Discovering Causal Relationships Between Time Series With Spatial Structure

2025-10-30

AI Summary

Existing causal discovery methods for spatiotemporal time-series data struggle to simultaneously address spatial autocorrelation, complex confounding, and high-dimensional scalability—often resorting to spatial aggregation or neglecting spatial dependencies altogether. Method: We propose the first spatiotemporal causal inference framework that unifies cross-context causal discovery with spatial confounder control. Building upon temporal causal modeling, it embeds a spatial-effect adjustment mechanism that explicitly models spatial autocorrelation and enables multi-context structural learning. Contribution/Results: The framework avoids spatial aggregation, scales efficiently to high-dimensional spatiotemporal variables, and significantly improves accuracy and interpretability of learned causal networks in real-world ecological and public health applications. It establishes a novel paradigm for causal modeling of complex systems where both temporal dynamics and spatial interdependence are essential.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Causal discovery is the subfield of causal inference concerned with estimating the structure of cause-and-effect relationships in a system of interrelated variables, as opposed to quantifying the strength of causal effects. As interest in causal discovery builds in fields such as ecology, public health, and environmental sciences where data is regularly collected with spatial and temporal structures, approaches must evolve to manage autocorrelation and complex confounding. As it stands, the few proposed causal discovery algorithms for spatiotemporal data require summarizing across locations, ignore spatial autocorrelation, and/or scale poorly to high dimensions. Here, we introduce our developing framework that extends time-series causal discovery to systems with spatial structure, building upon work on causal discovery across contexts and methods for handling spatial confounding in causal effect estimation. We close by outlining remaining gaps in the literature and directions for future research.

Problem

• Estimating causal relationships in spatially structured time series data
• Addressing spatial autocorrelation and confounding in causal discovery
• Developing scalable frameworks for high-dimensional spatiotemporal datasets

Innovation

• Extends time-series causal discovery to spatial systems
• Builds on cross-context causal discovery methods
• Addresses spatial autocorrelation and confounding issues