###################################################################################

###  R code to aquire and process MOD06_L2 cloud data from the MODIS platform

## connect to server of choice

#system("ssh litoria")

#R

library(sp)

library(rgdal)

library(reshape)

library(ncdf4)

library(geosphere)

library(rgeos)

library(multicore)

library(raster)

library(lattice)

library(rgl)

library(hdf5)

library(spgrass6)

X11.options(type="Xlib")

ncores=20  #number of threads to use

setwd("/home/adamw/personal/projects/interp")

setwd("/home/adamw/acrobates/projects/interp")

roi=readOGR("data/regions/Test_sites/Oregon.shp","Oregon")

roi=spTransform(roi,CRS(" +proj=sinu +lon_0=0 +x_0=0 +y_0=0"))

### Downloading data from LAADSWEB

# subset by geographic area of interest

# subset: 40-47, -115--125

## download data from ftp site.  Unfortunately the selection has to be selected using the website and orders downloaded via ftp.

system("wget -r --retr-symlinks ftp://ladsweb.nascom.nasa.gov/orders/500676499/ -P /home/adamw/acrobates/projects/interp/data/modis/MOD06_L2_hdf")

datadir="data/modis/MOD06_L2_hdf"

outdir="data/modis/MOD06_L2_hdf2"

summarydatadir="data/modis/MOD06_climatologies"

  path=list.files(datadir,full=T,recursive=T,pattern="hdf"),

  file=basename(list.files(datadir,full=F,recursive=T,pattern="hdf")))

fs$date=as.Date(substr(fs$file,11,17),"%Y%j")

fs$month=format(fs$date,"%m")

fs$year=format(fs$date,"%Y")

fs$time=substr(fs$file,19,22)

fs$datetime=as.POSIXct(strptime(paste(substr(fs$file,11,17),substr(fs$file,19,22)), '%Y%j %H%M'))

fs$file=as.character(fs$file)

## output ROI

#get bounding box of region in m

ge=SpatialPoints(data.frame(lon=c(-125,-115),lat=c(40,47)))

projection(ge)=CRS("+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs")

ge2=spTransform(ge, CRS(" +proj=sinu +lon_0=0 +x_0=0 +y_0=0"))

## vars

vars=as.data.frame(matrix(c(

  "Cloud_Effective_Radius_Uncertainty",  "CERU",

  "Cloud_Optical_Thickness",             "COT",

  "Cloud_Optical_Thickness_Uncertainty", "COTU",

  "Cloud_Water_Path",                    "CWP",

  "Cloud_Water_Path_Uncertainty",        "CWPU",

  "Cloud_Phase_Optical_Properties",      "CPOP",

  "Cloud_Multi_Layer_Flag",              "CMLF",

  "Cloud_Mask_1km",                      "CM1",

  "Quality_Assurance_1km",               "QA"),

### Installation of hegtool

## needed 32-bit libraries and java for program to install correctly

# system(paste("hegtool -h ",fs$path[1],sep=""))

#### Function to generate hegtool parameter file for multi-band HDF-EOS file

  print(paste("Starting file",basename(file)))

  outfile=paste(outdir,"/",fs$file[i],sep="")

#  date=fs$date[1]

#  origin=as.POSIXct("1970-01-01 00:00:00",tz="GMT")

### First write the parameter file (careful, heg is very finicky!)

  hdr=paste("NUM_RUNS = ",length(vars),"|MULTI_BAND_HDFEOS:",length(vars),sep="")

  grp=paste("

BEGIN

INPUT_FILENAME=",file,"

OBJECT_NAME=mod06

FIELD_NAME=",vars,"|

BAND_NUMBER = 1

OUTPUT_PIXEL_SIZE_X=1000

OUTPUT_PIXEL_SIZE_Y=1000

SPATIAL_SUBSET_UL_CORNER = ( ",upleft," )

SPATIAL_SUBSET_LR_CORNER = ( ",lowright," )

OUTPUT_PROJECTION_TYPE = SIN

ELLIPSOID_CODE = WGS84

OUTPUT_FILENAME = ",outfile,"

END

",sep="")

