/GraphEM

Gaussian graphical models (aka Markov random fields) embedded within an Expectation Maximization algorithm

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

https://img.shields.io/github/last-commit/paleopresto/GraphEM/main https://img.shields.io/github/license/paleopresto/GraphEM https://img.shields.io/pypi/pyversions/GraphEM

GraphEM

GraphEM refers to the climate field reconstruction approach proposed by Guillot et al. (2015), and its name means Gaussian graphical models embedded within an EM (Expectation-Maximization) algorithm.

Documentation

Reference of the GraphEM algorithm

  • Guillot, D., Rajaratnam, B., & Emile-Geay, J. (2015). Statistical paleoclimate reconstructions via Markov random fields. The Annals of Applied Statistics, 9(1), 324–352. https://doi.org/10.1214/14-AOAS794

Published studies using GraphEM

  • Vaccaro, A., Emile-Geay, J., Guillot, D., Verna, R., Morice, C., Kennedy, J., & Rajaratnam, B. (2021). Climate field completion via Markov random fields – Application to the HadCRUT4.6 temperature dataset. Journal of Climate, 1(aop), 1–66. https://doi.org/10.1175/JCLI-D-19-0814.1
  • Neukom, R., Steiger, N., Gómez-Navarro, J. J., Wang, J., & Werner, J. P. (2019). No evidence for globally coherent warm and cold periods over the preindustrial Common Era. Nature, 571(7766), 550–554. https://doi.org/10.1038/s41586-019-1401-2
  • Wang, Jianghao, Emile-Geay, J., Guillot, D., McKay, N. P., & Rajaratnam, B. (2015). Fragility of reconstructed temperature patterns over the Common Era: Implications for model evaluation. Geophysical Research Letters, 42(17), 7162–7170. https://doi.org/10.1002/2015GL065265
  • Wang, J., Emile-Geay, J., Guillot, D., Smerdon, J. E., & Rajaratnam, B. (2014). Evaluating climate field reconstruction techniques using improved emulations of real-world conditions. Clim. Past, 10(1), 1–19. https://doi.org/10.5194/cp-10-1-2014