Abstract
PurposeMeteorological disasters pose a significant risk to people’s lives and safety, and accurate prediction of weather-related disaster losses is crucial for bolstering disaster prevention and mitigation capabilities and for addressing the challenges posed by climate change. Based on the uncertainty of meteorological disaster sequences, the damping accumulated autoregressive GM(1,1) model (DAARGM(1,1)) is proposed.Design/methodology/approachFirstly, the autoregressive terms of system characteristics are added to the damping-accumulated GM(1,1) model, and the partial autocorrelation function (PACF) is used to determine the order of the autoregressive terms. In addition, the optimal damping parameters are determined by the optimization algorithm.FindingsThe properties of the model were analyzed in terms of the stability of the model solution and the error of the restored value. By fitting and predicting the losses affected by meteorological disasters and comparing them with the results of four other grey models, the validity of the new model in fitting and prediction was verified.Originality/valueThe dynamic damping trend factor is introduced into the grey generation operator so that the grey model can flexibly adjust the accumulative order of the sequence. On the basis of the damping accumulated grey model, the autoregressive term of the system characteristics is introduced to take into account the influence of the previous data, which is more descriptive of the development trend of the time series itself and increases the effectiveness of the model.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call