Introduction

Summary of 2019 S1 and S2 data comapred to Indonesian Palm data from https://essd.copernicus.org/articles/13/1211/2021/. values extracted from GEE script - https://code.earthengine.google.com/3d54f3d02d1dc0e4d7347ea5b6b11ab0

Data summary

Summary of the number of polygons of each class with 2019 Palm mask as training

library(dplyr)
library(ggplot2)
library(knitr)
library(plotly)
library(caret)


setwd("~/Downloads")

d <- read.csv("PalmExplore_S1S2.csv")
d <- as.data.frame(d)

WC <- c("Industrial", "Smallholder", "Other landcover")
joinC <- data.frame(classification = c(1:3), classTxt = WC, WCcolor = c('#CBE39B', '#FEE391', '#009474'))
d <- merge(d, joinC, by = "classification")


d <- d %>% dplyr::select(-system.index, -.geo)
d <- na.omit(d)

#summary of interpretation

summary <- d %>% group_by(classTxt) %>% summarize(n())
kable(summary)
classTxt n()
Industrial 1018
Other landcover 3481
Smallholder 480

Violin plots

With 2019 palm prediction as training

RSvars <- c("IRECI", "NDVI", "NDVI705", "NDWI", "PolRatio", "REIP", "VH_MTF", "VV_MTF", "green", "nir", "re1", "re2", "re3", "red", "swir1",             "swir2")


for (i in 1:length(RSvars)){
  var <- RSvars[i]
  print(
  ggplot(d, aes_string(x = "classTxt", y = var, fill = "classTxt")) + 
    geom_violin() +
    scale_fill_manual(name = "", values=c('#ff0000', '#696969', '#ef00ff')) +
    xlab("Class")
  )
}

Violin plots - with no other

With 2019 palm prediction as training

d <- filter(d, classification != 3)
for (i in 1:length(RSvars)){
  var <- RSvars[i]
  print(
  ggplot(d, aes_string(x = "classTxt", y = var, fill = "classTxt")) + 
    geom_violin() +
    scale_fill_manual(name = "", values=c('#ff0000','#ef00ff')) +
    xlab("Class")
  )
}