EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Turning Immersive Viewers into Analytical Workspaces: ASCRIBE-XR and Agent-Driven Scientific Visualization

Ronald Pandolfi iD, Luke Weidner, James Sethian iD, Jeffrey Donatelli iD, Daniela Ushizima iD

Journal of Imaging · 20.08.2026 · 12 (8) · 393

DOI: 10.3390/jimaging12080393 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 20.08.2026. Verfasst von Ronald Pandolfi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Applied Math and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: US Department of Energy (DOE) Office of Science, Advanced Scientific Computing Research (ASCR).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scientific visualization is changing from passive observation to active, AI-assisted collaboration. While Extended Reality (XR) has proven valuable for comprehending dense 3D arrays, traditional VR applications are typically deployed in rigid, single-purpose, and monolithic architectures. In this paper, we present the evolution of ASCRIBE-XR: a virtual reality platform backed by remote computation that has been re-engineered into a dynamic, service-oriented ecosystem. We introduce three core innovations that make immersive data analysis easier, faster, and more flexible when using multimodal scientific imaging. First, a lightweight Python REST interface decouples XR logic from the rendering engine, enabling real-time, programmable scene customization and on-demand data generation. Second, we present a Specimen Catalog architecture that lets the platform pivot between radically different disciplines, ranging from archaeological heterogeneous concrete and fuel-cell membranes to the root system of a bioenergy grass, by describing each dataset through portable metadata rather than hard-coded application logic. Finally, we introduce a prompt-driven layer powered by the Claude Agent SDK, allowing researchers to generate, segment, and manipulate volumetric and mesh data through natural language dialogue within the virtual space. For example, applying foundation models such as the Segment Anything Model (SAM) to perform zero-shot segmentation on demand. By bridging human intent with remote computation, ASCRIBE-XR relaxes the constraints of conventional visualization tools, offering a highly adaptable, conversational platform for scientific discovery with human auditing.

Schlagwörter

Stichwörter der Autor:innen

AI auditingLLMagentic analysiscomputer visionvirtual reality

Autor:innen und Institutionen

  • Applied Math and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.
  • Computer Science Department, Sonoma State University, Rohnert Park, CA 94928, USA.
  • Berkeley Institute for Data Science, University of California Berkeley, Berkeley, CA 94709, USA.
  • Department of Mathematics, University of California Berkeley, Berkeley, CA 94709, USA.
  • Bakar Computational Health Sciences Institute, University of California San Francisco, San Francisco, CA 94143, USA.

ORCID-Profile: Ronald Pandolfi, James Sethian, Jeffrey Donatelli, Daniela Ushizima

Förderung

  • US Department of Energy (DOE) Office of Science, Advanced Scientific Computing Research (ASCR)

Zitieren

APA

Pandolfi, R., Weidner, L., Sethian, J., Donatelli, J., & Ushizima, D. (2026). Turning Immersive Viewers into Analytical Workspaces: ASCRIBE-XR and Agent-Driven Scientific Visualization. Journal of Imaging, 12(8), 393. https://doi.org/10.3390/jimaging12080393

Vancouver

Pandolfi R, Weidner L, Sethian J, Donatelli J, Ushizima D. Turning Immersive Viewers into Analytical Workspaces: ASCRIBE-XR and Agent-Driven Scientific Visualization. Journal of Imaging. 2026;12(8):393. doi:10.3390/jimaging12080393

BibTeX
@article{Pandolfi2026,
  author = {Pandolfi, Ronald and Weidner, Luke and Sethian, James and Donatelli, Jeffrey and Ushizima, Daniela},
  title = {Turning Immersive Viewers into Analytical Workspaces: ASCRIBE-XR and Agent-Driven Scientific Visualization},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {393},
  doi = {10.3390/jimaging12080393}
}
Kostenlos starten →