Interpolation and smoothing on the sphere by means of ordinary kriging.

interpolate_krige( observations, targets, value, lon_obs = lon, lat_obs = lat, lon_targets = lon, lat_targets = lat )

observations | data.frame of observations. |
---|---|

targets | data.frame of locations to calculate the interpolated and smoothed values for (target points). |

value | Column with values in |

lon_obs | Column in |

lat_obs | Column in |

lon_targets | Column in |

lat_targets | Column in |

Object equal to object `targets`

including extra columns for the predicted value and the variance.

`observations`

should include at least columns for longitude and latitude.

`targets`

should include at least columns for longitude, latitude and value of interest to interpolate and smooth.

Kriging can be considered as linear regression with spatially correlated residuals. Kriging is most appropriate when it is known there is a spatially correlated distance or directional bias in the data. It is often used in soil science and geology.

See `splines on the sphere`

for interpolation and smoothing on the sphere by means of splines.

Martin Haringa

if (FALSE) { target <- sf::st_drop_geometry(nl_postcode3) obs <- insurance %>% dplyr::sample_n(1000) pop_df <- interpolate_krige(obs, target, population_pc4) pop_sf <- left_join(nl_postcode3, pop_df) choropleth(pop_sf, value = "population_pc4_pred", n = 13) choropleth(pop_sf, value = "population_pc4_var", n = 13) }