Assimilative Causal Inference

Abstract

Causal inference is fundamental across scientific disciplines, yet existing methods struggle to capture instantaneous, time-evolving causal relationships in complex, high-dimensional systems. In this paper, assimilative causal inference (ACI) is developed, which is a methodological framework that leverages Bayesian data assimilation to trace causes backward from observed effects. ACI solves the inverse problem rather than quantifying forward influence. It uniquely identifies dynamic causal interactions without requiring observations of candidate causes, accommodates short datasets, and, in principle, can be implemented in high-dimensional settings by employing efficient data assimilation algorithms. Crucially, it provides online tracking of causal roles that may reverse intermittently and facilitates a mathematically rigorous criterion for the causal influence range, revealing how far effects propagate. The effectiveness of ACI is demonstrated by complex dynamical systems showcasing intermittency and extreme events. ACI opens valuable pathways for studying complex systems, where transient causal structures are critical.

47 pages (Main Text pp. 1--17; Supplementary Information pp. 18--47), 11 figures (3 in Main Text, 8 in Supplementary Information). Published in Nature Communications. The MATLAB code used in the analyses and to generate the figures in this work can be found in https://github.com/marandmath/ACI_code . For further details visit https://mariosandreou.short.gy/ACI

References in corpus (11)

• Measuring Information Transfer
• Granger causality and transfer entropy are equivalent for Gaussian variables
• Detecting causal associations in large nonlinear time series datasets
• Causal Network Inference by Optimal Causation Entropy
• Causation Entropy Identifies Indirect Influences, Dominance of Neighbors and Anticipatory Couplings
• Quantifying Causal Coupling Strength: A Lag-specific Measure For Multivariate Time Series Related To Transfer Entropy
• Disentangling different types of El Niño episodes by evolving climate network analysis
• Estimating model evidence using data assimilation
• Causation entropy from symbolic representations of dynamical systems
• Detecting and Attributing Change in Climate and Complex Systems: Foundations, Green's Functions, and Nonlinear Fingerprints
• A data-driven framework for dimensionality reduction and causal inference in climate fields