Movatterモバイル変換

Station File (G06)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G06

Format

## 'Station_G06'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (G17)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G17

Format

## 'Station_G17'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (G20)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G20

Format

## 'Station_G20'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (G21)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G21

Format

## 'Station_G21'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (G25)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G25

Format

## 'Station_G25'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (G48)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_G48

Format

## 'Station_G48'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (W10)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_W10

Format

## 'Station_W10'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (W11)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_W11

Format

## 'Station_W11'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (W19)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_W19

Format

## 'Station_W19'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Station File (W20)

Description

Contains made up climate data for imaginary climate stations for education purposes.

Usage

Station_W20

Format

## 'Station_W20'A data frame with 10 rows and 5 columns

plotID

Plot ID of imaginary climate station

datetime

Timestamp of record for station

Ta_200

Imaginary air temperature at 200 cm above ground

Source

Randomly created climate data at random created stations extracted from a random climate map made by climodr.

Autocorrelation

Description

Tests the final.csv created with 'fin.csv' on autocorrelation to producereliable models.

Usage

autocorr(  envrmt = .GlobalEnv$envrmt,  method = "monthly",  resp,  pred,  plot.corrplot = TRUE,  corrplot = "coef")

Arguments

Value

One .csv file per response variable. These will later be used when 'autocorrelation' is set 'TRUE' during 'calc.model'.

See Also

'calc.model'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)#extract predictor values from raster filescsv_fin <- fin.csv(envrmt = envrmt,                   method = "monthly",                   save_output = TRUE)# Test data for autocorrelation after running fin.csvautocorr(envrmt = envrmt,         method = "monthly",         resp = 5,         pred = c(8:23),         plot.corrplot = FALSE)

Calculate spectral indices

Description

Calculates a set of spectral indices to have more predictor variables available when further modeling.

Usage

calc.indices(  envrmt = .GlobalEnv$envrmt,  vi = "all",  bands = c("blue", "green", "red", "nir", "nirb", "re1", "re2", "re3", "swir1", "swir2"),  overwrite = FALSE)

Arguments

Value

SpatRaster-Stack

See Also

'crop.all', 'fin.csv'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)

Modelling

Description

Creates Models for each climate value

Usage

calc.model(  envrmt = .GlobalEnv$envrmt,  method = "monthly",  timespan,  climresp,  classifier = c("rf", "pls", "lm", "glm"),  seed = NULL,  p = 0.8,  folds = "all",  predrows,  mnote = NULL,  k = NULL,  tc_method = "cv",  metric = "RMSE",  doParallel = FALSE,  autocorrelation = FALSE,  ...)

Arguments

Value

data frame.

See Also

'autocorr'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)#extract predictor values from raster filescsv_fin <- fin.csv(envrmt = envrmt,                   method = "monthly",                   save_output = TRUE)# Test data for autocorrelation after running fin.csvautocorr(envrmt = envrmt,         method = "monthly",         resp = 5,         pred = c(8:23),         plot.corrplot = FALSE)# Create 36 different models (12 months x 3 classifiers) for every month in 2017calc.model(envrmt = envrmt,           method = "monthly",           timespan = c(2017),           climresp = 5,           classifier = c("rf",                          "pls",                          "lm"),           seed = 707,           p = 0.8,           folds = "LLO",           mnote = "normal",           predrows = c(8:23),           tc_method = "cv",           metric = "RMSE",           autocorrelation = TRUE,           doParallel = FALSE)

Load in Example Data

Description

Climodr comes with a full set of example data. But since this package runs primarily with data,that is not linked to the global environment, but saved in local folders build via 'envi.create',one can't just load example data. This function will load all the example data used in the vignetteinto your climodr environment. This way you can run all the code from the vignette.

Usage

clim.sample(envrmt = .GlobalEnv$envrmt)

Arguments

Value

Multiple files used by the climodr vignette

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)

Create Maps using the 'terra' package graphic parameters

Description

Plot results of climodr into maps. Right now maps are created using the terra package.The maps created are very basic. Will be updated to run with tidyterra in future.

Usage

climplot(  envrmt = .GlobalEnv$envrmt,  mnote,  sensor,  aoa = FALSE,  mapcolors = rev(grDevices::terrain.colors(50)),  scale_position = "bottomleft",  north_position = "topright")

Arguments

Value

Maps in PNG-Format to your harddrive.

