Rapid prediction of earthquake casualties is vital to improve the efficiency of emergency rescue and reduce social losses. Using the Delphi process, nine feature attributes affecting post-earthquake casualties are identified. Corresponding membership functions for the feature attributes are established based on fuzzy theory. The objective weights of feature attributes obtained from the entropy technology are applied to modify the subjective weights from Analytical Hierarchy Process (AHP). To expand the size of the case base, a new idea of collecting cases based on seismic intensity scenarios is proposed. A numerical experiment is carried out for all cases in the case base along the proposed fuzzy Case-Based Reasoning technical route. The average prediction error is only 14.93% .

The prediction of casualties in earthquakes is very important for improving the efficiency of emergency rescue measures and reducing the number of casualties. Given the time lag and poor accuracy of population density data published in statistical yearbooks, a Baidu heatmap is used in this study to accurately estimate the regional population density. Based on the standard support vector machine (SVM) prediction model, a piecewise loss function and a robust wavelet kernel function are proposed to effectively reduce the prediction error. Given a characteristic attribute set of factors related to earthquake casualties, the new prediction model is tested in 34 cases involving earthquake cases on the Chinese mainland since 2011. Compared with other prediction techniques, the proposed robust wavelet SVM can converge more quickly, and the prediction error is lower than that of the standard backpropagation neural network (BPNN) and standard SVM.