Knowledge Capture And Discovery

We develop Artificial Intelligence (AI) approaches that use knowledge to accelerate and innovate scientific discovery processes that are unnecessarily carried out manually and inefficiently today.

Research Interests

Knowledge capture

Representing and acquiring knowledge to be used in AI systems

Semantic Workflows

Automated reasoning about characteristics of data and steps in computational experiments

Ontology Tools

Collaborative ontology development and sharing

Scientific Discovery

Efficient exploration of alternative methods to analyze data

Task-based collaboration

Collaborations that are driven by a shared scientific question

Provenance

Capturing the history of scientific research

Knowledge Networks

Interconnecting scientific knowledge in the Web

Reproducibility

Improving scientific publications

Machine Learning

Intelligent assistance for data analysis

Projects

A semantic workflow system that assists scientists with the design of computational experiments

Varun Ratnakar, Yolanda Gil, Daniel Garijo, Hernan Vargas, Deborah Khider, Maximiliano Osorio

The Scientific Paper of the Future Initiative

In the near future, scientists will routinely use new tools to develop research papers that will document all the associated digital objects (data, software, workflows, etc.). This will make science more open, promote fair credit of scientific contributions, and facilitate reproducibility.

The Scientific Paper of the Future Initiative

The Geoscience Paper of the Future Initiative

Guidelines and courses to build the Geoscience Papers of the Future

The Geoscience Paper of the Future Initiative

A Phased Performance-Based Pipeline Planner for Automated Machine Learning

P4ml

Organic Data Science Framework

Organic Data Science Framework (ODSF) to support scientific collaborations that revolve around complex science questions that require significant coordination to synthesize multi-disciplinary findings, enticing contributors to remain engaged for extended periods of time, and continuous growth to accommodate new contributors as needed as the work evolves over time.

Organic Data Science Framework

Organic Data Curation

A novel approach to data publishing that requires minimal effort from scientists

Organic Data Curation

OPMW-PROV: The Open Provenance Model for Workflows

Tracking the provenance of scientific experiments and their executions

A software metadata registry to describe scientific software in a user-friendly manner

Ontosoft

The Neuro-DISK project automates the analysis of neuroscience data.

Varun Ratnakar, Yolanda Gil, Daniel Garijo, Hernan Vargas, Deborah Khider, Maximiliano Osorio

Model Integration through Knowledge-Rich Data and Process Composition

Yolanda Gil, Varun Ratnakar, Daniel Garijo, Deborah Khider, Maximiliano Osorio

MINT

LinkedEarth is a community of paleoscientists working to develop standards and software to enable paleoscience in the era of Big Data. This community produces data products and standards, software, cyberinfrastructure, and training opportunities.

Linked Earth

Finding common fragments in scientific workflows

Automating hypothesis-driven discovery in different scientific domains

Varun Ratnakar, Yolanda Gil, Daniel Garijo, Hernan Vargas, Deborah Khider, Maximiliano Osorio

Data Narratives

Creating automatic descriptions of experiment results

Data Narratives

Climate DISK uses the DISK framework to automate climate analysis

Varun Ratnakar, Yolanda Gil, Daniel Garijo, Hernan Vargas, Deborah Khider, Maximiliano Osorio

An automated system for time series analysis.

Deborah Khider, Varun Ratnakar

autoTS

A new sketching project to accelerate scientific workflows using EarthCube technologies