See Also

'terra::plot'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)#extract predictor values from raster filescsv_fin <- fin.csv(envrmt = envrmt,                   method = "monthly",                   save_output = TRUE)# Test data for autocorrelation after running fin.csvautocorr(envrmt = envrmt,         method = "monthly",         resp = 5,         pred = c(8:23),         plot.corrplot = FALSE)# Create 36 different models (12 months x 3 classifiers) for every month in 2017calc.model(envrmt = envrmt,           method = "monthly",           timespan = c(2017),           climresp = 5,           classifier = c("rf",                          "pls",                          "lm"),           seed = 707,           p = 0.8,           folds = "LLO",           mnote = "normal",           predrows = c(8:23),           tc_method = "cv",           metric = "RMSE",           autocorrelation = TRUE,           doParallel = FALSE)# Make predictionsclimpred(envrmt = envrmt,         method = "monthly",         mnote = "normal",         AOA = TRUE)# Create a Temperature Map from the vignette modelclimplot(envrmt = envrmt,         mnote = "normal",         sensor = "Ta_200",         aoa = TRUE,         mapcolors = rev(heat.colors(50)),         scale_position = "bottomleft",         north_position = "topright")

Predict sensor data area wide

Description

Use the models created using 'calc.model' to predict the modeled data onto afull spatial raster scene.

Usage

climpred(envrmt = .GlobalEnv$envrmt, method = "monthly", mnote, AOA = TRUE)

Arguments

Value

Multiple models.rds stored in the /workflow/models folder.

See Also

'autocorr', 'predict'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)#extract predictor values from raster filescsv_fin <- fin.csv(envrmt = envrmt,                   method = "monthly",                   save_output = TRUE)# Test data for autocorrelation after running fin.csvautocorr(envrmt = envrmt,         method = "monthly",         resp = 5,         pred = c(8:23),         plot.corrplot = FALSE)# Create 36 different models (12 months x 3 classifiers) for every month in 2017calc.model(envrmt = envrmt,           method = "monthly",           timespan = c(2017),           climresp = 5,           classifier = c("rf",                          "pls",                          "lm"),           seed = 707,           p = 0.8,           folds = "LLO",           mnote = "normal",           predrows = c(8:23),           tc_method = "cv",           metric = "RMSE",           autocorrelation = TRUE,           doParallel = FALSE)# Make predictionsclimpred(envrmt = envrmt,         method = "monthly",         mnote = "normal",         AOA = TRUE)predlist <- list.files(envrmt$path_predictions,                       pattern = ".tif")head(predlist)

Cropping tiff data

Description

Crops input data to the extent size and reprojects them into project Coordinate reference system.

Usage

crop.all(  envrmt = .GlobalEnv$envrmt,  method = "MB_Timeseries",  crs = NULL,  ext = NULL,  overwrite = FALSE,  ...)

Arguments

Value

SpatRaster-Stack. Also saved to /workflow/rworkflow

See Also

'fin.csv', 'calc.indices'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)

Create climodr environment

Description

Creates an environment climodr will use during the calculation process. A list is returned with all paths to all folders.After creating the environment, all necessary data should be stored into the depending Input sub-folders.There is also an additional temp-folder, where temporary data is stored, which can be deleted after not being used anymore.

Usage

envi.create(proj_path = tempdir(), memfrac = NULL, ...)

Arguments

Value

list. Contains all paths to each folder in the project directory. Necessary for climodr to operate its functions.

Examples

# create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)

Extent file for vignette

Description

A vector file containing the shape and extent of the Area used in thevignette

Usage

ext_vignette

Format

## 'ext_vignette'

class

SpatVector

geometry

polygons

dimensions

1, 1 (geometries, attributes)

extent

805737, 812824, 5890352, 5896005 (xmin, xmax, ymin, ymax)

coord. ref.

WGS 84 / UTM zone 32N (EPSG:32632)

values

1

Spat Vector

Source

Randomly created in (QGIS)[https://www.qgis.org/download/thank-you/].

Final aggregation for CSV-Data

Description

Extract the raster values of all raster layers from a scene at the stationcoordinates at each time stamp. The extracted data will be attached to thestation data so there is a .csv-file with coordinates, sensor data (response values)and extracted raster data (predictor values). The data is ready to be used for modelling.

Usage

fin.csv(  envrmt = .GlobalEnv$envrmt,  method = "monthly",  crs = NULL,  save_output = TRUE,  ...)

Arguments

Value

List

See Also

'prep.csv', 'proc.csv', 'spat.csv', 'calc.indices'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)# Crop all raster bandscrop.all(envrmt = envrmt,         method = "MB_Timeseries",         overwrite = TRUE)# Calculate Indices from cropped raster bandscalc.indices(envrmt = envrmt,             vi = "all",             bands = c("blue", "green", "red",                       "nir", "nirb",                       "re1", "re2", "re3",                       "swir1", "swir2"),             overwrite = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)#extract predictor values from raster filescsv_fin <- fin.csv(envrmt = envrmt,                   method = "monthly",                   save_output = TRUE)head(csv_fin)

Plot description file

Description

Contains made up coordinates for imaginary climate stations for education purposes.

