The 6th International Workshop on Big Data & AI-Assisted Tools, Methods, and
Use Cases for Innovative Scientific Discovery (BTSD 2026)
in conjunction with 2026 IEEE International Conference on Big Data, December 14-17, 2026, Phoenix, AZ, USA
The 6th International Workshop on Big Data & AI-Assisted Tools, Methods, and
Use Cases for Innovative Scientific Discovery (BTSD 2026)
in conjunction with 2026 IEEE International Conference on Big Data, December 14-17, 2026, Phoenix, AZ, USA
Big data, machine learning, artificial intelligence, and data science technologies have driven major advances in scientific discovery by enabling researchers to integrate, reuse, and analyze vast, heterogeneous datasets. These advances have inspired scientists in physics, chemistry, materials science, climate science, energy, medicine, and other domains to explore how data-intensive methods can accelerate discovery.
Since its first edition in 2019, BTSD has served as a recurring IEEE BigData workshop on practical big data tools, methods, and use cases for innovative scientific discovery. The 2026 workshop explicitly extends this legacy: BTSD will now foreground AI-assisted tools as a central part of the scientific tool ecosystem, rather than treating them merely as adjacent topics under machine learning or data analytics.
This update reflects a rapidly emerging shift in how scientific work is being performed. Researchers are increasingly using AI-assisted environments such as foundation-model interfaces, research copilots, AI coding assistants including Codex and Claude Code, workflow agents, retrieval-augmented systems, tool-calling models, and interoperability protocols such as the Model Context Protocol (MCP). These tools are beginning to change not only how code and analyses are produced, but also how scientific questions are posed, tested, documented, and reproduced.
These systems are beginning to affect the full scientific lifecycle: data collection and curation, metadata generation, software development, pipeline construction, simulation setup, exploratory analysis, visualization, hypothesis generation, literature synthesis, and reproducibility. They can lower barriers for domain scientists, but they also introduce new research questions about trust, evaluation, provenance, security, maintainability, scientific validity, and human oversight.
BTSD 2026 will provide a focused forum for domain scientists, computer scientists, data scientists, AI researchers, software engineers, and cyberinfrastructure specialists to examine how AI-assisted big data tools are changing scientific practice. The workshop will collect successful use cases, identify unsolved methodological and infrastructure challenges, and promote collaborations that make AI-assisted scientific discovery more reliable, transparent, and impactful.
The workshop invites submissions on research, systems, methods, evaluations, and real-world use cases related to big data and AI-assisted tools for scientific discovery. Topics of interest include, but are not limited to:
AI-assisted tools, agents, copilots, and coding assistants for scientific data analysis, discovery, and research software engineering
Foundation models, large language models, multimodal models, retrieval-augmented generation, scientific knowledge graphs, and semantic search for research workflows
Tool-calling models, MCP-enabled scientific tools, interoperable agent workflows, notebook intelligence, and executable research records
Scientific data processing and management, including integration, standardization, sampling, validation, metadata generation, FAIR data, provenance, and data fusion
Big data systems and infrastructure for AI-assisted science, including cloud, HPC, edge computing, databases, query processing, performance, and scalability
Combining simulation, experiment, machine learning models, and data for scientific discovery, including uncertainty quantification and evaluation methods
Benchmarking and trustworthy AI for science, including correctness, robustness, reproducibility, hallucination control, bias, privacy, security, and governance
Visualization, interaction, and user experience design for AI-assisted scientific exploration
Domain-specific tools and use cases in physics, chemistry, materials science, biology, medicine, climate, energy, power systems, engineering, national security, and environmental science
Case studies, tutorials, demonstrations, education, training, and community practices for responsible AI-augmented scientific teams
which facilitate innovation and discovery in scientific domains such as:
Physics, Chemistry, Material science
Power Systems and Grid Resilience
Mechanical Engineering, Nuclear Engineering
National Security, Environmental Science
Biomedical science, and more.
Submissions describing success stories, ongoing research with open questions, lessons learned, and practical tools for scientific big data processing are especially encouraged.
TBD
Please submit a short paper (minimum 4 page, up to 6 page IEEE 2-column format) or full paper (minimum 8 page, up to 10 page IEEE 2-column format) through the online submission system. Submission is single-blind review system.
https://wi-lab.com/cyberchair/2026/bigdata26/scripts/submit.php?subarea=S33&undisplay_detail=1&wh=/cyberchair/2026/bigdata26/scripts/ws_submit.php
Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (see link to "formatting instructions" below). https://www.ieee.org/conferences/publishing/templates.html
Important Dates
Paper abstract submission due September 19, 2026
Full workshop paper submission due October 1, 2026
Notification of paper acceptance to authors November 4, 2026
Camera-ready submission of accepted papers November 25, 2026
Organizer Background
Sangkeun Matthew Lee earned his Ph.D. in Computer Science and Engineering from Seoul National University in 2012 and joined Oak Ridge National Laboratory (ORNL) in 2013 as a postdoctoral research associate. He is a Senior Research Staff member in the Critical Infrastructure Resilience Group within ORNL's Geospatial Science and Human Security Division. Lee has led interdisciplinary research in data analytics for power systems, building science, materials science, and medical sciences, advancing energy resilience analytics and scientific software tools.
Thomaz Carvalhaes is a R&D Scientist in the Critical Infrastructure Resilience Group at Oak Ridge National Laboratory. His work focuses on grid energy infrastructure as complex systems facing unexpected disruptions and a rapidly changing future. He has worked on disaster resilience and infrastructure projects using geospatial data analytics, modeling, and mixed quantitative and qualitative methods to develop decision tools and datasets.
Hillary K. Fishler serves as a research scientist in the Critical Infrastructure Resilience Group at Oak Ridge National Laboratory. Her research centers on coupled human-natural systems related to electric grid infrastructure and ancillary services. Her work applies team science and data-driven narratives to infrastructure and industry applications, including data governance, risk management, information security, social sciences, land-use planning, ecology, and vegetation management.
Minsu Kim is a research scientist at Oak Ridge National Laboratory whose work applies advanced AI technologies, especially transformer models, to Electronic Health Records and genomic data in bioinformatics. His research supports healthcare analytics, predictive modeling, interpretability, and the use of complex biomedical datasets in personalized medicine.