Spotlight and more in-depth information on projects that are specific to the Center for Data Science and Technology.
Distributed Architecture, Workflow and Numerics
DAWN (Distributed Analytics, Workflows and Numerics) is a model developed at JPL to simulate Big Data processing in science. The model can be used to evaluate costs and tradeoffs of different system architectures based on several estimators such as the overall elapsed time, separate computation and data transfer time, uncertainty (if available) and monetary cost. Because of its generality, DAWN can be applied to the analysis of data processing use cases from virtually any scientific discipline: current applications include Astronomy, Climate Science, Hydrology, Medical Science, and generic processing on the Cloud. JPL is in the process of making DAWN open source, and hosting it on GutHub.