When analyzing heterogeneous data comprising numerical and categorical attributes, it is common to treat the different data types separately or transform the categorical attributes to numerical ones. The transformation has the advantage of facilitating an integrated multi-variate analysis of all attributes. We propose a novel technique for transforming categorical data into interpretable numerical feature vectors using Large Language Models (LLMs). The LLMs are used to identify the categorical attributes' main characteristics and assign numerical values to these characteristics, thus generating a multi-dimensional feature vector. The transformation can be computed fully automatically, but due to the interpretability of the characteristics, it can also be adjusted intuitively by an end user. We provide a respective interactive tool that aims to validate and possibly improve the AI-generated outputs. Having transformed a categorical attribute, we propose novel methods for ordering and color-coding the categories based on the similarities of the feature vectors.

Abstract Latent feature spaces of deep neural networks are frequently used to effectively capture semantic characteristics of a given dataset. In the context of spatio‐temporal ensemble data, the latent space represents a similarity space without the need of an explicit definition of a field similarity measure. Commonly, these networks are trained for specific data within a targeted application. We instead propose a general training strategy in conjunction with a deep neural network architecture, which is readily applicable to any spatio‐temporal ensemble data without re‐training. The latent‐space visualization allows for a comprehensive visual analysis of patterns and temporal evolution within the ensemble. With the use of SimilarityNet, we are able to perform similarity analyses on large‐scale spatio‐temporal ensembles in less than a second on commodity consumer hardware. We qualitatively compare our results to visualizations with established field similarity measures to document the interpretability of our latent space visualizations and show that they are feasible for an in‐depth basic understanding of the underlying temporal evolution of a given ensemble.

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.