MatchingLIBSandPIXL.Rmd

---
title: "Combining LIBS and PIXL Data"
author: "Margo VanEsselstyn"
date: "`r Sys.Date()`"
output:
  pdf_document:
    toc: yes
  html_document:
    toc: yes
subtitle: "DAR Mars"
---

```{r setup, include=FALSE}
# Set the default CRAN repository
local({r <- getOption("repos")
       r["CRAN"] <- "http://cran.r-project.org" 
       options(repos=r)
})

if (!require("pandoc")) {
  install.packages("pandoc")
  library(pandoc)
}

if (!require("rmarkdown")) {
  install.packages("rmarkdown")
  library(rmarkdown)
}
if (!require("tidyverse")) {
  install.packages("tidyverse")
  library(tidyverse)
}
if (!require("stringr")) {
  install.packages("stringr")
  library(stringr)
}

if (!require("ggbiplot")) {
  install.packages("ggbiplot")
  library(ggbiplot)
}

if(!require("knitr")){
  install.packages("knitr")
  library(knitr)
}

if(!require("cluster")){
  install.packages("cluster")
  library(cluster)
}

if(!require("ggtern")){
  install.packages("ggtern")
  library(ggtern)
}

if(!require("caret")){
  install.packages("caret")
  library(caret)
}

if(!require("geosphere")){
  install.packages("geosphere")
  library(geosphere)
}

knitr::opts_chunk$set(echo = TRUE)
```


### Data Preparation

Load in LIBS data
```{r, data01}
#load in LIBS data
libs.df <- readRDS("/academics/MATP-4910-F24/DAR-Mars-F24/Data/supercam_libs_moc_loc.Rds")

#Drop the standard deviation features, the sum of the percentages, 
#the distance, and the total frequencies
libs.df <- libs.df %>% 
  select(!(c(distance_mm,Tot.Em.,SiO2_stdev,TiO2_stdev,Al2O3_stdev,FeOT_stdev,
             MgO_stdev,Na2O_stdev,CaO_stdev,K2O_stdev,Total)))

# Convert the points to numeric
libs.df$point <- as.numeric(libs.df$point)
libs.df[,6:13] <- sapply(libs.df[,6:13],as.numeric)

#remove the scct/reference samples
libs.df<-libs.df%>%
  filter(!(grepl("scct", target)))

#add a column to indicate the nearest pixl
libs.df<-cbind(nearestpixl=0,libs.df)

#make a dataframe of just the LIBS Lat/Long and target name and remove duplicates
libstargets.df<-libs.df[,c(1,3,4,5)]
libstargets.df<-distinct(libstargets.df)
```

Load in PIXL data

```{r, data02}
#read in pixl data with lat/long
pixl.df<-readRDS("/academics/MATP-4910-F24/DAR-Mars-F24/StudentData/pixl_sol_coordinates.Rds")

#include only pixl metadata
pixl.df<-pixl.df %>%
  select(c(1,2,19,20,22))

#convert Lat/Long to numeric
pixl.df$Lat <- as.numeric(pixl.df$Lat)
pixl.df$Long <- as.numeric(pixl.df$Long)

#remove rows so we only have one sample per abrasion and remove atmospheric sample
pixl.df<-pixl.df[c(2,4,6,8,10,12,14,16),]
```


### Combining datasets

```{r}
distance=100
distCosine(pixl.df[1,c(1,2)],libstargets.df[1,c(2,3)], r=3393169)
for(i in 1:nrow(pixl.df)) {
    libstargets.df<-libstargets.df%>%mutate(nearestpixl = ifelse(distHaversine(pixl.df[i,c(1,2)],c(lat,lon),r=3393169),pixl.df[i,5], nearestpixl))

}
```

```{r}
libstargets.df<-cbind(libstargets.df,"Distance"=0,"Bellegrade"=0,"Dourbes"=0,"Quartier"=0,"Alfalfa"=0,"ThorntonGap"=0,"BerryHollow"=0,"Novarupta"=0,"UganikIsland"=0)
```

```{r}
#DistCosine(pixl.df[1,c(1,2)],libstargets.df[1,c(2,3)], r=3393169)

for(i in 1:nrow(libstargets.df)) {
    libstargets.df[i,c(6:13)]<-c(distHaversine(pixl.df[1,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[2,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[3,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[4,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[5,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[6,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[7,c(1,2)],libstargets.df[i,c(2,3)],r=3393169),
                                 distHaversine(pixl.df[8,c(1,2)],libstargets.df[i,c(2,3)],r=3393169))
    
    libstargets.df[i,1]<-which.min(libstargets.df[i,c(6:13)])
    libstargets.df[i,5]<-min(libstargets.df[i,c(6:13)])
}

libstargets.df$nearestpixl<-as.factor(libstargets.df$nearestpixl)

levels(libstargets.df$nearestpixl)<-(c("Bellegrade","Dourbes","Quartier","Alfalfa","ThorntonGap","BerryHollow","Novarupta","UganikIsland"))
```


```{r}
Bellegrade<-libstargets.df[libstargets.df$nearestpixl=="Bellegrade",]$target
Dourbes<-libstargets.df[libstargets.df$nearestpixl=="Dourbes",]$target
Quartier<-libstargets.df[libstargets.df$nearestpixl=="Quartier",]$target
Alfalfa<-libstargets.df[libstargets.df$nearestpixl=="Alfalfa",]$target
ThorntonGap<-libstargets.df[libstargets.df$nearestpixl=="ThorntonGap",]$target
BerryHollow<-libstargets.df[libstargets.df$nearestpixl=="BerryHollow",]$target
Novarupta<-libstargets.df[libstargets.df$nearestpixl=="Novarupta",]$target
UganikIsland<-libstargets.df[libstargets.df$nearestpixl=="UganikIsland",]$target
```


