Hypersonic aircraft uncertain trajectory prediction method based on depth Gaussian process

The invention discloses a hypersonic flight vehicle uncertain trajectory prediction method based on a depth Gaussian process. The hypersonic flight vehicle uncertain trajectory prediction method comprises the steps of 1, obtaining multiple groups of parameter data related to flight of a hypersonic flight vehicle; step 2, taking each group of parameter data as an input variable, and constructing a training sample set in cooperation with a time number corresponding to the input variable; step 3, establishing a depth Gaussian process model; step 4, based on the training sample set in the step 2, establishing a mapping relation under training sample conditional probability by adopting the deep Gaussian process model obtained in the step 3, and obtaining an optimal solution through calculation; and step 5, taking the optimal solution obtained in the step 4 as a weight parameter of a deep Gaussian process model, taking a test sample in the training sample set as model input, and implementing trajectory prediction t