The Probabilistic Backbone of Data-Driven Complex Networks: An example in Climate
Data Analysis, Statistics and Probability
2020-11-03 v2 Atmospheric and Oceanic Physics
Machine Learning
Abstract
Correlation Networks (CNs) inherently suffer from redundant information in their network topology. Bayesian Networks (BNs), on the other hand, include only non-redundant information (from a probabilistic perspective) resulting in a sparse topology from which generalizable physical features can be extracted. We advocate the use of BNs to construct data-driven complex networks as they can be regarded as the probabilistic backbone of the underlying complex system. Results are illustrated at the hand of a global climate dataset.
Cite
@article{arxiv.1912.03758,
title = {The Probabilistic Backbone of Data-Driven Complex Networks: An example in Climate},
author = {Catharina Graafland and José M. Gutiérrez and Juan M. López and Diego Pazó and Miguel A. Rodríguez},
journal= {arXiv preprint arXiv:1912.03758},
year = {2020}
}