Applications of artificial intelligence for disaster management
- PDF / 2,540,975 Bytes
- 59 Pages / 439.37 x 666.142 pts Page_size
- 100 Downloads / 300 Views
Applications of artificial intelligence for disaster management Wenjuan Sun1 · Paolo Bocchini1 · Brian D. Davison2 Received: 1 February 2019 / Accepted: 16 June 2020 © Springer Nature B.V. 2020
Abstract Natural hazards have the potential to cause catastrophic damage and significant socioeconomic loss. The actual damage and loss observed in the recent decades has shown an increasing trend. As a result, disaster managers need to take a growing responsibility to proactively protect their communities by developing efficient management strategies. A number of research studies apply artificial intelligence (AI) techniques to process disasterrelated data for supporting informed disaster management. This study provides an overview of current applications of AI in disaster management during its four phases: mitigation, preparedness, response, and recovery. It presents example applications of different AI techniques and their benefits for supporting disaster management at different phases, as well as some practical AI-based decision support tools. We find that the majority of AI applications focus on the disaster response phase. This study also identifies challenges to inspire the professional community to advance AI techniques for addressing them in future research. Keywords Disaster resilience · Disaster management · Artificial intelligence
1 Introduction Natural hazards have caused catastrophic damage and significant socioeconomic loss, showing an increasing trend (Hoeppe 2016). Statistics for 2017 indicate economic losses from natural hazards in the USA exceed $300 billion; Hurricane Harvey alone has caused $125 billion in socioeconomic losses (Wilts 2018). These adverse impacts pose challenges * Wenjuan Sun [email protected] Paolo Bocchini [email protected] Brian D. Davison [email protected] 1
Department of Civil and Environmental Engineering, Lehigh University, Bethlehem, PA 18015, USA
2
Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA 18015, USA
13
Vol.:(0123456789)
Natural Hazards
to disaster response managers, who face increasingly tight resources and an exhausted workforce, and such challenges force local authorities to re-evaluate their policies for disaster management. There are large volumes of data generated daily, including real data and simulation data. Both types of data can be used to support disaster management. The advancement of information communication technologies, such as social media, telecommunication data, and remote sensing, makes large volumes of real data available (Eguchi et al. 2008; Boccardo and Tonolo 2014; Rawat et al. 2015; Adeel et al. 2018; Novellino et al. 2018). Sometimes, real data are scarce. In research communities, many computational models are developed to generate simulation data for estimating the disaster-induced impact and identifying vulnerable structures, such as IN-CORE (Ellingwood et al. 2016) and PRAISys (The PRAISys Team 2018). Regardless of data type, acquiring, managing, and processing big data in a sho
Data Loading...
