Can we detect trends in natural disaster management with artificial intelligence? A review of modeling practices

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.

Computational models of community resilience

“…▪ Machine learning such as reinforcement learning and artificial intelligence were recently used to train game-winning agents (e.g., chess or strategy games) to evolve a community that wins battles and has an adequate use of resources (Tan and Guo, 2020). In reinforcement learning, software agents interact with an environment where they learn the best set of policies that maximize a reward.…”

Afet Risk Yönetiminde Yapay Zekâ Kullanımının Rolü

“…Kontrolü zor olan bu yapı için sistemlerden gelen verilerin depolanması, işlenmesi, haritalandırılması ve değerlendirilmesi için teknolojinin sağladığı olanaklara ihtiyaç vardır. Yenilikçi teknolojilerden yararlanılması ise, afet sonrasında olduğu kadar, afet öncesinde de riskin azaltılması adına oldukça önemli kazanımlar sağlayacaktır [5,[7][8][9]. Dünya genelinde yoğun nüfus ve yapılaşma pratiklerinin gözlemlendiği günümüzde, afetlerin sayısının ve sıklığının her geçen gün artmakta olduğu ve küresel iklim değişikliği sebebiyle farklı coğrafi bölgelerde çeşitlenen afet türlerinin görüldüğü açıkça ortadadır.…”

Flood Susceptibility Modeling in a Subtropical Humid Low-Relief Alluvial Plain Environment: Application of Novel Ensemble Machine Learning Approach

“…In recent years, modeling development has attracted the attention of many researchers in various scientific disciplines (Cheng and Han, 2016;He et al, 2018;Chen et al, 2021). Multicriteria decision-making (MCDM) (Opricovic and Tzeng, 2004;Abdullahi et al, 2015;De Brito and Evers, 2016;Turskis et al, 2019) and artificial intelligence (Suman et al, 2016;Guikema, 2020;Sun et al, 2020;Tan et al, 2021) models are very popular among researchers. There are a wide variety of flood inundation prediction models, e.g., statistical models including bivariate and multivariate (Tehrany et al, 2014), machine learning models, multi-criteria decision-making (MCDM) (Nachappa et al, 2020), and an ensemble of two or more models (Arabameri et al, 2020c).…”