🔴 1. Exploratory Spatial Data Analysis

1.1 Exploring dataset with rgee

library(rgee)
library(tidyrgee)
library(sf)
library(terra)
library(raster)
library(stars)
library(viridis)
library(ggplot2)
library(mapview)
library(mlr3)
library(mlr3spatial)
ee_Initialize()
#> ── rgee 1.1.5 ─────────────────────────────────────── earthengine-api 0.1.326 ── 
#>  ✔ user: not_defined
#>  ✔ Initializing Google Earth Engine:
 ✔ Initializing Google Earth Engine:  DONE!
#> 
 ✔ Earth Engine account: users/ambarja 
#> ────────────────────────────────────────────────────────────────────────────────

The Earth Engine DataSet has several variables, in this example, we are going to visualize the night lights dataset.

# Setup the colour palette with the elevation values
viz = list(
  min = 0,
  max = 60,
  palette = mako(n = 100)
  )

# Mapping the world elevation
ee$ImageCollection("NOAA/VIIRS/DNB/MONTHLY_V1/VCMSLCFG")$
  select("avg_rad")$
  filterDate("2021-01-01","2021-12-31")$
  max() %>%
  Map$addLayer(name = "Night light",visParams = viz) + 
  Map$addLegend(visParams = viz, name = "Elevation")

Exploring the NOAA/VIIRS/DNB/MONTHLY_V1/VCMSLCFG dataset with tidyrgee

modis_ic <- ee$ImageCollection$Dataset$NOAA_VIIRS_DNB_MONTHLY_V1_VCMSLCFG |> 
  as_tidyee()

head(modis_ic$vrt)
#> # A tibble: 6 × 8
#>   id            time_start          syste…¹ date       month  year   doy band_…²
#>   <chr>         <dttm>              <chr>   <date>     <dbl> <dbl> <dbl> <list> 
#> 1 NOAA/VIIRS/D… 2014-01-01 00:00:00 201401… 2014-01-01     1  2014     1 <chr>  
#> 2 NOAA/VIIRS/D… 2014-02-01 00:00:00 201402… 2014-02-01     2  2014    32 <chr>  
#> 3 NOAA/VIIRS/D… 2014-03-01 00:00:00 201403… 2014-03-01     3  2014    60 <chr>  
#> 4 NOAA/VIIRS/D… 2014-04-01 00:00:00 201404… 2014-04-01     4  2014    91 <chr>  
#> 5 NOAA/VIIRS/D… 2014-05-01 00:00:00 201405… 2014-05-01     5  2014   121 <chr>  
#> 6 NOAA/VIIRS/D… 2014-06-01 00:00:00 201406… 2014-06-01     6  2014   152 <chr>  
#> # … with abbreviated variable names ¹​system_index, ²​band_names

🔴 2. Random Forest Model

🔴 3. Predicition Malaria

🔴 4. Precision and Accuracy