potential

This package provides functions to compute the potential model as defined by Stewart (1941). Several options are available to customize the model, for example it is possible to fine-tune the distance friction functions or to use custom distance matrices. Some computations are parallelized to improve their efficiency.

• Website
• Vignette
• Blog post

Installation

You can install the released version of potential from CRAN with:

install.packages("potential")

You can install the development version of potential from GitHub with:

# install.packages("remotes")
remotes::install_github("riatelab/potential")

Demo

library(mapsf)
library(potential)
# Display the spatial interaction function
plot_inter(fun = "e", span = 75000, beta = 2, limit = 250000)

# create a regular grid
y <- create_grid(x = n3_poly, res = 20000)
# compute potentials
pot <- mcpotential(
  x = n3_pt, y = y,
  var = "POP19",
  fun = "e", span = 75000,
  beta = 2, limit = 250000, 
  ncl = 2
)
# Define potential according to the maximum value
y$pot <- pot / max(pot) * 100
# create equipotential areas
bks <- seq(0, 100, length.out = 11)
equipot <- equipotential(y, var = "pot", breaks = bks, mask = n3_poly)
# map potentials
mf_theme("default")
mf_map(x = equipot, var = "min", type = "choro", 
       breaks = bks, 
       pal = hcl.colors(10, 'Teal'),
       border = "#121725", 
       leg_val_rnd = 0,
       lwd = .2, 
       leg_pos = "topright", 
       leg_title = "Potential Intensity")
mf_title(txt = "Potentials of Population")
mf_credits(txt = "© EuroGeographics for the administrative boundaries and © Eurostat for data")

Note

This package provides access to the revamped potential-related functions initially offered by SpatialPosition.

References

Stewart, John Q. 1941. “An Inverse Distance Variation for Certain Social Influences.” Science 93 (2404): 89–90. https://doi.org/10.1126/science.93.2404.89.