A Review of Using Deep Learning Technology in the Built Environment of Disaster Management Phases
Abstract
Türkiye is a country on the Alpine-Himalayan earthquake zone and needs an effective disaster management plan, with its geography experiencing severe seismic activities. In this respect, natural disaster risks can be reduced by using developing artificial intelligence technology and deep learning applications in the mitigation, preparedness, response, and recovery phases that constitute the disaster management plan. This study examines deep learning models, application areas, deep learning layers and libraries used, and how deep learning can be used in the four stages of disaster management through study examples in the literature. The study aims to examine the use of deep learning in architecture and disaster management phases based on the earthquake factor as a result of the literature review. As a result, when studies on deep learning are examined, disaster management studies closely related to the discipline of architecture are mainly in the response phase. However, the discipline of architecture plays an important role at every stage of disaster management. In this respect, as holistic studies and applications related to deep learning, architectural science, and effective disaster management increase, the loss of life and property due to disasters, especially earthquakes, will decrease. The study carried out is thought to be an important guide for future research.
Keywords
Artificial intelligence, deep learning, disaster management, earthquake, architecture
Thanks
National and international research and publication ethics have been complied with in the article. Ethics committee approval was not required in the study.
References
- Alimovski, E. (2019). Derin öğrenmeye dayalı güçlü yüz tanıma sistemi için gan ile veri çoğaltma (Master's thesis). İstanbul Sabahattin Zaim Üniversitesi Fen Bilimleri Enstitüsü, İstanbul.
- Amin, M. S. & Ahn, H. (2021). Earthquake disaster avoidance learning system using deep learning. Cognitive Systems Research, 66, 221-235.
- Baran Ergül, D., Varol Malkoçoğlu, A. B. & Acun Özgünler, S. (2022). Mimari tasarım karar verme süreçlerinde yapay zeka tabanlı bulanık mantık sistemlerinin değerlendirilmesi. Journal of Architectural Sciences and Applications, 7 (2), 878-899. DOI: 10.30785/mbud.1117910
- Bingöl, K., Er Akan, A., Örmecioğlu, H. T. & Er, A. (2020). Depreme dayanıklı mimari tasarımda yapay zeka uygulamaları: Derin öğrenme ve görüntü işleme yöntemi ile düzensiz taşıyıcı sistem tespiti. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 35(4), 2197-2210. DOI: 10.17341/gazimmfd.647981
- Chalapathy, R. & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
- Chaoxian, L., Haigang, S. & Shan, Z. (2023). Efficient building damage assessment from post-disaster aerial video using lightweight deep learning models, International Journal of Remote Sensing, 44:22, 6954-6980, DOI: 10.1080/01431161.2023.2277163
- Chaudhuri, N. & Bose, I. (2020). Exploring the role of deep neural networks for post-disaster decision support. Decision Support Systems, 130, 113234.
- Chen, T., Li, M., Li, Y., Lin, M., Wang, N., Wang, M. ... & Zhang, Z. (2015). Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems. arXiv preprint arXiv:1512.01274.
- CloudTime Talk. (2022). Deep learning (derin öğrenme) nedir. Access address (12.06.2023): https://cloudtalktime.com/deep-learning-derin-ogrenme-nedir/
- Dahl, R., Norouzi, M. & Shlens, J. (2017). Pixel recursive super resolution. In Proceedings of the IEEE international Conference on Computer Vision (pp. 5439-5448).