Abstract
Causal discovery is the process of identifying potential cause-and-effect relationships from observed data. We use causal discovery to construct networks that track interactions around the globe based on time series data of atmospheric fields, such as daily geopotential height data. The key idea is to interpret large-scale atmospheric dynamical processes as information flow around the globe and to identify the pathways of this information flow using causal discovery and graphical models. We first review the basic concepts of using causal discovery, specifically constraint-based structure learning of probabilistic graphical models. Then we report on our recent progress, including some results on anticipated changes in the climate’s network structure for a warming climate and computational advances that allow us to move to three-dimensional networks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arnold A, Liu Y, Abe N (2007) Temporal causal modeling with graphical Granger methods. In: Proceedings of the 13th ACM SIGKDD international conference on knowledge discovery and data mining (SIGKDD’07), San Jose. 10pp
Bendito E, Carmona A, Encinas AM, Gesto JM (2007) Estimation of Fekete points. J Comput Phys 225:2354–2376. doi:10.1016/j.jcp.2007.03.017
Cano R, Sordo C, Gutierrez J (2004) Applications of Bayesian networks in meteorology. In: Gaámez JA et al (eds) Advances in Bayesian networks. Springer, Berlin/New York, pp 309–327
Chen X, Hoffman MM, Bilmes JA, Hesselberth JR, Noble WS (2010) A dynamic Bayesian network for identifying protein-binding footprints from single molecule-based sequencing data. Bioinformatics 26:i334–i342. ISMB 2010. doi:10.1093/bioinformatics/btq175
Chu T, Danks D, Glymour C (2005) Data driven methods for nonlinear Granger causality: climate teleconnection mechanisms. Technical report CMU-PHIL-171, Department of Philosophy, Carnegie Mellon University, Pittsburgh
Colombo D, Maathuis MH (2013) Order-independent constraint-based causal structure learning. (arXiv:1211.3295v2)
Cossentino M, Raimondi FM, Vitale MC (2001) Bayesian models of the pm10 atmospheric urban pollution. In: Proceedings of the ninth international conference on modeling, monitoring and management of air pollution: air pollution IX, Ancona, Italy. WIT press, Boston, pp 143–152
Deng Y, Ebert-Uphoff I (2014) Weakening of atmospheric information flow in a warming climate in the community climate system model. Geophys Res Lett 7. doi:10.1002/2013GL058646
Ebert-Uphoff I, Deng Y (2012a) Causal discovery for climate research using graphical models. J Clim 25(17):5648–5665. doi:10.1175/JCLI-D-11-00387.1
Ebert-Uphoff I, Deng Y (2012b) A new type of climate network based on probabilistic graphical models: results of Boreal winter versus summer. Geophys Res Lett 39(L19701):7. doi:10.1029/2012GL053269
Ebert-Uphoff I, Deng Y (2014) Causal discovery from spatio-temporal data with applications to climate science. In: 13th international conference on machine learning and applications, Detroit, 3–6 Dec, 8pp
El-dawlatly SE-d (2011) Graph-based methods for inferring neuronal connectivity from spike train ensembles. Ph.D. thesis, Electrical Engineering, Michigan State University. Available at http://etd.lib.msu.edu/islandora/object/etd%3A357/datastream/OBJ/view
Friedman N, Linial M, Nachman I, Pe’er D (2000) Using Bayesian networks to analyze expression data. J Comput Biol 7(3–4):601–620
Hlinka J, Hartman D, Vejmelka M, Runge J, Marwan N, Kurths J, Palus M (2013) Reliability of inference of directed climate networks using conditional mutual information. Entropy 15(6):2023–2045
Kalnay E, et al (1996) The NCEP/NCAR 40-year reanalysis project. Bull Am Meteorol Soc 77:437–471. doi:10.1175/1520–0477(1996)077<0437:TNYRP>2.0.CO;2
Kennett RJ, Korb KB, Nicholson AE (2001) Seabreeze prediction using Bayesian networks. In: Proceedings of the fifth Pacific-Asia conference on knowledge discovery and data minung (PAKDD’01), Hong Kong (PAKDD), pp 148–153
Kistler R, et al (2001) The NCEP-NCAR 50-year reanalysis: monthly means CD-ROM and documentation. Bull Am Meteorol Soc 82:247–267. doi:10.1175/1520-0477(2001)082¡0247:TNNYRM¿2.3.CO;2
Koller D, Friedman N (2009) Probabilistic graphical models – principles and techniques, 1st edn. MIT, Cambridge, 1280pp
Margolin AA, Nemenman I, Basso K, Wiggins C, Stolovitzky G, Dalla Favera R, Califano A (2006) Aracne: an algorithm for the reconstruction of gene regulatory networks in a mammalian cellular context. BMC Bioinformatics 7(Suppl.):S7. doi:10.1186/1471-2105-7-S1-S7
Neapolitan RE (2004) Learning Bayesian networks. Pearson Prentice Hall, Upper Saddle River, NJ, 674pp
Needham CJ, Bradford JR, Bulpitt AJ, Westhead DR (2007) A primer on learning in Bayesian networks for computational biology. PLoS Comput Biol 3(8):e129. doi:10.1371/journal.pcbi.0030129
Pearl J (1988) Probabilistic reasoning in intelligent systems: networks of plausible inference, 2nd printing. Morgan Kaufman, San Francisco, CA, 552pp
Runge J (2014) Detecting and quantifying causality from time series of complex systems. Ph.D. thesis, Humboldt-University Berlin. Available at http://edoc.hu-berlin.de/dissertationen/runge-jakob-2014-08-05/PDF/runge.pdf
Sachs K, Perez O, Pe’er D, Lauffenburger DA, Nolan GP (2005) Causal protein-signaling networks derived from multiparameter single-cell data. Science 22 308(5721):523–529. doi:10.1126/science.1105809
Shipley B (2002) Cause and correlation in biology: a user’s guide to path analysis, structural equations and causal inference, 1st edn. Cambridge University Press, Cambridge, 332p
Spirtes P, Glymour C (1991) An algorithm for fast recovery of sparse causal graphs. Soc Sci Comput Rev 9(1):67–72
Spirtes P, Glymour C, Scheines R (1993) Causation, prediction, and search. Springer lecture notes in statistics, 1st edn. Springer, New York, 526pp
Tsonis AA, Roebber PJ (2004) The architecture of the climate network. Physica A 333:497–504. doi:10.1016/j.physa.2003.10.045
Yin JH (2005) A consistent Poleward shift of the storm tracks in simulations of 21st century climate. Geophys Res Lett 32:L18701. doi:10.1029/2005GL023684
Zerenner T, Friedrichs P, Lehnerts K, Hense A (2014) A Gaussian graphical model approach to climate networks. Chaos 24:023103
Acknowledgements
Support for this work is provided by two grants of the NSF Climate and Large-Scale Dynamics (CLD) program, namely, grant AGS-1147601 awarded to Yi Deng and a collaborative grant (AGS-1445956 and AGS-1445978) awarded to both authors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ebert-Uphoff, I., Deng, Y. (2015). Using Causal Discovery Algorithms to Learn About Our Planet’s Climate. In: Lakshmanan, V., Gilleland, E., McGovern, A., Tingley, M. (eds) Machine Learning and Data Mining Approaches to Climate Science. Springer, Cham. https://doi.org/10.1007/978-3-319-17220-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-17220-0_11
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-17219-4
Online ISBN: 978-3-319-17220-0
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)