Abstract: The importance of the disaster information forecast is growing in the process of disaster relief. This paper presents an integrated forecasting model based on the TEI@I methodology for typhoon disaster relief materials reserving with the example of super typhoon Lekima. The empirical results reveal that TEI@I methodology integrated model can significantly improve the prediction performance over other simulation algorithms models presented in this study, especially the nonlinear prediction results adjusted NGA model of operation time reduced from 200s to 99.92s based on TEI@I methodology. The connotation of "decomposition before integration" in TEI@I methodology introduces the analysis and prediction of non-linear demand. TEI@I methodology can not only analyze the impact of the timeliness requirement of the external environment on the demand for relief materials, but also integrate the time series after analysis to improve the prediction accuracy of the model.

Key words: TEI@I methodology, NGA, typhoon disaster, timeliness