Causal Discovery from Sparse Time-Series Data Using Echo State Network

TL;DR

This paper introduces a novel causal discovery method for sparse and irregular time-series data using Gaussian Process Regression for missing data imputation and Echo State Networks for causal inference, outperforming existing algorithms.

Contribution

The paper presents a new combined approach using Gaussian Processes and Echo State Networks to improve causal discovery in sparse, non-uniformly sampled time-series data.

Findings

Outperforms existing causal discovery algorithms in MCC and ROC metrics.

Effective in handling missing data and irregular sampling.

Demonstrates viability on complex chemical process data.

Abstract

Causal discovery between collections of time-series data can help diagnose causes of symptoms and hopefully prevent faults before they occur. However, reliable causal discovery can be very challenging, especially when the data acquisition rate varies (i.e., non-uniform data sampling), or in the presence of missing data points (e.g., sparse data sampling). To address these issues, we proposed a new system comprised of two parts, the first part fills missing data with a Gaussian Process Regression, and the second part leverages an Echo State Network, which is a type of reservoir computer (i.e., used for chaotic system modelling) for Causal discovery. We evaluate the performance of our proposed system against three other off-the-shelf causal discovery algorithms, namely, structural expectation-maximization, sub-sampled linear auto-regression absolute coefficients, and multivariate Granger Causality with vector auto-regressive using the Tennessee Eastman chemical dataset; we report on their corresponding Matthews Correlation Coefficient(MCC) and Receiver Operating Characteristic curves (ROC) and show that the proposed system outperforms existing algorithms, demonstrating the viability of our approach to discover causal relationships in a complex system with missing entries.