Journal of the Korea Institute of Building Construction (한국건축시공학회지)

The Korean Institute of Building Construction (한국건축시공학회)
권호 표지
DOI QR코드

DOI QR Code

A Foundational Study on Deep Learning for Assessing Building Damage Due to Natural Disasters

자연재해로 인한 건물의 피해 평가를 위한 딥러닝 기초 연구

  • Received : 2024.04.17
  • Accepted : 2024.05.21
  • Published : 2024.06.20
Download PDF
⟨ Previous Next ⟩

Abstract

The escalating frequency and intensity of natural disasters and extreme weather events due to climate change have caused increasingly severe damage to societal infrastructure and buildings. Government agencies and private companies are actively working to evaluate these damages, but existing technologies and methodologies often fall short of meeting the practical demands for accurate assessment and prediction. This study proposes a novel approach to assess building damage resulting from natural disasters, focusing on typhoons-one of the most devastating natural hazards experienced in the country. The methodology leverages deep learning algorithms to evaluate typhoon-related damage, providing a comprehensive framework for assessment. The framework and outcomes of this research can provide foundational data for the evaluation of natural disaster-induced damage over the entire life cycle of buildings and can be applied in various other industries and research areas for assessing risk of damage.

기후 변화에 따른 자연재해와 이상기상의 빈도 및 심도가 날로 증가하면서, 사회기반시설과 건축물에 미치는 영향도 점차 커지고 있다. 이러한 문제에 대응하기 위해 다양한 정부 기관과 민간 부문에서는 이로인한 피해를 정확히 평가하려는 노력을 기울이고 있지만, 현실에 부합하는 정밀한 피해 예측과 평가는 여전히 도전적인 과제로 남아 있으며, 현재의 기술 수준으로는 부족함이 많다. 이러한 배경 하에, 본 연구는 우리나라에서 발생하는 주요 자연재해 중 하나인 태풍에 의한 건축물 피해를 분석하여, 해당 피해를 정확히 평가할 수 있는 방법론을 제시하고자 한다. 딥러닝 알고리즘을 활용한 평가 방식과 프레임워크를 도입하여, 태풍으로 인한 건물 피해 평가에 관한 연구를 진행하였다. 본 연구의 결과는 건물의 수명주기 전반에 걸친 자연재해 피해 평가에 필요한 기본 데이터를 제공하고, 다양한 산업 및 연구 영역에서 위험 평가에 활용이 가능하다.

Keywords

Acknowledgement

This research was funded by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(2022R1F1A106314113) and supported by research fund from Songwon University2024(A2024-20).

