Spatiotemporal information conversion machine for time-series prediction

TL;DR

The paper introduces the spatiotemporal information conversion machine (STICM), a neural network framework that improves multistep-ahead time-series prediction by integrating spatial-temporal transformations and causal inference, demonstrating superior robustness and accuracy.

Contribution

The novel STICM framework combines STI transformation with temporal convolutional networks and causal inference, enabling more accurate and robust multistep time-series predictions without relying on explicit models.

Findings

Superior performance on benchmark and real-world datasets

Robustness to noise in multistep predictions

Effective inference of causal factors

Abstract

Making predictions in a robust way is a difficult task only based on the observed data of a nonlinear system. In this work, a neural network computing framework, the spatiotemporal information conversion machine (STICM), was developed to efficiently and accurately render a multistep-ahead prediction of a time series by employing a spatial-temporal information (STI) transformation. STICM combines the advantages of both the STI equation and the temporal convolutional network, which maps the high-dimensional/spatial data to the future temporal values of a target variable, thus naturally providing the prediction of the target variable. From the observed variables, the STICM also infers the causal factors of the target variable in the sense of Granger causality, which are in turn selected as effective spatial information to improve the prediction robustness of time-series. The STICM was successfully applied to both benchmark systems and real-world datasets, all of which show superior and robust performance in multistep-ahead prediction, even when the data were perturbed by noise. From both theoretical and computational viewpoints, the STICM has great potential in practical applications in artificial intelligence (AI) or as a model-free method based only on the observed data, and also opens a new way to explore the observed high-dimensional data in a dynamical manner for machine learning.