Perception of earthquake and analysis of its impact factors based on interpretable machine learning: data from the 6 august 2023 earthquake in Pingyuan County, China

Erhao Zhang, Ning Ding (), Lixuan Yang, Yang Wang, Jiguang Shi and Yingjian Xu
Additional contact information
Erhao Zhang: People’s Public Security University of China
Ning Ding: People’s Public Security University of China
Lixuan Yang: People’s Public Security University of China
Yang Wang: People’s Public Security University of China
Jiguang Shi: People’s Public Security University of China
Yingjian Xu: People’s Public Security University of China

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2025, vol. 121, issue 6, No 18, 6829 pages

Abstract: Abstract In August 6, 2023, a 5.5 magnitude earthquake occurred in Pingyuan County, China. Numerous individuals who experienced the earthquake conveyed that they "sensed tremors but failed to recognize it as an earthquake", leading to a delayed implementation of self-protection measures when the earthquake occurred. In this paper, for investigating the causes of individual differences in earthquake perception, a questionnaire was designed and conducted locally one week after the earthquake with 340 responses. It’s found that those who perceived the earthquake occurrence took timely self-protection measures to minimize their damage. Consequently, the ability to perceive earthquake occurrences emerged as a pivotal factor constraining individuals' timely adoption of self-protection measures. To predict whether an individual can perceive the earthquake occurrence, a CatBoost model was trained on acquired data, achieving 92.2% accuracy. For further exploring the specific effect of impact factors on individual earthquake occurrence perception and its degree, we used SHAP (Shapley Additive Explanations) interpretable machine learning to explain the prediction results of model. It’s found that age exerted the most significant influence on earthquake perception, with older individuals more likely to perceive earthquakes compared to younger counterparts. Males have a higher level of earthquake occurrence perception than females, contrasting with prior research that suggested a higher level perception of risk degree and awareness of consequences among females. In contrast to conventional beliefs, experiencing earthquakes of low to moderate magnitudes did not significantly enhance an individual's perception of earthquake occurrences. This study contributes to the emergency management efforts of the earthquake administration.

Keywords: Risk perception; Earthquake; Machine learning; Shapley additive explanations (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-024-07073-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:121:y:2025:i:6:d:10.1007_s11069-024-07073-3

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-024-07073-3

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().