References

  1. Kim JM, Kim T, Son K, Yum SG, Ahn S. Measuring vulnerability of typhoon in residential facilities: Focusing on typhoon maemi in south korea. Sustainability. 2019 May;11(10):1-11.
  2. Kim JM, Son K, Yum SG, Ahn S. Typhoon vulnerability analysis in south korea utilizing damage record of typhoon maemi. Advances in Civil Engineering. 2020 Sep;2020(3):1-10. https://doi.org/10.1155/2020/8885916
  3. IContribution of Working Group II to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. Climate change 2014: impacts, adaptation, and vulnerability. Cambridge (UK): Intergovernmental Panel on Climate Change; 2014. Part A, Global and Sectoral Aspects; 1820 p.
  4. Kim JM, Son S, Lee S, Son K. Cost of climate change: Risk of building loss from typhoon in South Korea. Sustainability. 2020 Aug;12(17)1-11.
  5. Ulbrich U, Fink AH, Klawa M, Pinto JG. Three extreme storms over Europe in December 1999. Weather. 2001 Apr;56(3):70-80. https://doi.org/10.1002/j.1477-8696.2001.tb06540.x
  6. Blake ES, Landsea C, Gibney EJ. The deadliest, costliest, and most intense united states tropical cyclones from 1851 to 2010 (and other frequently requested hurricane facts). FL: National Hurricane Center; 2011. 49 p.
  7. Sanders DEA, Brix A, Duffy P, Forster W, Hartington T, Jones G, Levi C, Paddam P, Papachristou D, Perry G, Rix S, Ross F, Smith AJ, Seth A, Westcott D, Wilkinson M. The management of losses arising from extreme events. London (UK): Convention General Insurance Study Group GIRO; 2002. 261 p.
  8. Howard K, Robert M, Christophe VB. Risk analysis for extreme events: Economic incentives for reducing future losses. MD: National Institute of Standards and Technology; 2004. 103 p. Report No.: NIST GCR 04-871
  9. Kim JM, Woods PK, Park YJ, Kim T, Son K. Predicting hurricane wind damage by claim payout based on Hurricane Ike in Texas. Geomatics, Natural Hazards and Risk. 2016;7(5):1513-25. https://doi.org/10.1080/19475705.2015.1084540
  10. Al Najar M, Thoumyre G, Bergsma EW, Almar R, Benshila R, Wilson DG. Satellite derived bathymetry using deep learning. Machine Learning. 2021 Jul;112:1107-30.
  11. Yi Y, Zhang W. A new deep-learning-based approach for earthquake-triggered landslide detection from single-temporal rapideye satellite imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020 Oct;13:6166-76. https://doi.org/10.1109/JSTARS.2020.3028855
  12. Shane Crawford P, Hainen AM, Graettinger AJ, van de Lindt JW, Powell L. Discrete-outcome analysis of tornado damage following the 2011 Tuscaloosa, Alabama, tornado. Natural Hazards Review. 2020 Jul;21(4):04020040. https://doi.org/10.1061/(ASCE)NH.1527-6996.0000396
  13. Moishin M, Deo RC, Prasad R, Raj N, Abdulla S. Designing deep-based learning flood forecast model with ConvLSTM hybrid algorithm. IEEE Access. 2021 Mar;9:50982-93. https://doi.org/10.1109/ACCESS.2021.3065939
  14. Khosravi K, Panahi M, Golkarian A, Keesstra SD, Saco PM, Bui DT, Lee S. Convolutional neural network approach for spatial prediction of flood hazard at national scale of Iran. Journal of Hydrology. 2020 Sep;591:125552. https://doi.org/10.1016/j.jhydrol.2020.125552
  15. Kim JM, Bae J, Son S, Son K, Yum SG. Development of model to predict natural disaster-induced financial losses for construction projects using deep learning techniques. Sustainability. 2021 May;13(9):5304. https://doi.org/10.3390/su13095304
  16. Kim JM, Yum SG, Park H, Bae J. A deep learning algorithm-driven approach to predicting repair costs associated with natural disaster indicators: The case of accommodation facilities. Journal of Building Engineering. 2021 Oct;42:103098. https://doi.org/10.1016/j.jobe.2021.103098
  17. Kim JM, Son K, Kim YJ. Assessing regional typhoon risk of disaster management by clustering typhoon paths. Environment, Development and Sustainability. 2019 Oct;21(1):2083-96. https://doi.org/10.1007/s10668-018-0086-2
  18. Kim JM, Yum SG, Park H, Bae J. Strategic framework for natural disaster risk mitigation using deep learning and cost-benefit analysis. Natural Hazards and Earth System Sciences. 2022 Jun;22(6):2131-44. https://doi.org/10.5194/nhess-22-2131-2022
  19. D'Ayala D, Copping A, Wang H. A conceptual model for multi-hazard assessment of the vulnerability of historic buildings. Structural Analysis of Historical Constructions: Possibilities of Numerical and Experimental Techniques, Proceedings of the Fifth International Conference. New Delhi (India): Macmillian; 2006. p. 121-40.
  20. Yum SG, Kim JM, Wei HH. Development of vulnerability curves of buildings to windstorms using insurance data: An empirical study in South Korea. Journal of Building Engineering. 2021 Feb;34:101932. https://doi.org/10.1016/j.jobe.2020.101932
  21. De Silva DG, Kruse JB, Wang Y. Spatial dependencies in wind-related housing damage. Natural Hazards. 2008 Mar;47(3):317-30. https://doi.org/10.1007/s11069-008-9221-y
  22. Betsis S, Kalogirou M, Aretoulis G, Pertzinidou M. Work accidents correlation analysis for construction projects in Northern Greece 2003-2007: A retrospective study. Safety. 2019 May;5(2):33. https://doi.org/10.3390/safety5020033
  23. Kim JM, Lim KK, Yum SG, Son S. A deep learning model development to predict safety accidents for sustainable construction: A case study of fall accidents in south korea. Sustainability. 2022 Jan;14(3):1583. https://doi.org/10.3390/su14031583
  24. Ahmed S. Causes and effects of accident at construction site: A study for the construction industry in Bangladesh. International Journal of Sustainable Construction Engineering and Technology. 2019 Dec;10(2):18-40.
  25. Ajayi A, Oyedele L, Owolabi H, Akinade O, Bilal M, Davila Delgado JM, Akanbi L. Deep learning models for health and safety risk prediction in power infrastructure projects. Risk Analysis. 2020 Oct;40(10):2019-39. https://doi.org/10.1111/risa.13425
  26. Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B. Liu T, Wang X, Wang G, Cai J, Chen T. Recent advances in convolutional neural networks. Pattern Recognition. 2018 May;77:354-77. https://doi.org/10.1016/j.patcog.2017.10.013