semivariogram: Computes the semi-variogram using a dataframe or a stars...

In stxplore: Exploration of Spatio-Temporal Data

Computes the semi-variogram using a dataframe or a stars object.

Description

Computes the semi-variogram from a stars or a dataframe. Input arguments differ for each case. Function autoplot can plot the output.

When the input is a dataframe, the locations, time and the quantity of interest needs to be given. When the input is a stars object, a 3 dimensional stars object needs to be given as input with the first 2 dimensions being spatial and the third being time.

Usage

semivariogram(
  x,
  latitude_linear = TRUE,
  longitude_linear = TRUE,
  missing_value = -9999,
  width = 80,
  cutoff = 1000,
  tlagmax = 6,
  ...
)

## S3 method for class 'data.frame'
semivariogram(
  x,
  latitude_linear = TRUE,
  longitude_linear = TRUE,
  missing_value = -9999,
  width = 80,
  cutoff = 1000,
  tlagmax = 6,
  times_df,
  values_df,
  ...
)

## S3 method for class 'stars'
semivariogram(
  x,
  latitude_linear = TRUE,
  longitude_linear = TRUE,
  missing_value = -9999,
  width = 80,
  cutoff = 1000,
  tlagmax = 6,
  ...
)

## S3 method for class 'semivariogramobj'
autoplot(object, ...)

Arguments

x	The dataframe or stars object. If it is a dataframe, then it should have the locations.
latitude_linear	If TRUE a linear model is fitted with latitude as a covariate is fitted.
longitude_linear	If TRUE a linear model is fitted with longitude as a covariate is fitted.
missing_value	If a certain value such as -9999 denotes the missing values for given locations and times.
width	A parameter to the gstat::variogram function. The width of the distance intervals to be considered.
cutoff	A parameter to the gstat::variogram function. The spatial separation distance.
tlagmax	A parameter to the gstat::variogram function. The maximum time lag.
...	Other arguments that need to be used for datafames or currently ignored.
times_df	For dataframes: the dataframe containing the dates in Date format.
values_df	For dataframes: the dataframe of dimension length(times) x length(locations) containing the quantity of interest.
object	For autoplot: the output from the semivariogram function.

Value

A semivariogram object with a gstat variogram and the original data.

Examples

# Dataframe example
library(dplyr)
data(locs)
data(Times)
data(Tmax)
temp_part <- with(Times, paste(year, month, day, sep = "-"))
temp_part <- data.frame(date = as.Date(temp_part)[913:923])
Tmax <- Tmax[913:923, ]
semidf <- semivariogram(locs,
        temp_part,
        Tmax,
        latitude_linear = FALSE,
        longitude_linear = FALSE,
        missing_value = -9999,
        width = 50,
        cutoff = 1000,
        tlagmax = 7
)
autoplot(semidf)

# Stars example
library(stars)
# Create a stars object from a data frame
precip_df <- NOAA_df_1990[NOAA_df_1990$proc == 'Precip', ] %>%
  filter(date >= "1992-02-01" & date <= "1992-02-05")
precip <- precip_df[ ,c('lat', 'lon', 'date', 'z')]
st_precip <- st_as_stars(precip, dims = c("lon", "lat", "date"))
semist <- semivariogram(st_precip)
autoplot(semist)

stxplore documentation built on Feb. 16, 2023, 9:53 p.m.