|
Surfpack
Overview
NOTE: As of September 2008, Surfpack is no longer under active development, although it is still available for dowload. Surfpack will continue to be maintained as part of the DAKOTA software toolkit.
Surfpack is a general-purpose software
library of multidimensional function approximation methods for
applications such as data visualization, data mining, sensitivity
analysis, uncertainty quantification, and numerical optimization. Surfpack
is primarily intended for use on sparse, irregularly-spaced sets of data
points, where the data do not lie on a regularly-spaced grid. Surfpack
generates output data files that can be readily imported into many
standard data plotting and visualization software tools.
Surfpack generates
mathematical models based on user-supplied data, and then uses these
models for predicting (both via interpolation and extrapolation) general
trends in the data. For example, a geologist could use Surfpack to create
an approximate “map” of an underground water source, based on
moisture content data from a few irregularly-spaced drill sites located
within a city. Surfpack is a general-purpose mathematical and statistical
software package, with broad applications to both technical and
non-technical fields of study.
The Surfpack software package is
written in a combination of C++ and FORTRAN77 programming languages. The
C++ portion of Surfpack provides the primary data management and user
interface capabilities, while the FORTRAN77 portion of Surfpack covers the
bulk of the function approximation calculations. There are five main
function approximation types in Surfpack. These are (1) low-order
polynomial regression, (2) kriging interpolation, (3) multivariate
adaptive regression splines, (4) a simple artificial neural network, and
(5) a basic radial basis function method.
See the Surfpack manuals and
reference materials for more information on the capabilities of this
software package.
Surfpack Software Downloads
(click here)
The following downloads are available as of 25 August 2006:
- Source code files
- Binary executable files for Intel Pentium / Red Hat
Linux (Enterprise 4) workstations
- Surfpack demonstration files
Surfpack Manuals and Technical References
(click
here)
Surfpack Contact Information
Brian M. Adams
Email: surfpack-developers@software.sandia.gov
Related Sites at Sandia National
Labs:
|
