Space‐Time Causal Discovery in Earth System Science: A Local Stencil Learning Approach

Journal Article · Fri Jul 11 00:00:00 EDT 2025 · Journal of Geophysical Research: Machine Learning and Computation

DOI:https://doi.org/10.1029/2024JH000546· OSTI ID:2585941

Nichol, J. Jake ^[1]; Weylandt, Michael ^[2]; Fricke, G. Matthew ^[3]; Moses, Melanie E. ^[4]; Bull, Diana L. ^[5]; Swiler, Laura Painton ^[5]

---

1. Univ. of New Mexico, Albuquerque, NM (United States); Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
2. City Univ. of New York (CUNY), NY (United States). Baruch College. Dept. of Natural Science
3. Univ. of New Mexico, Albuquerque, NM (United States)
4. Univ. of New Mexico, Albuquerque, NM (United States); Santa Fe Inst. (SFI), Santa Fe, NM (United States)
5. Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Causal discovery tools enable scientists to infer meaningful relationships from observational data, spurring advances in fields as diverse as biology, economics, and climate science. Despite these successes, the application of causal discovery to space-time systems remains immensely challenging due to the high-dimensional nature of the data. For example, in climate sciences, modern observational temperature records over the past few decades regularly measure thousands of locations around the globe. To address these challenges, we introduce Causal Space-Time Stencil Learning (CaStLe), a novel meta-algorithm for discovering causal structures in complex space-time systems. CaStLe leverages regularities in local space-time dependencies to learn governing global dynamics. This local perspective eliminates spurious confounding and drastically reduces sample complexity, making space-time causal discovery practical and effective. For causal discovery, CaStLe flexibly accepts any appropriately adapted time series causal discovery algorithm to recover local causal structures. These advances enable causal discovery of geophysical phenomena that were previously unapproachable, including non-periodic, transient phenomena such as volcanic eruption plumes. Regularities in local space-time dependencies are transformed into informative spatial replicates, which actually improve CaStLe's performance when applied to ever-larger spatial grids. We successfully apply CaStLe to discover the atmospheric dynamics governing the climate response to the 1991 Mount Pinatubo volcanic eruption. We provide validation experiments to demonstrate the effectiveness of CaStLe over existing causal-discovery frameworks on a range of geophysics-inspired benchmarks while identifying the method's limitations and domains where its assumptions may not hold.

• Research Organization: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA)
• Grant/Contract Number: NA0003525
• OSTI ID: 2585941
• Report Number(s): SAND--2025-08626J; 1751588
• Journal Information: Journal of Geophysical Research: Machine Learning and Computation, Journal Name: Journal of Geophysical Research: Machine Learning and Computation Journal Issue: 3 Vol. 2; ISSN 2993-5210
• Publisher: American Geophysical Union (AGU)
• Country of Publication: United States
• Language: English