I am happy to announce GeoStats.jl, a package with high-performance implementations of geostatistical algorithms for the Julia programming language. It is in its initial development, and currently only contains Kriging estimation methods.
There is lots to be done in order to get estimation/simulation algorithms working on arbitrary domains (regular grids, unstructured meshes, etc.). In particular, I am planning to work on a hierarchy of types (similar to that of VTK) for spatial domains as my next step when Julia v0.6+ is out. If you have suggestions on how to achieve this hierarchy or if you see some interplay between this package and other packages for spatial data, please reach out.
The long-term goal is to have a general framework in which one can formulate geostatistical problems on any spatial domain and solve them efficiently (possibly in parallel) on modern hardware.
Related packages are:
- GeoStatsImages.jl - Training images for geostatistical simulation
- GslibIO.jl - Utilities to read/write extended GSLIB files in Julia
Contributions and suggestions are more than welcome.