DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization

TL;DR

This survey reviews recent deep learning approaches in scientific visualization, focusing on scalar and vector field data, and discusses challenges and future research directions in the emerging DL4SciVis field.

Contribution

It provides a comprehensive classification and analysis of DL methods applied to SciVis, highlighting gaps and guiding future research in this specialized area.

Findings

DL methods are increasingly applied to SciVis problems.

Current research mainly focuses on scalar and vector field data.

Identifies key challenges and future directions for DL in SciVis.

Abstract

Since 2016, we have witnessed the tremendous growth of artificial intelligence+visualization (AI+VIS) research. However, existing survey papers on AI+VIS focus on visual analytics and information visualization, not scientific visualization (SciVis). In this paper, we survey related deep learning (DL) works in SciVis, specifically in the direction of DL4SciVis: designing DL solutions for solving SciVis problems. To stay focused, we primarily consider works that handle scalar and vector field data but exclude mesh data. We classify and discuss these works along six dimensions: domain setting, research task, learning type, network architecture, loss function, and evaluation metric. The paper concludes with a discussion of the remaining gaps to fill along the discussed dimensions and the grand challenges we need to tackle as a community. This state-of-the-art survey guides SciVis researchers in gaining an overview of this emerging topic and points out future directions to grow this research.