Delayformer: Spatiotemporal Transformation for Predicting High-Dimensional Dynamics.

ABSTRACT: Predicting time series is of great importance in various scientific and engineering fields. However, in the context of limited and noisy data, accurately predicting the dynamics of all variables in a high-dimensional system is a challenging task due to their nonlinearity and complex interactions. This study introduces the Delayformer framework for simultaneously predicting the dynamics of all variables by developing a novel multivariate spatiotemporal information (mvSTI) transformation that makes each observed variable into a delay-embedded state (vector) and further cross-learns those states from different variables. From a dynamical systems viewpoint, Delayformer predicts system states rather than individual variables, thus theoretically and computationally overcoming such nonlinearity a

SUBMITTER: Wang Z 

PROVIDER: S-EPMC12806438 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature