Mapping correlations and coherence: adjacency-based approach to data visualization and regularity discovery

TL;DR

This paper introduces an adjacency-based algorithm that maps the type and strength of correlations in complex data, enabling spatially resolved analysis of regularities in physical systems and other fields.

Contribution

The paper presents a novel correlation mapping algorithm that accounts for symmetry and spatial inhomogeneity, improving the visualization and discovery of data regularities.

Findings

The method effectively reveals different correlation regimes in physical and climate data.

It allows for spatial separation of regions with distinct correlation types.

The approach is simple, versatile, and applicable to various complex datasets.

Abstract

The development of science has been transforming man's view towards nature for centuries. Observing structures and patterns in an effective approach to discover regularities from data is a key step toward theory-building. With increasingly complex data being obtained, revealing regularities systematically has become a challenge. Correlation is a most commonly-used and effective approach to describe regularities in data, yet for complex patterns, spatial inhomogeneity and complexity can often undermine the correlations. We present an algorithm to derive maps representing the type and degree of correlations, by taking the two-fold symmetry of the correlation vector into full account using the Stokes parameter. The method allows for a spatially resolved view of the nature and strength of correlations between physical quantities. In the correlation view, a region can often be separated into different subregions with different types of correlations. Subregions correspond to physical regimes for physical systems, or climate zones for climate maps. The simplicity of the method makes it widely applicable to a variety of data, where the correlation-based approach makes the map particularly useful in revealing regularities in physical systems and alike. As a new and efficient approach to represent data, the method should facilitate the development of new computational approaches to regularity discovery.