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)))

#make a dataframe of just the LIBS Lat/Long and target name and remove duplicates
libstargets.df<-cbind("nearestpixl"=0,libs.df[,1:4])
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}
# Create a new dataframe with the LIBS metatdata as well as features corresponding to each PIXL Abrasion
libstargets.df<-cbind(libstargets.df,"Distance"=0,"Bellegrade"=0,"Dourbes"=0,"Quartier"=0,"Alfalfa"=0,"ThorntonGap"=0,"BerryHollow"=0,"Novarupta"=0,"UganikIsland"=0)
```

```{r}
#Calculate the distance between each LIBS target and each PIXL abrasion, then fill in the minimum distances
for(i in 1:nrow(libstargets.df)) {
    libstargets.df[i,c(7:14)]<-c(distHaversine(pixl.df[1,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[2,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[3,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[4,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[5,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[6,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[7,c(1,2)],libstargets.df[i,c(3,4)],r=3393169),
                                 distHaversine(pixl.df[8,c(1,2)],libstargets.df[i,c(3,4)],r=3393169))
    
    libstargets.df[i,1]<-which.min(libstargets.df[i,c(7:14)])
    libstargets.df[i,6]<-min(libstargets.df[i,c(7:14)])
}

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

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


```{r}
#Create vectors of LIBS targets corresponding to each PIXL Abrasion
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
```

```{r}
#Add the nearest Abrasion to the LIBS data
libs.pixl.merged <- cbind("Abrasion"=0,libs.df)

libs.pixl.merged<-libs.pixl.merged%>%
  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, "Uganik Island",Abrasion)))))))))

targetdistance<-libstargets.df[,2:6]
libs.pixl.merged<-merge(libs.pixl.merged,targetdistance,by=c("target","sol","lat","lon"),all.x=T)
```

```{r}
#Add back some pixl features
pix<-pixl.df[,c(1,2,4,5)]
libs.pixl <- merge(libs.pixl.merged, pix, by.x="Abrasion",by.y="abrasion",all.x=TRUE)

#rename and reorder columns
libs.pixl<-cbind("LIBS.Target"=libs.pixl$target,libs.pixl[,4:5],"LIBS.Sol"=libs.pixl$sol,"LIBS.Point"=libs.pixl$point,"Distance"=libs.pixl$Distance,"PIXL.Abrasion"=libs.pixl$Abrasion,libs.pixl[,16:18],libs.pixl[,7:14])
colnames(libs.pixl)<-c("LIBS.Target","LIBS.Lat","LIBS.Lon","LIBS.Sol","LIBS.Point",   "Distance","PIXL.Abrasion","PIXL.Lat","PIXL.Lon","PIXL.Campaign","LIBS.SiO2","LIBS.TiO2","LIBS.Al2O3","LIBS.FeOT","LIBS.MgO","LIBS.CaO","LIBS.Na2O","LIBS.K2O")
```

```{r}
#setwd("~/DAR-Mars-F24/StudentData")
#saveRDS(libs.pixl,"PIXL_LIBS_Combined.Rds")
```

The libs.pixl dataframe is now saved to PIXL_LIBS_Combined.Rds, which can be found in the StudentData folder. 

### Ternary Diagram

Example of creating a ternary plot filtering the combined LIBS and PIXL data
```{r}
libs.tern <- libs.pixl %>%
  mutate(x=(LIBS.SiO2+LIBS.Al2O3)/100,y=(LIBS.FeOT+LIBS.MgO)/100,z=(LIBS.CaO+LIBS.Na2O+LIBS.K2O)/100)

libs.tern<-libs.tern[,c(6,7,19:21)]
```


```{r}
meters=7

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

meters=100

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


### Line plot

Example of how to add the pixl data as extra rows to the LIBS data, so that it can be graphed on the same plot

```{r}
#remove certain features from the combined pixl libs dataset
libs.matrix <- libs.pixl[,c(7,1,11,13:18,12)]

#rename columns
libs.matrix<-cbind(libsorpixl=1,libs.matrix)

colnames(libs.matrix)<-c("libsorpixl","Abrasion","targets+names","SiO2","Al2O3","FeOT","MgO","CaO","Na2O","K2O","TiO2")
```


```{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}
#rename pixl columns and combine dataframes
colnames(pixl.df)<-colnames(libs.matrix)
pixllibs.df<-rbind(pixl.df,libs.matrix)
```