Machine Learning for Scientific Visualization: Ensemble Data Analysis

TL;DR

This paper develops deep learning methods to enhance the analysis and visualization of complex, high-dimensional scientific ensemble data, enabling better dimensionality reduction, flow estimation, and temporal interpolation.

Contribution

It introduces novel autoencoder strategies for stable low-dimensional embeddings and presents FLINT and HyperFLINT models for accurate, adaptable flow estimation and interpolation in scientific data.

Findings

Autoencoder-based embeddings are stable under partial labels.

FLINT achieves high-quality flow reconstruction without domain-specific assumptions.

HyperFLINT improves accuracy by conditioning on simulation parameters.

Abstract

Scientific simulations and experimental measurements produce vast amounts of spatio-temporal data, yet extracting meaningful insights remains challenging due to high dimensionality, complex structures, and missing information. Traditional analysis methods often struggle with these issues, motivating the need for more robust, data-driven approaches. This dissertation explores deep learning methodologies to improve the analysis and visualization of spatio-temporal scientific ensembles, focusing on dimensionality reduction, flow estimation, and temporal interpolation. First, we address high-dimensional data representation through autoencoder-based dimensionality reduction for scientific ensembles. We evaluate the stability of projection metrics under partial labeling and introduce a Pareto-efficient selection strategy to identify optimal autoencoder variants, ensuring expressive and reliable low-dimensional embeddings. Next, we present FLINT, a deep learning model for high-quality flow estimation and temporal interpolation in both flow-supervised and flow-unsupervised settings. FLINT reconstructs missing velocity fields and generates high-fidelity temporal interpolants for scalar fields across 2D+time and 3D+time ensembles without domain-specific assumptions or extensive finetuning. To further improve adaptability and generalization, we introduce HyperFLINT, a hypernetwork-based approach that conditions on simulation parameters to estimate flow fields and interpolate scalar data. This parameter-aware adaptation yields more accurate reconstructions across diverse scientific domains, even with sparse or incomplete data. Overall, this dissertation advances deep learning techniques for scientific visualization, providing scalable, adaptable, and high-quality solutions for interpreting complex spatio-temporal ensembles.