Uncertainty‐aware Visualization of Regional Time Series Correlation in Spatio‐temporal Ensembles

Abstract

Given a time‐varying scalar field, the analysis of correlations between different spatial regions, i.e., the linear dependence of time series within these regions, provides insights into the structural properties of the data. In this context, regions are connected components of the spatial domain with high time series correlations. The detection and analysis of such regions is often performed globally, which requires pairwise correlation computations that are quadratic in the number of spatial data samples. Thus, operations based on all pairwise correlations are computationally demanding, especially when dealing with ensembles that model the uncertainty in the spatio‐temporal phenomena using multiple simulation runs. We propose a two‐step procedure: In a first step, we map the spatial samples to a 3D embedding based on a pairwise correlation matrix computed from the ensemble of time series. The 3D embedding allows for a one‐to‐one mapping to a 3D color space such that the outcome can be visually investigated by rendering the colors for all samples in the spatial domain. In a second step, we generate a hierarchical image segmentation based on the color images. From then on, we can visually analyze correlations of regions at all levels in the hierarchy within an interactive setting, which includes the uncertainty‐aware analysis of the region's time series correlation and respective time lags.

Snowflake: visualizing microbiome abundance tables as multivariate bipartite graphs

“…For downstream analysis that results in matrices (e.g., pairwise distances, similarities, and correlation), inspired by Evers et al (2021) , we propose using multidimensional scaling (MDS) to project the samples to a three-dimensional space. These new dimensions can then be translated to the CIELAB color space, in which a perceived change in color resembles its geometric distance.…”

A Tool for Visualization and Analysis of Neighbourhoods, Clusters, and Indicators during the COVID‐19 Pandemic

“…Spatiotemporal analysis may use visualization approaches to aggregate regions by their event occurrence similarities over time [26], derive dynamic urban causal analysis [27], and explore the correlation between regions [28] and cooccurrence of spatial events [29]. Given the spatiotemporal analysis capabilities, different risk visualization applications were developed.…”

Incorporating Texture Information into Dimensionality Reduction for High-Dimensional Images

“…The resulting color images are then used to aid the segmentation with the goal of identifying tissue segments with similar properties, according to the original attribute space. Recently, Evers et al [14] followed a similar approach to identify regional correlations in spatio-temporal weather ensemble simulations with the main difference of using MDS instead of t-SNE. Others combine dimensionality reduction with segmented image data.…”