Can we detect trends in natural disaster management with artificial intelligence? A review of modeling practices
- PDF / 1,041,233 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 51 Downloads / 263 Views
Can we detect trends in natural disaster management with artificial intelligence? A review of modeling practices Ling Tan1 · Ji Guo2,3 · Selvarajah Mohanarajah4 · Kun Zhou5 Received: 31 July 2020 / Accepted: 11 November 2020 © Springer Nature B.V. 2020
Abstract There has been an unsettling rise in the intensity and frequency of natural disasters due to climate change and anthropogenic activities. Artificial intelligence (AI) models have shown remarkable success and superiority to handle huge and nonlinear data owing to their higher accuracy and efficiency, making them perfect tools for disaster monitoring and management. Accordingly, natural disaster management (NDM) with the usage of AI models has received increasing attention in recent years, but there has been no systematic review so far. This paper presents a systematic review on how AI models are applied in different NDM stages based on 278 studies retrieved from Elsevier Science, Springer LINK and Web of Science. The review: (1) enables increased visibility into various disaster types in different NDM stages from the methodological and content perspective, (2) obtains many general results including the practicality and gaps of extant studies and (3) provides several recommendations to develop innovative AI models and improve the quality of modeling. Overall, a comprehensive assessment and evaluation for the reviewed studies are performed, which tracked all stages of NDM research with the applications of AI models. Keywords Natural disaster management · Artificial intelligence · Stage analysis * Ling Tan [email protected] Ji Guo [email protected] Selvarajah Mohanarajah [email protected] Kun Zhou [email protected] 1
School of Applied Meteorology, Nanjing University of Information Science and Technology, Nanjing 210044, China
2
School of Economics and Management, Shanghai Maritime University, Shanghai 201306, China
3
Collaborative Innovation Center On Climate and Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China
4
School of Computer Science, Mathematics and Computer Science, University of North Carolina At Pembroke, Pembroke, NC 28372, USA
5
School of Management Science and Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China
13
Vol.:(0123456789)
Natural Hazards
1 Introduction According to the Emergency Events Database (EM-DAT), there were 348 natural disasters on average between 2008 and 2017. Associated with these disasters were 67,572 fatalities, 198.8 million injured or homeless people, and $166.7 billion economic losses per year (EM-DAT 2019). The intensity and frequency of natural disasters such as floods, storms, droughts, heat waves and wildfires have gradually increased, and the range affected has also continued to expand due to climate change and anthropogenic activities (Kalantari et al. 2019). Consequently, the influence caused by these disasters has created serious challenges to the sustainable development of
Data Loading...
