#DATE: 12/27/2012                                                                                 

infile3<-"LST_dates_var_names.txt"                        #LST dates name

infile4<-"models_interpolation_05142012.txt"              #Interpolation model names

infile5<-"mean_day244_rescaled.rst"                       #Raster or grid for the locations of predictions

infile6<-"LST_files_monthly_climatology.txt"

inlistf<-"list_files_05032012.txt"                        #Stack of images containing the Covariates

path<-"/home/parmentier/Data/IPLANT_project/data_Oregon_stations_10242012_GAM"

setwd(path)

#Station location of the study area

stat_loc<-read.table(paste(path,"/","location_study_area_OR_0602012.txt",sep=""),sep=",", header=TRUE)

#GHCN Database for 1980-2010 for study area (OR) 

data3<-read.table(paste(path,"/","ghcn_data_TMAXy1980_2010_OR_0602012.txt",sep=""),sep=",", header=TRUE)

out_prefix<-"_365d_GAM_fus5_all_lstd_12302012"                #User defined output prefix

#projection used in the interpolation of the study area

source("GAM_fusion_function_multisampling_12302012.R")

###Reading the station data and setting up for models' comparison

filename<-sub(".shp","",infile1)             #Removing the extension from file.

ghcn<-readOGR(".", filename)                 #reading shapefile 

CRS<-proj4string(ghcn)                       #Storing projection information (ellipsoid, datum,etc.)

mean_LST<- readGDAL(infile5)                 #Reading the whole raster in memory. This provides a grid for kriging

proj4string(mean_LST)<-CRS                   #Assigning coordinate information to prediction grid.

ghcn <- transform(ghcn,Northness = cos(ASPECT*pi/180)) #Adding a variable to the dataframe

ghcn <- transform(ghcn,Eastness = sin(ASPECT*pi/180))  #adding variable to the dataframe.

ghcn <- transform(ghcn,Northness_w = sin(slope*pi/180)*cos(ASPECT*pi/180)) #Adding a variable to the dataframe

ghcn <- transform(ghcn,Eastness_w = sin(slope*pi/180)*sin(ASPECT*pi/180))  #adding variable to the dataframe.

#Remove NA for LC and CANHEIGHT

dates <-readLines(paste(path,"/",infile2, sep=""))

LST_dates <-readLines(paste(path,"/",infile3, sep=""))

models <-readLines(paste(path,"/",infile4, sep=""))

lines<-read.table(paste(path,"/",inlistf,sep=""), sep=" ")                  #Column 1 contains the names of raster files

inlistvar<-lines[,1]

inlistvar<-paste(path,"/",as.character(inlistvar),sep="")

covar_names<-as.character(lines[,2])                                         #Column two contains short names for covaraites

s_raster<- stack(inlistvar)                                                  #Creating a stack of raster images from the list of variables.

layerNames(s_raster)<-covar_names                                            #Assigning names to the raster layers

projection(s_raster)<-CRS

#stat_val<- extract(s_raster, ghcn3)                                          #Extracting values from the raster stack for every point location in coords data frame.

pos<-match("ASPECT",layerNames(s_raster)) #Find column with name "value"

r1<-raster(s_raster,layer=pos)             #Select layer from stack

pos<-match("slope",layerNames(s_raster)) #Find column with name "value"

r2<-raster(s_raster,layer=pos)             #Select layer from stack

N<-cos(r1*pi/180)

E<-sin(r1*pi/180)

Nw<-sin(r2*pi/180)*cos(r1*pi/180)   #Adding a variable to the dataframe

Ew<-sin(r2*pi/180)*sin(r1*pi/180)   #Adding variable to the dataframe.

pos<-match("LC4",layerNames(s_raster)) #Find column with name "value"

LC4<-raster(s_raster,layer=pos)             #Select layer from stack

s_raster<-dropLayer(s_raster,pos)

LC4[is.na(LC4)]<-0

pos<-match("LC6",layerNames(s_raster)) #Find column with name "value"

LC6<-raster(s_raster,layer=pos)             #Select layer from stack

s_raster<-dropLayer(s_raster,pos)

LC6[is.na(LC6)]<-0

LC_s<-stack(LC1,LC3,LC4,LC6)

layerNames(LC_s)<-c("LC1_forest","LC3_grass","LC4_crop","LC6_urban")

plot(LC_s)

xy<-coordinates(r1)  #get x and y projected coordinates...

xy_latlon<-project(xy, CRS, inv=TRUE) # find lat long for projected coordinats (or pixels...)

lon<-raster(xy_latlon) #Transform a matrix into a raster object ncol=ncol(r1), nrow=nrow(r1))

ncol(lon)<-ncol(r1)

nrow(lon)<-nrow(r1)

extent(lon)<-extent(r1)

projection(lon)<-CRS  #At this stage this is still an empty raster with 536 nrow and 745 ncell 

lat<-lon

values(lon)<-xy_latlon[,1]

values(lat)<-xy_latlon[,2]

r<-stack(N,E,Nw,Ew,lon,lat,LC1,LC3,LC4,LC6, CANHEIGHT,ELEV_SRTM)

rnames<-c("Northness","Eastness","Northness_w","Eastness_w", "lon","lat","LC1","LC3","LC4","LC6","CANHEIGHT","ELEV_SRTM")

layerNames(r)<-rnames

s_raster<-addLayer(s_raster, r)

date1<-ISOdate(data3$year,data3$month,data3$day) #Creating a date object from 3 separate column

date2<-as.POSIXlt(as.Date(date1))

data3$date<-date2

d<-subset(data3,year>=2000 & mflag=="0" ) #Selecting dataset 2000-2010 with good quality: 193 stations

#May need some screeing??? i.e. range of temp and elevation...

d1<-aggregate(value~station+month, data=d, mean)  #Calculate monthly mean for every station in OR

id<-as.data.frame(unique(d1$station))     #Unique station in OR for year 2000-2010: 193 but 7 loss of monthly avg    

dst<-merge(d1, stat_loc, by.x="station", by.y="STAT_ID")   #Inner join all columns are retained

#This allows to change only one name of the data.frame

pos<-match("value",names(dst)) #Find column with name "value"

names(dst)[pos]<-c("TMax")

dst$TMax<-dst$TMax/10                #TMax is the average max temp for monthy data

#dstjan=dst[dst$month==9,]  #dst contains the monthly averages for tmax for every station over 2000-2010

#Extracting covariates from stack

coords<- dst[c('lon','lat')]              #Define coordinates in a data frame

coordinates(dst)<-coords                      #Assign coordinates to the data frame

proj4string(dst)<-CRS_locs_WGS84                  #Assign coordinates reference system in PROJ4 format

dst_month<-spTransform(dst,CRS(CRS_interp))     #Project from WGS84 to new coord. system

stations_val<-extract(s_raster,dst_month)  #extraction of the infomration at station location

stations_val<-as.data.frame(stations_val)

dst_extract<-cbind(dst_month,stations_val)

dst<-dst_extract

dst_all<-dst

dst<-subset(dst,dst$TMax>-15 & dst$TMax<40)

dst<-subset(dst,dst$ELEV_SRTM>0) #This will drop two stations...or 24 rows

ghcn_all<-ghcn

ghcn_test<-subset(ghcn,ghcn$value>-150 & ghcn$value<400)

ghcn_test2<-subset(ghcn_test,ghcn_test$ELEV_SRTM>0)

ghcn<-ghcn_test2