Using app function from {terra} package on raster stacks? (in parallel) - r

Question

I have four high resolution rasters for a country. I have split each raster into tiles and done some other processing to them. I now want to apply a function to each cell, of each 'stack' of the raster tiles, to produce one set of output tiles. The function is a little complex. I have tried to synthesise some data below to reproduce my current approach. It works (ish) but I'm convinced that there's a better way to do this. To use parallel processing on my unix box, I simply swap mapply for mcmapply, but I haven't done that in the example below as I presume many will be working on Windows machines. I'd welcome ideas on my approach and particularly optimisation.
library("terra")
library("glue")
## Make some toy data
dir.create("temp_folder")
dir.create("result_folder")
x <- rast(ncols = 10, nrows = 10)
a <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(a) <- some_values
a_tiles <- makeTiles(a, x, glue("temp_folder/tile_a_{1:100}.tif"), overwrite = TRUE)
b <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(b) <- some_values
b_tiles <- makeTiles(b, x, glue("temp_folder/tile_b_{1:100}.tif"), overwrite = TRUE)
c <-rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(c) <- some_values
c_tiles <- makeTiles(c, x, glue("temp_folder/tile_c_{1:100}.tif"), overwrite = TRUE)
d <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(d) <- some_values
d_tiles <- makeTiles(d, x, glue("temp_folder/tile_d_{1:100}.tif"), overwrite = TRUE)
## Outer function so that this can be used in parallel ? But maybe this is a silly way to do it?
outer_function <- function(a_tiles, b_tiles, c_tiles, d_tiles, output_files) {
one_a_tile <- rast(unlist(a_tiles))
one_b_tile <- rast(unlist(b_tiles))
one_c_tile <- rast(unlist(c_tiles))
one_d_tile <- rast(unlist(d_tiles))
output_file <- output_files
# I replace any NAs with 0 as an NA will break my 'if' statement of the inner_function.
# I get Error in if (z["a"] <= z["b"]) { : missing value where TRUE/FALSE needed
one_a_tile[is.na(one_a_tile)] <- 0
one_b_tile[is.na(one_b_tile)] <- 0
one_c_tile[is.na(one_c_tile)] <- 0
one_d_tile[is.na(one_d_tile)] <- 0
z <- sds(one_a_tile, one_b_tile, one_c_tile, one_d_tile)
## Inner function that actually does the work I want doing
inner_function <- function(z) {
names(z) <- c('a', 'b', 'c', 'd')
if (z['a'] <= z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 10),
(z['c'] + z['a'] * 20)))
}
if (z['a'] >= z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 40),
(z['c'] + z['a'] * 10)))
}
if (z['a'] == z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 60),
(z['c'] + z['a'] * 10)))
}
y <- ifelse(y == 0, NA, y)
return(y)
}
app(z,
inner_function,
filename = output_file,
overwrite = TRUE,
wopt = list(datatype = "INT4U"))
return(output_file)
}
results <- mapply(outer_function,
a_tiles = a_tiles,
b_tiles = b_tiles,
c_tiles = c_tiles,
d_tiles = d_tiles,
output_files = output_files <- glue("result_folder/result_tile_{1:length(d_tiles)}.tif"))
names(results) <- NULL
unlink("temp_folder", recursive = TRUE)
unlink("result_folder", recursive = TRUE)