JPL is involved in the development of data-driven methods to support scientific research, healthcare and other industries in systemizing the analysis of massive, heterogeneous data sets. This includes:
- Statistical and machine learning methods to enable data discovery (e.g., classification, detection, prioritization, reduction, etc)
- Automated data pipelines for generating and analyzing massive data sets (e.g., complex genomics and proteomics data pipelines)
- Visualization techniques for massive, heterogeneous data
Partners include National Institutes of Health, Leona Helmsley Foundation, multiple university and federal laboratory partners and industries
To support these endeavors, JPL participated in the National Research Council report, "Frontiers in Massive Data Analysis"