Usage

plot_description

Format

## 'plot_description'A data frame with 10 rows and 5 columns

plot

imaginary station name and code

general

imaginary category of climate station

region

location name of climate station

lat

Latitude Coordinate of climate station

lon

Longitude Coordinate of climate station

elevation

elevation of climate station

Source

Randomly created coordinates and stations extracted from a random climate map.

Preparing CSV-Data

Description

Crops input data to the extent size and removes NA-Values

Usage

prep.csv(envrmt = .GlobalEnv$envrmt, method = "proc", save_output = TRUE, ...)

Arguments

Value

List

See Also

'proc.csv', 'spat.csv', 'fin.csv'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#check the created csv filescsv_files <- grep("_no_NAs.csv$",                  list.files(envrmt$path_tworkflow),                  value=TRUE)csv_files

Processing CSV-Data

Description

Calculate averaged sensor values aggregated to a given time interval.

Usage

proc.csv(  envrmt = .GlobalEnv$envrmt,  method = "monthly",  rbind = TRUE,  save_output = TRUE,  ...)

Arguments

Value

List

See Also

'prep.csv', 'spat.csv', 'fin.csv'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)head(csv_data)

Resolution and Area

Description

This raster contains the area of interest as well as the desired modelresolution (100 m * 100 m) and the project extent.

Usage

res_area

Format

## 'res_area'A binary Raster of pixels with value 1 in extent that belong to example area

class

SpatRaster

dimensions

57, 71, 1 (nrow, ncol, nlyr)

resolution

100, 100 (x, y)

extent

805732, 812832, 5890310, 5896010 (xmin, xmax, ymin, ymax)

coord. ref.

WGS 84 / UTM zone 32N (EPSG:32632)

name

res_area

min/max

0/1

Source

Randomly created binary Spat Raster file with the project resolution of 100 m per pixel. Created in (QGIS)[https://www.qgis.org/download/thank-you/].

Spatial Raster File for Vignette

Description

A spatial Raster file from a random area choose for the Vignette or as dummy data.

Usage

sch_201707

Format

## 'sch_201707'A Spat Raster with 8 spectral bands

class

SpatRaster

dimensions

86, 151, 10 (nrow, ncol, nlyr)

resolution

100, 100 (x, y)

extent

801522.5, 816622.5, 5888973, 5897573 (xmin, xmax, ymin, ymax)

coord. ref.

WGS 84 / UTM zone 32N (EPSG:32632)

names

blue, green, red, nir, nirb, re1, re2, re3, swir1, swir2

min/max

33.90298/5479.6602

Source

Randomly created Spat Raster file from (Sentinel-2 Data)[https://browser.dataspace.copernicus.eu/?zoom=10&lat=52.96601&lng=13.86818&themeId=DEFAULT-THEME&visualizationUrl=U2FsdGVkX1

Digital Ground Model for Vignette

Description

A Digital Ground Model file from a random area choose for the Vignette or as dummy data.

Usage

sch_dgm

Format

## 'sch_dgm'A Digital Ground Model

class

SpatRaster

dimensions

86, 151, 10 (nrow, ncol, nlyr)

resolution

100, 100 (x, y)

extent

801522.5, 816622.5, 5888973, 5897573 (xmin, xmax, ymin, ymax)

coord. ref.

WGS 84 / UTM zone 32N (EPSG:32632)

names

elevation

min/max

48.75315/94.67307

Source

Randomly extracted Digital Ground Model.

Spatial aggregation for CSV-Data

Description

Extract station coordinates from meta-data and reproject the coordinates to theproject coordinate reference system.

Usage

spat.csv(  envrmt = .GlobalEnv$envrmt,  method = "monthly",  des_file,  crs = NULL,  save_output = TRUE,  ...)

Arguments

Value

Data Frame

See Also

'prep.csv', 'proc.csv', 'fin.csv'

Examples

#create climodr environment and allow terra-functions to use 70% of RAMenvrmt <- envi.create(proj_path = tempdir(),                      memfrac = 0.7)# Load the climodr example data into the current climodr environmentclim.sample(envrmt = envrmt)#prepare csv-filesprep.csv(envrmt = envrmt,         method = "proc",         save_output = TRUE)#process csv-filescsv_data <- proc.csv(envrmt = envrmt,                     method = "monthly",                     rbind = TRUE,                     save_output = TRUE)#extract station coordinatescsv_spat <- spat.csv(envrmt = envrmt,                     method = "monthly",                     des_file = "plot_description.csv",                     save_output = TRUE)head(csv_spat)