  ## if any remnants from previous runs remain, delete them

  if(length(list.files(tempdir(),pattern=basename(file)))>0)

    file.remove(list.files(tempdir(),pattern=basename(file),full=T))

  ## write it to a file

  cat(c(hdr,grp)    , file=paste(tempdir(),"/",basename(file),"_MODparms.txt",sep=""))

  ## now run the swath2grid tool  - must be run as root (argh!)!

  ## write the tiff file

  log=system(paste("sudo MRTDATADIR=/usr/local/heg/data ",

    "PGSHOME=/usr/local/heg/TOOLKIT_MTD PWD=/home/adamw /usr/local/heg/bin/swtif -p ",

    paste(tempdir(),"/",basename(file),"_MODparms.txt -d",sep=""),sep=""),intern=T)

      print(paste("Finished ", file))

}

### update fs with completed files

fs$complete=fs$file%in%list.files(outdir,pattern="hdf$")

table(fs$complete)

#### Run the gridding procedure

system("sudo ls")

mclapply(which(!fs$complete),function(fi){

  swath2grid(fi,vars=vars$variable,files=fs,

             outdir=outdir,

             upleft="47 -125",lowright="40 -115")},

         mc.cores=24)

##############################################################

### Import to GRASS for processing

## fucntion to convert binary to decimal to assist in identifying correct values

b2d=function(x) sum(x * 2^(rev(seq_along(x)) - 1)) #http://tolstoy.newcastle.edu.au/R/e2/help/07/02/10596.html

## for example:

b2d(c(T,T))

### create (or connect to) grass location

gisDbase="/media/data/grassdata"

gisLocation="oregon"

gisMapset="mod06"

Sys.setenv(GRASS_OVERWRITE=1)

Sys.setenv(DEBUG=0)

### Function to extract various SDSs from a single gridded HDF file and use QA data to throw out 'bad' observations

  tf=paste(tempdir(),"/grass", Sys.getpid(),"/", sep="")

  ## set up tempfile for this PID

  initGRASS(gisBase="/usr/lib/grass64",gisDbase=tf,SG=td,override=T,location="mod06",mapset="PERMANENT",home=tf,pid=Sys.getpid())

  system(paste("g.proj -c proj4=\"+proj=sinu +lon_0=0 +x_0=0 +y_0=0 +a=6371007.181 +b=6371007.181 +datum=WGS84 +units=m +no_defs\"",sep=""))

#system("g.mapset PERMANENT")

  execGRASS("r.in.gdal",input=paste("HDF4_EOS:EOS_GRID:\"",outdir,"/",fs$file[1],"\":mod06:Cloud_Mask_1km_0",sep=""),

            output="modisgrid",flags=c("quiet","overwrite","o"))

  system("g.region rast=modisgrid save=roi --overwrite")

  system("g.region roi")

  system("g.region -p")

#  getLocationProj()

  ## Identify which files to process

  nfs=length(tfs)

  ### print some summary info

  for(i in 1:nfs){

     ## Cloud Mask

     execGRASS("r.in.gdal",input=paste("HDF4_EOS:EOS_GRID:\"",file,"\":mod06:Cloud_Mask_1km_0",sep=""),

              output=paste("CM1_",i,sep=""),flags=c("overwrite","o")) ; print("")

    system(paste("r.mapcalc <<EOF

                CM_cloud_",i," =  ((CM1_",i," / 2^0) % 2) == 1  &&  ((CM1_",i," / 2^1) % 2^2) == 0 

                CM_clear_",i," =  ((CM1_",i," / 2^0) % 2) == 1  &&  ((CM1_",i," / 2^1) % 2^2) == 3 

EOF",sep=""))

    ## QA

             output=paste("QA_",i,sep=""),flags=c("overwrite","o")) ; print("")

   system(paste("r.mapcalc <<EOF

                 QA_COT2_",i,"=  ((QA_",i," / 2^1) % 2^2 )==3

                 QA_COT3_",i,"=  ((QA_",i," / 2^3) % 2^2 )==0

                 QA_CER_",i,"=   ((QA_",i," / 2^5) % 2^1 )==1

                 QA_CER2_",i,"=  ((QA_",i," / 2^6) % 2^2 )==3

EOF",sep="")) 

