首页|On the compatibility of established methods with emerging artificial intelligence and machine learning methods for disaster risk analysis

On the compatibility of established methods with emerging artificial intelligence and machine learning methods for disaster risk analysis

扫码查看
原文链接
  • NETL
  • NSTL
  • Wiley
There is growing interest in leveraging advanced analytics, including artificial intelligence(AI) and machine learning (ML), for disaster risk analysis (RA) applications.These emerging methods offer unprecedented abilities to assess risk in settings wherethreats can emerge and transform quickly by relying on “learning” through datasets.There is a need to understand these emerging methods in comparison to the moreestablished set of risk assessment methods commonly used in practice. These existingmethods are generally accepted by the risk community and are grounded in useacross various risk application areas. The next frontier in RA with emerging methodsis to develop insights for evaluating the compatibility of those risk methods withmore recent advancements in AI/ML, particularly with consideration of usefulness,trust, explainability, and other factors. This article leverages inputs from RA and AIexperts to investigate the compatibility of various risk assessment methods, includingboth established methods and an example of a commonly used AI-based method for disasterRA applications. This article utilizes empirical evidence from expert perspectivesto support key insights on those methods and the compatibility of those methods. Thisarticle will be of interest to researchers and practitioners in risk-analytics disciplineswho leverage AI/ML methods.

artificial intelligencecausal inferencedisaster risk analysisexplainabilitymachine learningtrustworthiness

Shital Thekdi、Unal Tatar、Joost Santos、Samrat Chatterjee

展开 >

Robins School of Business, University ofRichmond, Richmond, Virginia, USA

Cybersecurity Department, University at AlbanyState University of New York, Albany, New York,USA

Engineering Management and SystemsEngineering Department, The George WashingtonUniversity, Washington, District of Columbia,USA

Data Sciences and Machine Intelligence Group,Pacific Northwest National Laboratory, Richland,Washington, USA

展开 >

2025

10.1111/risa.17640

Risk analysis

Risk analysis

ISSN：0272-4332
年,卷(期)：2025.45(4)
  • 52