Exploring Non-Linear Dependencies in Atmospheric Data with Mutual Information

Abstract

Relations between atmospheric variables are often non-linear, which complicates research efforts to explore and understand multivariable datasets. We describe a mutual information approach to screen for the most significant associations in this setting. This method robustly detects linear and non-linear dependencies after minor data quality checking. Confounding factors and seasonal cycles can be taken into account without predefined models. We present two case studies of this method. The first one illustrates deseasonalization of a simple time series, with results identical to the classical method. The second one explores associations in a larger dataset of many variables, some of them lognormal (trace gas concentrations) or circular (wind direction). The examples use our Python package ‘ennemi’.

Keywords

• correlation detection
• variable selection
• mutual information
• exploratory data analysis