro. The images were labeled as damaged or undamaged using the Labelme editor, which generated JSON format files for the labeled images. Using Google Colab, the JSON files and unlabeled images were merged, and buildings were cropped and categorized into two classes: damaged and undamaged. As a preprocessing step, interpolation was applied, resulting in 2211 images with a size of 128x128. A Convolutional Neural Network [2] algorithm was created using TensorFlow, a Python library, via Google Colab. The performance metrics, including accuracy, loss, F1 score, ROC curve, precision, recall, and confusion matrix values, were compared based on the experiments.

##plugins.themes.academic_pro.article.details##

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite
Aygün, Z. ., Kocaman, M., Aydemir, S., & Konakoğlu, B. (2024). Building Damage Detection Using Deep Learning Architecture with Satellite Images: The Case of the 6 February 2023 Kahramanmaraş Earthquake. International Journal of Pioneering Technology and Engineering, 3(02), 53–61. https://doi.org/10.56158/jpte.2024.94.3.02

References

  1. . Ji, M., Liu, L., Du, R., and Buchroithner, M.F.,2019, A comparative study of texture and convolutional neural network features for detecting collapsed buildings after earthquakes using pre-and post-event satellite imagery, J Remote Sensing, 11(10): 1202.
  2. . Shahriar, N.,2023, What is convolutional neural network–CNN (Deep Learning), J Electronic resource.
  3. . Saito, K., Spence, R.J., Going, C., and Markus, M.,2004,Using high-resolution satellite images for post-earthquake building damage assessment: a study following the 26 January 2001 Gujarat earthquake, J Earthquake spectra, 20(1): 145-169.
  4. . Oommen, T., Rebbapragada, U., and Cerminaro, D.,2012, Earthquake damage assessment using objective image segmentation: a case study of 2010 Haiti earthquake, GeoCongress 2012: State of the Art and Practice in Geotechnical Engineering. 3069-3078.
  5. . Sugiyama, M. and Abe, H.S.K,2002, Detection of earthquake damaged areas from aerial photographs by using color and edge information. Proceedings of the 5th Asian Conference on Computer Vision, Melbourne, Australia.
  6. . Chen, Z. and Hutchinson, T.C.,2010, Image‐based framework for concrete surface crack monitoring and quantification, J Advances in Civil Engineering, 2010(1): 215295.
  7. . Ghaffarian, S., Kerle, N., Pasolli, E., and Jokar Arsanjani, J.,2009, Post-disaster building database updating using automated deep learning: An integration of pre-disaster OpenStreetMap and multi-temporal satellite data, J Remote sensing, 11(20): 2427.
  8. . Serifoglu Yilmaz, C., Yilmaz, V., Tansey, K., and Aljehani, N.S.,2023, Automated detection of damaged buildings in post-disaster scenarios: a case study of Kahramanmaraş (Türkiye) earthquakes on February 6, 2023, J Natural Hazards, 119(3): 1247-1271.
  9. . Sonka, M., Hlavac, V., and Boyle, R.,2013, Image processing, analysis and machine vision: Springer.
  10. . LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P.,1998, Gradient-based learning applied to document recognition, J Proceedings of the IEEE, 86(11): 2278-2324.
  11. . Zaccone, G.,2016, Getting started with TensorFlow: Packt Publishing ISBN.
  12. . Goodfellow, I., Bengio, Y.,2016, and Courville, A., Deep learning, vol. 29, MIT Press.
  13. . Clevert, D.-A.,2015, Fast and accurate deep network learning by exponential linear units (elus), J arXiv preprint arXiv:.07289.
  14. . Maas, A.L., Hannun, A.Y. , and Ng, A.Y.,2013, Rectifier nonlinearities improve neural network acoustic models. Proc. icml: Atlanta, GA.
  15. . Elfwing, S., Uchibe, E., and Doya, K.,2018, Sigmoid-weighted linear units for neural network function approximation in reinforcement learning, J Neural networks, 107: 3-11.
  16. . Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V.,2019, Searching for mobilenetv3. Proceedings of the IEEE/CVF international conference on computer vision.
  17. . Misra, D.,2019, Mish: A self regularized non-monotonic activation function, J arXiv preprint arXiv:.08681.
  18. . LeCun, Y., Bottou, L.,2002, Orr, G.B., and Müller, K.-R., Efficient backprop, Neural networks: Tricks of the trade, Springer. 9-50.
  19. . Bishop, C.M. and Nasrabadi, N.M.,2006, Pattern recognition and machine learning, 4: Springer.
  20. . Bridle, J.,1989, Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters, J Advances in neural information processing systems, 2.
  21. . Kingma, D.P.,2014, Adam: A method for stochastic optimization, J arXiv preprint arXiv:.07289.
  22. . Duchi, J., Hazan, E., and Singer, Y.,2011, Adaptive subgradient methods for online learning and stochastic optimization, J Journal of machine learning research, 12(7).
  23. . Zeiler, M.D.,2012, ADADELTA: an adaptive learning rate method, J arXiv preprint arXiv.
  24. . Montavon, G., Orr, G., and Müller, K.-R.,2012, Neural networks: tricks of the trade, 7700: springer.
  25. . Tieleman, T.,2012, Lecture 6.5‐rmsprop: Divide the gradient by a running average of its recent magnitude, J COURSERA: Neural networks for machine learning, 4(2): 26.