plot_geodist: Plot euclidean nearest neighbor distances in geographic space...

In CAST: 'caret' Applications for Spatial-Temporal Models

Plot euclidean nearest neighbor distances in geographic space or feature space

Description

Density plot of nearest neighbor distances in geographic space or feature space between training data as well as between training data and prediction locations. Optional, the nearest neighbor distances between training data and test data or between training data and CV iterations is shown. The plot can be used to check the suitability of a chosen CV method to be representative to estimate map accuracy. Alternatively distances can also be calculated in the multivariate feature space.

Usage

plot_geodist(
  x,
  modeldomain,
  type = "geo",
  cvfolds = NULL,
  cvtrain = NULL,
  testdata = NULL,
  samplesize = 2000,
  sampling = "regular",
  variables = NULL,
  unit = "m",
  stat = "density",
  showPlot = TRUE
)

Arguments

x	object of class sf, training data locations
modeldomain	SpatRaster, stars or sf object defining the prediction area (see Details)
type	"geo" or "feature". Should the distance be computed in geographic space or in the normalized multivariate predictor space (see Details)
cvfolds	optional. list or vector. Either a list where each element contains the data points used for testing during the cross validation iteration (i.e. held back data). Or a vector that contains the ID of the fold for each training point. See e.g. ?createFolds or ?CreateSpacetimeFolds or ?nndm
cvtrain	optional. List of row indices of x to fit the model to in each CV iteration. If cvtrain is null but cvfolds is not, all samples but those included in cvfolds are used as training data
testdata	optional. object of class sf: Data used for independent validation
samplesize	numeric. How many prediction samples should be used?
sampling	character. How to draw prediction samples? See spsample. Use sampling = "Fibonacci" for global applications.
variables	character vector defining the predictor variables used if type="feature. If not provided all variables included in modeldomain are used.
unit	character. Only if type=="geo" and only applied to the plot. Supported: "m" or "km".
stat	"density" for density plot or "ecdf" for empirical cumulative distribution function plot.
showPlot	logical

Details

The modeldomain is a sf polygon or a raster that defines the prediction area. The function takes a regular point sample (amount defined by samplesize) from the spatial extent. If type = "feature", the argument modeldomain (and if provided then also the testdata) has to include predictors. Predictor values for x are optional if modeldomain is a raster. If not provided they are extracted from the modeldomain rasterStack.

Value

A list including the plot and the corresponding data.frame containing the distances. Unit of returned geographic distances is meters.

Note

See Meyer and Pebesma (2022) for an application of this plotting function

Author(s)

Hanna Meyer, Edzer Pebesma, Marvin Ludwig

See Also

nndm

Examples

## Not run: 
library(sf)
library(terra)
library(caret)

########### prepare sample data:
dat <- get(load(system.file("extdata","Cookfarm.RData",package="CAST")))
dat <- aggregate(dat[,c("DEM","TWI", "NDRE.M", "Easting", "Northing")],
  by=list(as.character(dat$SOURCEID)),mean)
pts <- st_as_sf(dat,coords=c("Easting","Northing"))
st_crs(pts) <- 26911
pts_train <- pts[1:29,]
pts_test <- pts[30:42,]
studyArea <- terra::rast(system.file("extdata","predictors_2012-03-25.grd",package="CAST"))
studyArea <- studyArea[[c("DEM","TWI", "NDRE.M", "NDRE.Sd", "Bt")]]

########### Distance between training data and new data:
dist <- plot_geodist(pts_train,studyArea)

########### Distance between training data, new data and test data:
#mapview(pts_train,col.regions="blue")+mapview(pts_test,col.regions="red")
dist <- plot_geodist(pts_train,studyArea,testdata=pts_test)

########### Distance between training data, new data and CV folds:
folds <- createFolds(1:nrow(pts_train),k=3,returnTrain=FALSE)
dist <- plot_geodist(x=pts_train, modeldomain=studyArea, cvfolds=folds)

## or use nndm to define folds
AOI <- as.polygons(rast(studyArea), values = F) |>
  st_as_sf() |>
  st_union() |>
  st_transform(crs = st_crs(pts_train))
nndm_pred <- nndm(pts_train, AOI)
dist <- plot_geodist(x=pts_train, modeldomain=studyArea,
    cvfolds=nndm_pred$indx_test, cvtrain=nndm_pred$indx_train)

########### Distances in the feature space:
plot_geodist(x=pts_train, modeldomain=studyArea,
    type = "feature",variables=c("DEM","TWI", "NDRE.M"))

dist <- plot_geodist(x=pts_train, modeldomain=studyArea, cvfolds = folds, testdata = pts_test,
    type = "feature",variables=c("DEM","TWI", "NDRE.M"))

############ Example for a random global dataset
############ (refer to figure in Meyer and Pebesma 2022)
library(sf)
library(rnaturalearth)
library(ggplot2)

### Define prediction area (here: global):
ee <- st_crs("+proj=eqearth")
co <- ne_countries(returnclass = "sf")
co.ee <- st_transform(co, ee)

### Simulate a spatial random sample
### (alternatively replace pts_random by a real sampling dataset (see Meyer and Pebesma 2022):
sf_use_s2(FALSE)
pts_random <- st_sample(co.ee, 2000, exact=FALSE)

### See points on the map:
ggplot() + geom_sf(data = co.ee, fill="#00BFC4",col="#00BFC4") +
     geom_sf(data = pts_random, color = "#F8766D",size=0.5, shape=3) +
     guides(fill = FALSE, col = FALSE) +
     labs(x = NULL, y = NULL)

### plot distances:
dist <- plot_geodist(pts_random,co.ee,showPlot=FALSE)
dist$plot+scale_x_log10(labels=round)

## End(Not run)

CAST documentation built on May 31, 2023, 7:07 p.m.