ScalaGAUSS is a set of scalable tools for analyzing large-scale spatiotemporal data modeled as a Gaussian process/random field. The project addresses the computational challenges in statistical modeling and analysis of the data in a very large scale. Currently the Matlab version can handle 1 million data points on a general commercial desktop machine with several cores, and the C++ version can handle 1 billion data points on a computer cluster running MPI with sufficient memory. This project is supported by the U.S. Department of Energy under Contract No. DE-AC02-06CH11357.

Principal investigators:

The ScalaGAUSS team:

  • Jie Chen, Argonne National Laboratory
  • Tom Li, University of Missouri–St. Louis