Package 'geosimilarity'

Title: Geographically Optimal Similarity
Description: Understanding spatial association is essential for spatial statistical inference, including factor exploration and spatial prediction. Geographically optimal similarity (GOS) model is an effective method for spatial prediction, as described in Yongze Song (2022) <doi:10.1007/s11004-022-10036-8>. GOS was developed based on the geographical similarity principle, as described in Axing Zhu (2018) <doi:10.1080/19475683.2018.1534890>. GOS has advantages in more accurate spatial prediction using fewer samples and critically reduced prediction uncertainty.
Authors: Yongze Song [aut, cph] , Wenbo Lv [aut, cre]
Maintainer: Wenbo Lv <[email protected]>
License: GPL-3
Version: 3.7
Built: 2024-10-18 12:37:12 UTC
Source: CRAN

Help Index

geographically optimal similarity

Description

Computationally optimized function for geographically optimal similarity (GOS) model

Usage

gos(formula, data = NULL, newdata = NULL, kappa = 0.25, cores = 1)

Arguments

formula

A formula of GOS model.
data

A data.frame or tibble of observation data.
newdata

A data.frame or tibble of prediction variables data.
kappa

(optional) A numeric value of the percentage of observation locations with high similarity to a prediction location. kappa=1−taukappa = 1 - tau, where tau is the probability parameter in quantile operator. The default kappa is 0.25, meaning that 25% of observations with high similarity to a prediction location are used for modelling.
cores

(optional) Positive integer. If cores > 1, a parallel package cluster with that many cores is created and used. You can also supply a cluster object. Default is 1.

Value

A tibble made up of predictions and uncertainties.

pred

GOS model prediction results

uncertainty90

uncertainty under 0.9 quantile

uncertainty95

uncertainty under 0.95 quantile

uncertainty99

uncertainty under 0.99 quantile

uncertainty99.5

uncertainty under 0.995 quantile

uncertainty99.9

uncertainty under 0.999 quantile

uncertainty100

uncertainty under 1 quantile

References

Song, Y. (2022). Geographically Optimal Similarity. Mathematical Geosciences. doi: 10.1007/s11004-022-10036-8.

Examples

data("zn")
# log-transformation
hist(zn$Zn)
zn$Zn <- log(zn$Zn)
hist(zn$Zn)
# remove outliers
k <- removeoutlier(zn$Zn, coef = 2.5)
dt <- zn[-k,]
# split data for validation: 70% training; 30% testing
split <- sample(1:nrow(dt), round(nrow(dt)*0.7))
train <- dt[split,]
test <- dt[-split,]
system.time({
g1 <- gos(Zn ~ Slope + Water + NDVI  + SOC + pH + Road + Mine,
          data = train, newdata = test, kappa = 0.25, cores = 1)
})
test$pred <- g1$pred
plot(test$Zn, test$pred)
cor(test$Zn, test$pred)

function for the best kappa parameter

Description

Computationally optimized function for determining the best kappa parameter for the optimal similarity

Usage

gos_bestkappa(
  formula,
  data = NULL,
  kappa = seq(0.05, 1, 0.05),
  nrepeat = 10,
  nsplit = 0.5,
  cores = 1
)

Arguments

formula

A formula of GOS model.
data

A data.frame or tibble of observation data.
kappa

(optional) A numeric value of the percentage of observation locations with high similarity to a prediction location. kappa=1−taukappa = 1 - tau, where tau is the probability parameter in quantile operator. kappa is 0.25 means that 25% of observations with high similarity to a prediction location are used for modelling.
nrepeat

(optional) A numeric value of the number of cross-validation training times. The default value is 10.
nsplit

(optional) The sample training set segmentation ratio,which in ⁠(0,1)⁠. Default is 0.5.
cores

(optional) Positive integer. If cores > 1, a parallel package cluster with that many cores is created and used. You can also supply a cluster object. Default is 1.

Value

A list.

bestkappa

the result of best kappa

cvrmse

all RMSE calculations during cross-validation

cvmean

the average RMSE corresponding to different kappa in the cross-validation process

plot

the plot of rmse changes corresponding to different kappa

References

Song, Y. (2022). Geographically Optimal Similarity. Mathematical Geosciences. doi: 10.1007/s11004-022-10036-8.

Examples

data("zn")
# log-transformation
hist(zn$Zn)
zn$Zn <- log(zn$Zn)
hist(zn$Zn)
# remove outliers
k <- removeoutlier(zn$Zn, coef = 2.5)
dt <- zn[-k,]
# determine the best kappa
system.time({
b1 <- gos_bestkappa(Zn ~ Slope + Water + NDVI  + SOC + pH + Road + Mine,
                    data = dt,
                    kappa = c(0.01, 0.1, 1),
                    nrepeat = 1,
                    cores = 1)
})
b1$bestkappa
b1$plot

Spatial grid data of explanatory variables.

Description

Spatial grid data of explanatory variables.

Usage

grid

Format

grid: A tibble of grided trace element explanatory variables with 13132 rows and 12 variables, where the first column is ID.

Author(s)

Yongze Song [email protected]

Removing outliers.

Description

Function for removing outliers.

Usage

removeoutlier(x, coef = 2.5)

Arguments

x

A vector of a variable
coef

A number of the times of standard deviation. Default is 2.5.

Value

Location of outliers in the vector

Examples

data("zn")
# log-transformation
hist(zn$Zn)
zn$Zn <- log(zn$Zn)
hist(zn$Zn)
# remove outliers
k <- removeoutlier(zn$Zn, coef = 2.5)
k

Spatial datasets of trace element Zn.

Description

Spatial datasets of trace element Zn.

Usage

zn

Format

zn: A tibble of trace element Zn with 894 rows and 12 variables

Author(s)

Yongze Song [email protected]