Shape-preserving prediction for stationary functional time series

This article presents a novel method for prediction of stationary functional time series, in particular trajectories that share similar pattern but display variable phases. The limitation most the existing methodologies series is they only consider vertical variation (amplitude, scale, or shift). To overcome this limitation, we develop shape-preserving (SP) incorporates both and horizontal variation. One major advantage our proposed ability to preserve shape functions. Moreover, SP does not involve unnatural transformations can be easily implemented using software packages. utility demonstrated analysis non-metanic hydrocarbons (NMHC) concentration. demonstrates by captures common better than methods also provides competitive accuracy.