satellite-ground-truthing

This repo outlines a set of habitat-class ground truth data aggregated by USF-IMaRS for use in training of satellite image processing routines. Data provided by different sources is overviewed and standardized in the “Data Sources” reports. An exploration of the optical properties of each class is in “Class Reports”.

Data created and used here can be downloaded from box.com/satellite_ground_truth.

example data usage

# Install librarian package if you haven't already
if (!requireNamespace("librarian", quietly = TRUE)) {
  install.packages("librarian")
}
library(librarian)
shelf(
  dplyr,
  here,
  leaflet
)

  The 'cran_repo' argument in shelf() was not set, so it will use
  cran_repo = 'https://cran.r-project.org' by default.

  To avoid this message, set the 'cran_repo' argument to a CRAN
  mirror URL (see https://cran.r-project.org/mirrors.html) or set
  'quiet = TRUE'.

Load NERRS data

data <- read.csv(here("data/dwc/mangrove-jobos.csv"))

# Create a color palette
pal <- colorFactor(palette = "viridis", domain = data$occurrenceStatus)

# Create the leaflet map
leaflet(data) %>%
  addTiles() %>%
  addCircleMarkers(
    ~lon, ~lat,
    color = ~pal(occurrenceStatus),
    radius = 5,
    fillOpacity = 0.8,
    popup = ~paste("Occurrence Status:", occurrenceStatus)
  ) %>%
  addLegend(
    "bottomright", pal = pal, values = ~occurrenceStatus,
    title = "Occurrence Status",
    opacity = 1
  )