Embracing data irregularities in multivariate time series

GATE block setup. The transformation performed by the RNN is responsible for both incorporating into and translating the hidden representation in time to time . The updated latent representations at the target time are projected by a linear layer (LL) back into the original space. Data collection in many engineering fields involves multivariate time series gathered from a collection of sensors that operate independently of each other. These sensors often display various irregularities, such as different sampling rates and missing data. To manage these issues, complex preprocessing mechanisms are required, which become coupled with any statistical model trained with the transformed data. Modeling the motion of floating platforms anchored on seabeds from measurements acquired from sensors is a typical example. We propose and analyze a model in which each sensor is encoded using an independent time-informed recurrent neural network, information is propagated in a common latent space by a graph neural network, and a modified training method is used to induce temporal generalization of the model. Our method can generate forecasts in unseen frequencies, which provides empirical evidence that the model learns an implicit representation of the system’s time derivatives and is able to flexibly integrate the signal over the time domain. • A novel architecture is proposed to address irregularities in multivariate time series (MTS), including varying sampling rates, missing data, and time misalignments. • The model combines time-informed recurrent neural networks (RNNS) with graph neural networks (GNNs) for generalized temporal modeling. • A modified training method enables the model to generalize temporal patterns and generate forecasts at unseen frequencies. • Validation on real-world data from Floating Production, Storage, and Offloading units (FPSOs) demonstrates superior predictive accuracy and reduced preprocessing requirements.