Abstract
Earthquake casualty prediction is crucial for efficient and effective emergency management and response. In order to improve prediction reliability of earthquake casualties, correlation analysis and principal component analysis are used to select prediction covariates. Finally, five key indexes, including magnitude, epicenter intensity, population density, earthquake occurrence time and damaged building area, are chosen. According to the “two-stage” rule of earthquake casualties, a prediction model based on the modified partial Gaussian curve is proposed. In order to improve its prediction accuracy, the paper looked epicenter intensity and the casualty as the variables. And the partial Gaussian curve prediction model is modified by using the magnitude coefficient, population density coefficient, earthquake occurrence time coefficient and damaged building coefficient. The cross-validation experimental results show that the modified partial Gaussian curve has the advantages of good stability and high prediction accuracy comparing with the high-order nonlinearity, logarithmic curve, multivariate linearity, artificial neural network and so on. It can be used in practice from earthquake casualty prediction.
Similar content being viewed by others
References
Aghamohammadi H, Mesgari MS, Mansourian A, Molaei D (2013) Seismic human loss estimation for an earthquake disaster using neural network. Int J Environ Sci Technol 10(5):931–939
Aiko F, Robin S, Yutaka O et al (2010) Analytical study on vulnerability functions for casualty estimation in the collapse of adobe building induced by earthquake. Bull Earthq Eng 8:451–479
Ara S (2013) Analyzing population distribution and its effect on earthquake loss estimation in Sylhet, Bangladesh. Dissertation, University of Twente
He M, Zhou W (2011) Prediction of seismic casualties based on the seismic damage index. J Harbin Inst Technol 43(4):23–27
Jie Z, Huizhen G, Qi L (2011) Study on the model of earthquake casualty estimation based on wenchuan earthquake. China Saf Sci J 21(3):59–64
Liu J, Lin J (2012) Study on the evaluation method of earthquake casualties based on epicentral intensity. J Nat Disasters 21(5):113–119
Ma Y, Xie L (2000) Methodologies for assessment of earthquake casualty. Earthq Eng Eng Dyn 24(4):140–147
Max W, Sushil G, Philippe R (2017) Casualty estimates in two up-dip complementary Himalayan earthquakes. Seismol Res Lett 88(6):1508–1515
Muhammet G, Ali FG (2016) An artificial neural network based on earthquake casualty estimation model for Istanbul city. Nat Hazards 84:2163–2178
Samardjieva E, Oike K (1992) Modeling the number of casualties from earthquake. J Nat Disaster Sci 14(1):17–28
Shan Y, Haixia W, Yajie M (2005) Three-layer BP network model for estimation of casualties in an earthquake. J Earthq Eng Eng Vib 25(6):113–117
Shapira S, Aharonson-Daniel L et al (2015) Integrating epidemiological and engineering approaches in the assessment of human casualties in earthquakes. Nat Hazards 78(7):1447–1462
Shi W, Chen K, Xie Y et al (2012) Study on the estimation method of casualties of earthquake victims in Yunnan. J Seismol Res 35(3):387–392
Tian X, Zhu W (2012) Study on earthquake casualty estimation model based on principal component analysis and BP neural network analysis. Northwest Seismol J 34(4):365–368
Wang X et al (2011) ANN model for the estimation of life casualties in earthquake engineering. Syst Eng Procedia 1:55–60
Wen BC, Jiang C (2013) Forecasting emergency demand based on BP neural network and principal component analysis. Adv Inf Serv Sci 5(13):38–45
Wu H, Feng T, Hong Z (2013) Earthquake casualties prediction model based on remote sensing images. J Tongji Univ (Med Sci) 34(5):36–39
Xin T, Zhu R (2012) Study on earthquake casualties forecasting model based on principal component analysis and BP neural network analysis. China Earthq Eng J 34(4):365–368
Xing H, Zhonglin Z, Shaoyu W (2015) The prediction model of earthquake casualty based on robust wavelet v-SVM. Nat Hazards 77:717–732
Acknowledgements
The paper is supported by the Western Project of the National Social Science Fund (No. 18XGL016). We thank Huidong Jin, the famous scientist of CSIRO, data 61, Australia, for his help, experts and journal editors who reviewed this article and all scholars who provided references.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, X., Jin, H. An earthquake casualty prediction model based on modified partial Gaussian curve. Nat Hazards 94, 999–1021 (2018). https://doi.org/10.1007/s11069-018-3452-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11069-018-3452-3