Pairwise correlation between raster layers in R

r correlation raster
Ricardo Adelino picture Ricardo Adelino · Aug 19, 2015 · Viewed 7.7k times · Source

I need accomplish a pairwise Pearson correlation between 19 raster layers for Africa Continent extracted from WordClim database. I want to checking what are variables layers more correlated/significant to my model. For this i tried use the layerStats function from Raster package, but after execute my output not contain numerical values, all the rows and columns showed NAs values. Below is my script.

#Loading raster files from WorldClim database
rastFiles<- list.files(pattern="bil")
a<-stack(rastFiles)

# Adjusting for African Continent
newext<-c(-20, 55, -35, 45)
Africa<-crop(a,newext)
Africa

#Correlation
cor<-layerStats(Africa,'pearson')

Answer

Lucas Fortini picture Lucas Fortini · Aug 19, 2015

In r, simply use the code below, ensuring you have na.rm=T to deal with NAs across layers:

library(raster)    
jnk=layerStats(raster_stack, 'pearson', na.rm=T)
corr_matrix=jnk$'pearson correlation coefficient'

Related questions

How can I create a correlation matrix in R?

I have 92 set of data of same type. I want to make a correlation matrix for any two combination possible. i.e. I want a matrix of 92 x92. such that element (ci,cj) should be correlation between ci and cj. …

Read More
Calculate correlation with cor(), only for numerical columns

I have a dataframe and would like to calculate the correlation (with Spearman, data is categorical and ranked) but only for a subset of columns. I tried with all, but R's cor() function only accepts numerical data (x must be …

Read More
cor shows only NA or 1 for correlations - Why?

I'm running cor() on a data.framewith all numeric values and I'm getting this as the result: price exprice... price 1 NA exprice NA 1 ... So it's either 1 or NA for each value in the resulting table. Why are the NAs showing …

Read More