### Ternary Diagram
```{r}
meters=100

included.libs<-(libstargets.df%>%
  filter(Distance<meters))$target

libs.matrix <-libs.df %>%
  filter(target %in% included.libs)

libs.matrix <- libs.matrix[,c(5,7:14)]

libs.tern <- as.data.frame(libs.matrix) %>%
  mutate(x=(SiO2+Al2O3)/100,y=(FeOT+MgO)/100,z=(CaO+Na2O+K2O)/100) %>%
  select(-c(SiO2,Al2O3,FeOT,MgO,CaO,Na2O,K2O,TiO2))

libs.tern<-cbind("Abrasion"=0,libs.tern)

libs.tern<-libs.tern%>%
  mutate(Abrasion = ifelse(target%in%Alfalfa,"Alfalfa", 
                    ifelse(target %in% Bellegrade, "Belegrade",
                    ifelse(target %in% BerryHollow, "BerryHollow",
                    ifelse(target %in% Dourbes, "Dourbes",
                    ifelse(target %in% Novarupta, "Novarupta",
                    ifelse(target %in% Quartier, "Quartier",
                    ifelse(target %in% ThorntonGap, "ThorntonGap",
                    ifelse(target %in% UganikIsland, "UganikIsland",Abrasion)))))))))

kabledf<-rbind("Distance (m)"=meters,"Targets"=length(included.libs),"Points"=nrow(libs.tern))

kable(kabledf)
```


```{r}
ggtern(libs.tern, ggtern::aes(x=x,y=y,z=z)) +
  geom_point(data=libs.tern,aes(color=Abrasion,alpha=0.5)) + 
  theme_rgbw() + 
  labs(title=paste("Mars LIBS Data Within",distance,"meters of PIXL",sep=" "),
       x="Si+Al",
       y="Fe+Mg",
       z="Ca+Na+K")+theme(legend.position="right") + 
  guides(alpha="none")
```


### Line plot

```{r}
meters=100

included.libs<-(libstargets.df%>%
  filter(Distance<meters))$target


libs.matrix <-libs.df %>%
  filter(target %in% included.libs)

libs.matrix <- libs.matrix[,c(5,7:14)]

libs.matrix<-libs.matrix[,c(1:2,4:9,3)]

libs.matrix<-cbind("Abrasion"=0,libs.matrix)

libs.matrix<-libs.matrix%>%
  mutate(Abrasion = ifelse(target%in%Alfalfa,"Alfalfa", 
                    ifelse(target %in% Bellegrade, "Belegrade",
                    ifelse(target %in% BerryHollow, "BerryHollow",
                    ifelse(target %in% Dourbes, "Dourbes",
                    ifelse(target %in% Novarupta, "Novarupta",
                    ifelse(target %in% Quartier, "Quartier",
                    ifelse(target %in% ThorntonGap, "ThorntonGap",
                    ifelse(target %in% UganikIsland, "UganikIsland",Abrasion)))))))))

libs.matrix<-cbind(libsorpixl=1,libs.matrix)
```


```{r, data03}
#read in pixl data with lat/long
pixl.df<-readRDS("/academics/MATP-4910-F24/DAR-Mars-F24/StudentData/pixl_sol_coordinates.Rds")

pixl.df<-pixl.df %>%
  select(c(5:8,12:14,17,19,18,22))

#reorder pixl columns so that it matches libs data organization
pixl.df<-pixl.df[,c(11,10,4,3,8,2,6,1,5,7)]

#remove atmospheric sample
pixl.df<-pixl.df[2:16,]

pixl.df<-cbind(libsorpixl=0,pixl.df)
```

```{r}
colnames(pixl.df)<-colnames(libs.matrix)
pixllibs.df<-rbind(pixl.df,libs.matrix)
```