#                 QA_CWP2_",i,"=  ((QA_",i," / 2^9) % 2^2 )==3

   ## Optical Thickness

   execGRASS("r.in.gdal",input=paste("HDF4_EOS:EOS_GRID:\"",file,"\":mod06:Cloud_Optical_Thickness",sep=""),

            flags=c("overwrite","o")) ; print("")

            flags=c("overwrite","o")) ; print("")

   ## set CER to 0 in clear-sky pixels

   system(paste("r.mapcalc \"CER2_",i,"=if(CM_clear_",i,"==0,CER_",i,",0)\"",sep=""))   

   ## Cloud Water Path

#            output=paste("CWP_",i,sep=""),title="cloud_water_path",

#            flags=c("overwrite","o")) ; print("")

#   execGRASS("r.null",map=paste("CWP_",i,sep=""),setnull="-9999")

         COT_denom=",paste("!isnull(COT2_",1:nfs,")",sep="",collapse="+"),"

         COT_numer=",paste("if(isnull(COT2_",1:nfs,"),0,COT2_",1:nfs,")",sep="",collapse="+"),"

         COT_daily=COT_numer/COT_denom

         CER_denom=",paste("!isnull(CER2_",1:nfs,")",sep="",collapse="+"),"

         CER_numer=",paste("if(isnull(CER2_",1:nfs,"),0,CER2_",1:nfs,")",sep="",collapse="+"),"

         CER_daily=CER_numer/CER_denom

  #### Write the file to a geotiff

  execGRASS("r.out.gdal",input="COT_daily",output=paste(tifdir,"/COT_",format(date,"%Y%m%d"),".tif",sep=""),nodata=-999,flags=c("quiet"))

  execGRASS("r.out.gdal",input="CLD_daily",output=paste(tifdir,"/CLD_",format(date,"%Y%m%d"),".tif",sep=""),nodata=99,flags=c("quiet"))

### delete the temporary files 

  unlink_.gislock()

  system("/usr/lib/grass64/etc/clean_temp")

### print update

  print(paste(" ###################################################################               Finished ",date,"

################################################################"))

###########################################

### Now run it

tdates=tdates[!done]

###  Produce the monthly averages

fs2=data.frame(

  file=basename(list.files(tifdir,full=F,recursive=T,pattern="tif$")))

fs2$type=substr(fs2$file,1,3)

fs2$date=as.Date(substr(fs2$file,5,12),"%Y%m%d")

fs2$month=format(fs2$date,"%m")

fs2$year=format(fs2$date,"%Y")

fs2$path=as.character(fs2$path)

fs2$file=as.character(fs2$file)

# Define type/month products

vs=expand.grid(type=unique(fs2$type),month=c("01","02","03","04","05","06","07","08","09","10","11","12"))

## identify which have been completed

#done=

#  do.call(rbind,strsplit(list.files(summarydatadir),"_|[.]"))[,3]

#table(done)

#tdates=tdates[!done]

## process the summaries using the raster package

mclapply(1:nrow(vs),function(i){

  print(paste("Starting ",vs$type[i]," for month ",vs$month[i]))

  td=stack(fs2$path[which(fs2$month==vs$month[i]&fs2$type==vs$type[i])])

       filename=paste(summarydatadir,"/",vs$type[i],"_mean_",vs$month[i],".tif",sep=""),

       format="GTiff")

  calc(td,sd,na.rm=T,

       filename=paste(summarydatadir,"/",vs$type[i],"_sd_",vs$month[i],".tif",sep=""),

       format="GTiff")

  print(paste("Processing missing data for ",vs$type[i]," for month ",vs$month[i]))

  calc(td,function(i)

       sum(!is.na(i)),filename=paste(summarydatadir,"/",vs$type[i],"_count_",vs$month[i],".tif",sep=""),

       format="GTiff")

  calc(td,function(i) sum(ifelse(i==0,0,1)),

       filename=paste(summarydatadir,"/",vs$type[i],"_clear_",vs$month[i],".tif",sep=""),format="GTiff")

}