Estimating unknowns with spatial interpolation

Over the course of time, you may be presented with a geospatial dataset with a sparse number of observations that do not cover the entire study area that you’re interested in analyzing. As such, you may be looking for a way to fill in the missing geographies. Spatial interpolation is a process that uses known values from observations to estimate values at other unknown locations. This process is common in a number of scientific fields, such as meteorology and wildlife conservation. When it comes to meteorology, weather data is provided from a handful of weather stations in a given geography. From that information, meteorologists are asked to make predictions about what the weather will be at other locations.

There are many methods for performing spatial interpolation, including Inverse Distance Weighted (IDW) interpolation, Triangular Information Network (TIN) interpolation, and Kriging-based interpolation methods, to name a...