Inferring causation from time series in Earth system sciences

Jakob Runge, Sebastian Bathiany, Erik Bollt, Gustau Camps-Valls, Dim Coumou, Ethan Deyle, Clark Glymour, Marlene Kretschmer, Miguel D. Mahecha, Jordi Muñoz-Marí, Egbert H. van Nes, Jonas Peters, Rick Quax, Markus Reichstein, Marten Scheffer, Bernhard Schölkopf, Peter Spirtes, George Sugihara, Jie Sun, Kun Zhang & 1 others Jakob Zscheischler

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

The heart of the scientific enterprise is a rational effort to understand the causes behind the phenomena we observe. In large-scale complex dynamical systems such as the Earth system, real experiments are rarely feasible. However, a rapidly increasing amount of observational and simulated data opens up the use of novel data-driven causal methods beyond the commonly adopted correlation techniques. Here, we give an overview of causal inference frameworks and identify promising generic application cases common in Earth system sciences and beyond. We discuss challenges and initiate the benchmark platform causeme.net to close the gap between method users and developers.

Original languageEnglish
Article number2553
JournalNature Communications
Volume10
Issue number1
DOIs
Publication statusPublished - 14 Jun 2019

Fingerprint

Earth Sciences
Systems science
Causality
Time series
Earth (planet)
Benchmarking
photographic developers
inference
dynamical systems
Dynamical systems
platforms
causes
Industry
Experiments

Cite this

Runge, J., Bathiany, S., Bollt, E., Camps-Valls, G., Coumou, D., Deyle, E., ... Zscheischler, J. (2019). Inferring causation from time series in Earth system sciences. Nature Communications, 10(1), [2553]. https://doi.org/10.1038/s41467-019-10105-3
Runge, Jakob ; Bathiany, Sebastian ; Bollt, Erik ; Camps-Valls, Gustau ; Coumou, Dim ; Deyle, Ethan ; Glymour, Clark ; Kretschmer, Marlene ; Mahecha, Miguel D. ; Muñoz-Marí, Jordi ; van Nes, Egbert H. ; Peters, Jonas ; Quax, Rick ; Reichstein, Markus ; Scheffer, Marten ; Schölkopf, Bernhard ; Spirtes, Peter ; Sugihara, George ; Sun, Jie ; Zhang, Kun ; Zscheischler, Jakob. / Inferring causation from time series in Earth system sciences. In: Nature Communications. 2019 ; Vol. 10, No. 1.
@article{02a3c7efc2b04a18873e57eeadb58709,
title = "Inferring causation from time series in Earth system sciences",
abstract = "The heart of the scientific enterprise is a rational effort to understand the causes behind the phenomena we observe. In large-scale complex dynamical systems such as the Earth system, real experiments are rarely feasible. However, a rapidly increasing amount of observational and simulated data opens up the use of novel data-driven causal methods beyond the commonly adopted correlation techniques. Here, we give an overview of causal inference frameworks and identify promising generic application cases common in Earth system sciences and beyond. We discuss challenges and initiate the benchmark platform causeme.net to close the gap between method users and developers.",
author = "Jakob Runge and Sebastian Bathiany and Erik Bollt and Gustau Camps-Valls and Dim Coumou and Ethan Deyle and Clark Glymour and Marlene Kretschmer and Mahecha, {Miguel D.} and Jordi Mu{\~n}oz-Mar{\'i} and {van Nes}, {Egbert H.} and Jonas Peters and Rick Quax and Markus Reichstein and Marten Scheffer and Bernhard Sch{\"o}lkopf and Peter Spirtes and George Sugihara and Jie Sun and Kun Zhang and Jakob Zscheischler",
year = "2019",
month = "6",
day = "14",
doi = "10.1038/s41467-019-10105-3",
language = "English",
volume = "10",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "Nature Publishing Group",
number = "1",

}

Runge, J, Bathiany, S, Bollt, E, Camps-Valls, G, Coumou, D, Deyle, E, Glymour, C, Kretschmer, M, Mahecha, MD, Muñoz-Marí, J, van Nes, EH, Peters, J, Quax, R, Reichstein, M, Scheffer, M, Schölkopf, B, Spirtes, P, Sugihara, G, Sun, J, Zhang, K & Zscheischler, J 2019, 'Inferring causation from time series in Earth system sciences' Nature Communications, vol. 10, no. 1, 2553. https://doi.org/10.1038/s41467-019-10105-3

Inferring causation from time series in Earth system sciences. / Runge, Jakob; Bathiany, Sebastian; Bollt, Erik; Camps-Valls, Gustau; Coumou, Dim; Deyle, Ethan; Glymour, Clark; Kretschmer, Marlene; Mahecha, Miguel D.; Muñoz-Marí, Jordi; van Nes, Egbert H.; Peters, Jonas; Quax, Rick; Reichstein, Markus; Scheffer, Marten; Schölkopf, Bernhard; Spirtes, Peter; Sugihara, George; Sun, Jie; Zhang, Kun; Zscheischler, Jakob.

In: Nature Communications, Vol. 10, No. 1, 2553, 14.06.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Inferring causation from time series in Earth system sciences

AU - Runge, Jakob

AU - Bathiany, Sebastian

AU - Bollt, Erik

AU - Camps-Valls, Gustau

AU - Coumou, Dim

AU - Deyle, Ethan

AU - Glymour, Clark

AU - Kretschmer, Marlene

AU - Mahecha, Miguel D.

AU - Muñoz-Marí, Jordi

AU - van Nes, Egbert H.

AU - Peters, Jonas

AU - Quax, Rick

AU - Reichstein, Markus

AU - Scheffer, Marten

AU - Schölkopf, Bernhard

AU - Spirtes, Peter

AU - Sugihara, George

AU - Sun, Jie

AU - Zhang, Kun

AU - Zscheischler, Jakob

PY - 2019/6/14

Y1 - 2019/6/14

N2 - The heart of the scientific enterprise is a rational effort to understand the causes behind the phenomena we observe. In large-scale complex dynamical systems such as the Earth system, real experiments are rarely feasible. However, a rapidly increasing amount of observational and simulated data opens up the use of novel data-driven causal methods beyond the commonly adopted correlation techniques. Here, we give an overview of causal inference frameworks and identify promising generic application cases common in Earth system sciences and beyond. We discuss challenges and initiate the benchmark platform causeme.net to close the gap between method users and developers.

AB - The heart of the scientific enterprise is a rational effort to understand the causes behind the phenomena we observe. In large-scale complex dynamical systems such as the Earth system, real experiments are rarely feasible. However, a rapidly increasing amount of observational and simulated data opens up the use of novel data-driven causal methods beyond the commonly adopted correlation techniques. Here, we give an overview of causal inference frameworks and identify promising generic application cases common in Earth system sciences and beyond. We discuss challenges and initiate the benchmark platform causeme.net to close the gap between method users and developers.

U2 - 10.1038/s41467-019-10105-3

DO - 10.1038/s41467-019-10105-3

M3 - Article

VL - 10

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

IS - 1

M1 - 2553

ER -

Runge J, Bathiany S, Bollt E, Camps-Valls G, Coumou D, Deyle E et al. Inferring causation from time series in Earth system sciences. Nature Communications. 2019 Jun 14;10(1). 2553. https://doi.org/10.1038/s41467-019-10105-3