gstat: Spatial and Spatio-Temporal Geostatistical Modelling and Prediction

gstat is a dataset for geostatistical modelling, prediction, and simulation. The description indicates it supports variogram modelling, kriging, and spatio-temporal kriging, as well as simulation methods. It was authored by Edzer Pebesma and is hosted on the paperswithcode platform.

Use Cases

• Predicting spatial phenomena like pollution levels based on variogram modelling and kriging.
• Simulating spatial fields for uncertainty analysis using sequential Gaussian or indicator simulation.
• Modelling spatio-temporal data for forecasting applications using spatio-temporal kriging.
• Creating variogram maps to analyze spatial variability and correlation structures.

Strengths

• Description specifies support for multiple advanced geostatistical methods, including simple, ordinary, and universal kriging.
• Includes both point and block (co)kriging, as well as spatio-temporal kriging.
• Supports integration with sf and stars, which are standard R packages for spatial data.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

paperswithcode