Network-based data processing (left) relies on choices made for network connectivity and interpolation, notions that are absent within implicit neural representations (INR, right). A newly funded project, co-led by Lawrence Livermore National Laboratory researchers, will enable processing methods for visual analysis of INRs directly, without a traditional grid representation. Figure courtesy of Andrew Gillette.
Lawrence Livermore National Laboratory researchers are beginning work on a three-year project aimed at improving methods for visual analysis of large, heterogeneous data sets as part of a recent Department of Energy funding opportunity.
The joint project, titled “Neural Field Processing for Visual Analysis,” will be led at LLNL by co-principal investigator (PI) Andrew Gillette. Gillette is joined by lead PI Matthew Berger at Vanderbilt University and co-PI Joshua Levine at the University of Arizona.
While visualization is essential to understanding the results of numerical simulations, modern datasets can be large in size and heterogeneous in type, making direct processing computationally challenging, Gillette said.
The newly funded project will explore methods for processing ‘implicit neural representations’ (INRs), datasets that incorporate coordinate-based neural networks to represent scientific datasets efficiently and compactly. Currently, traditional processing algorithms and visual analysis techniques cannot be directly applied to INRs, Gillette explained.
“It is an honor to have been selected to conduct this research for the DOE,” Gillette said. “Fast and accurate visualization is essential to a wide variety of activities conducted in DOE laboratories; my goal over the next three years is to partner closely with application domain specialists and demonstrate how Advances in visualization methodologies can directly benefit scientific research.”
Gillette, who took over the PI role from former LLNL computer scientist Harsh Bhatia, said the project will encode key features of large data sets using emerging INR techniques. In addition, it will provide methods to quickly extract and interact with dataset features using only the compactly represented INR as a data surrogate, rather than maintaining access to the full dataset. As an example, the methods could be applied to visual interfaces for computational fluid dynamics simulations, which contain important fine-scale geometric and topological features in a large 3D region.
The new project was one of five funding awarded in September under the DOE’s “Data Visualization for Scientific Discovery, Decision Making, and Communication” Funding Opportunity Announcement (FOA). The goal of the FOA is to advance visualization techniques to address the challenges of rapidly expanding data generation and the complexity of the types of data produced by scientific experiments and simulations performed on modern supercomputers.
According to DOE, the advances will address emerging visualization technologies, enable better interdisciplinary collaboration, and improve communication across domains. Total funding for scientific data visualization research was $12.5 million.
/ Public communication. This material from the original organization/author(s) may be ad hoc in nature, edited for clarity, style and length. The views and opinions expressed are those of the author(s). See them in full here.