Dynamic Modes as Time Representation for Spatiotemporal Forecasting
This work addresses the challenge of capturing complex multi-scale periodicity in spatiotemporal forecasting for applications like urban planning and climate modeling, representing an incremental improvement over conventional time embeddings.
The paper tackled the problem of modeling long-range seasonal dependencies in spatiotemporal forecasting by introducing a data-driven time embedding method using Dynamic Mode Decomposition (DMD), which improved long-horizon forecasting accuracy, reduced residual correlation, and enhanced temporal generalization across urban mobility, highway traffic, and climate datasets.
This paper introduces a data-driven time embedding method for modeling long-range seasonal dependencies in spatiotemporal forecasting tasks. The proposed approach employs Dynamic Mode Decomposition (DMD) to extract temporal modes directly from observed data, eliminating the need for explicit timestamps or hand-crafted time features. These temporal modes serve as time representations that can be seamlessly integrated into deep spatiotemporal forecasting models. Unlike conventional embeddings such as time-of-day indicators or sinusoidal functions, our method captures complex multi-scale periodicity through spectral analysis of spatiotemporal data. Extensive experiments on urban mobility, highway traffic, and climate datasets demonstrate that the DMD-based embedding consistently improves long-horizon forecasting accuracy, reduces residual correlation, and enhances temporal generalization. The method is lightweight, model-agnostic, and compatible with any architecture that incorporates time covariates.