GeoStatsImages.jl
June 27, 2026 · View on GitHub
Training images for geostastical simulation in Julia.
This package converts famous training images from the geostatistcs literature to a standard format for quick experimentation in Julia. It is part of the GeoStats.jl framework and can be used in conjunction with multiple-point simulation algorithms.
The standard format is a geotable as discussed in the book
Geospatial Data Science with Julia.
Continuous variables as stored as "value" and categorical
variables are stored "code".
The contributors of this package do not hold any copyright on the data. Please give credit to the sources listed on the preview table.
Usage
The geostatsimage function takes an image name as input and
returns a geotable. Please run GeoStatsImages.available() to
discover all available image names.
julia> geostatsimage("WalkerLake")
78000×2 GeoTable over 260×300 CartesianGrid
┌─────────────┬─────────────────────────────────────────────────────────────┐
│ value │ geometry │
│ Continuous │ Quadrangle │
│ [NoUnits] │ 🖈 Cartesian{NoDatum} │
├─────────────┼─────────────────────────────────────────────────────────────┤
│ 0.0 │ Quadrangle((x: 0.0 m, y: 0.0 m), ..., (x: 0.0 m, y: 1.0 m)) │
│ 1.28207e-5 │ Quadrangle((x: 1.0 m, y: 0.0 m), ..., (x: 1.0 m, y: 1.0 m)) │
│ 2.56414e-5 │ Quadrangle((x: 2.0 m, y: 0.0 m), ..., (x: 2.0 m, y: 1.0 m)) │
│ 3.8462e-5 │ Quadrangle((x: 3.0 m, y: 0.0 m), ..., (x: 3.0 m, y: 1.0 m)) │
│ 5.12827e-5 │ Quadrangle((x: 4.0 m, y: 0.0 m), ..., (x: 4.0 m, y: 1.0 m)) │
│ 6.41034e-5 │ Quadrangle((x: 5.0 m, y: 0.0 m), ..., (x: 5.0 m, y: 1.0 m)) │
│ 7.69241e-5 │ Quadrangle((x: 6.0 m, y: 0.0 m), ..., (x: 6.0 m, y: 1.0 m)) │
│ 8.97447e-5 │ Quadrangle((x: 7.0 m, y: 0.0 m), ..., (x: 7.0 m, y: 1.0 m)) │
│ 0.000102565 │ Quadrangle((x: 8.0 m, y: 0.0 m), ..., (x: 8.0 m, y: 1.0 m)) │
│ 0.000115386 │ Quadrangle((x: 9.0 m, y: 0.0 m), ..., (x: 9.0 m, y: 1.0 m)) │
│ ⋮ │ ⋮ │
└─────────────┴─────────────────────────────────────────────────────────────┘
77990 rows omitted
Preview
| Name | Preview | Type | Data source |
|---|---|---|---|
| WalkerLake |  | Continuous | Mariethoz & Caers, 2014 |
| StoneWall |  | Continuous | Mariethoz & Caers 2014 |
| Herten |  | Continuous | Mariethoz & Caers 2014 |
| Lena |  | Continuous | Mariethoz & Caers 2014 |
| IceWedges |  | Continuous | Mariethoz & Caers 2014 |
| StanfordV |  | Continuous | Mao & Journel 2014 |
| Gaussian30x10 |  | Continuous | Hoffimann 2020 |
| Strebelle |  | Categorical | Strebelle 2002 |
| Ellipsoids |  | Categorical | Mariethoz & Caers 2014 |
| Bangladesh |  | Categorical | Mariethoz & Caers 2014 |
| Concrete |  | Categorical | Mariethoz & Caers 2014 |
| Dunes |  | Categorical | Mariethoz & Caers 2014 |
| Jha2014 |  | Categorical | Mariethoz & Caers 2014 |
| Ohau |  | Categorical | Mariethoz & Caers 2014 |
| WestCoastAfrica |  | Categorical | Mariethoz & Caers 2014 |
| Flumy |  | Categorical | Hoffimann et al 2017 |
| Fluvsim |  | Categorical | Mariethoz & Caers, 2014 |
| Ketton |  | Categorical | Imperial College Pore-Scale Modelling Group |
Collections
FlumeContinuous
FlumeBinary
Contributing
Contributions are very welcome, as are feature requests and suggestions.
If you have any questions, please contact our community.