Location heatmaps in R

Let’s use a built-in example within R: location of earthquakes off the island of Fiji.

#>      lat   long depth mag stations
#> 1 -20.42 181.62   562 4.8       41
#> 2 -20.62 181.03   650 4.2       15
#> 3 -26.00 184.10    42 5.4       43
#> 4 -17.97 181.66   626 4.1       19
#> 5 -20.42 181.96   649 4.0       11
#> 6 -19.68 184.31   195 4.0       12

This data set contains spatial point data of earthquakes modelled with a certain magnitude and focal depth using observations from a certain number of observatories (stations).

Take a shape and setup the base map

#> Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

#> Loading required package: htmlwidgets

#> tmap mode set to interactive viewing

Create a grid

This makes an outline and is a good check to see if the bounding box is correct

#> although coordinates are longitude/latitude, st_intersects assumes that they are planar

Now divide into a grid with cells. In the case below we divide the bounding box region into 20 cells of equal size and equal length in both dimensions.

#> although coordinates are longitude/latitude, st_intersects assumes that they are planar

#> 
#> Attaching package: 'dplyr'

#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag

#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union

#> although coordinates are longitude/latitude, st_intersects assumes that they are planar

#> `summarise()` ungrouping output (override with `.groups` argument)