I created land-use rasters for the city of Montreal for 2012, 2014, and 2016; all of which I converted from vectors to rasters in QGIS. I want to create a logit model to predict land-use changes. I was suggested to split up the data into a series of reclassified rasters with values 1 and 0 ... 1 representing a specific land use and 0 representing something other than that land use.

My thought is to frame my analysis around the neighborhood effect, whether a cell is susceptible to change as a function of the cells surrounding it.

I've installed all raster packages deemed relevant and uploaded the rasters into R:

install.packages("dismo") #map raster on Google Map




All of my rasters have the same perimeters:

class       : RasterLayer 
dimensions  : 3000, 3000, 9e+06  (nrow, ncol, ncell)
resolution  : 13.03578, 11.03338  (x, y)
extent      : 267707.3, 306814.6, 5029977, 5063078  (xmin, xmax, ymin, ymax)
coord. ref. : +proj=tmerc +lat_0=0 +lon_0=-73.5 +k=0.9999 +x_0=304800 +y_0=0 +datum=NAD83 +units=m +no_defs +ellps=GRS80 +towgs84=0,0,0 
data source : C:\Users\Senun\Docs\MTL\QGIS\MTL_14.tif 
names       : MTL_14 
values      : 0, 1100  (min, max) 

This is what my rasters look like plotted (it was grayscaled in QGIS): enter image description here

I have a lot of "empty space" (0) to account for.

enter image description here

I'm at a loss--this is my first time working with rasters in R--on how to proceed. I couldn't find an example or tutorial dealing with multiple rasters; furthermore I have difficulty identifying my cell values. Should I start with reclassifying my pixels?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.