[ncl-talk] Subsetting MACAv2 files

[Toni Klemm]

Good morning,

I created spatial subsets from MACAv2 downscaled climate projections for the continental US (CONUS), however, the subsetted files have the same file as the originals (ca. 1.5 GB), even though the subset area only covers about half of CONUS (I checked). I couldn’t attach the files, but I attached the NCL script below. The NCL script I use is adapted from one I used to create subsets of vegetation projections for which the file size afterwards was about half, as one would expect. Does anyone have ideas for why the size isn’t reduced? Is the original MACAv2 data somehow compressed and gets uncompressed in the process? Any advice is much appreciated.

Thank you very much!

Best,
Toni



; ---------------------------------------------------

load "$NCARG_ROOT/lib/ncarg/nclscripts/csm/gsn_code.ncl"
load "$NCARG_ROOT/lib/ncarg/nclscripts/csm/gsn_csm.ncl"
load "$NCARG_ROOT/lib/ncarg/nclscripts/csm/contributed.ncl"

; ---------------------------------------------------

begin

RCP_in_list = [/"rcp45","rcp85"/]

RCP_out_list = [/"rcp_45","rcp_85"/]

model_list = [/"CCSM4","GFDL-ESM2M","HadGEM2-ES365","IPSL-CM5A-LR","MRI-CGCM3"/]

variable_list = [/"ppt","tdmean","tmax","tmin"/]

do h = 0, ListCount(RCP_in_list) - 1 

  do j = 0, ListCount(model_list) - 1 

    do k = 0, ListCount(variable_list) - 1 


  ; ***********************************************
  ; READ IN MACA FILE
  ; ***********************************************

  print("1 - Read in " + RCP_in_list[h](0) + "/" + model_list[j](0) + "/" + variable_list[k](0) + ".nc")

  MACA_f = addfile("~/NIFA/MACAv2/MACA_" + RCP_in_list[h](0) + "/" + model_list[j](0) + "/" + variable_list[k](0) + ".nc", "r")


  ; ***********************************************
  ; READ IN VARIABLES
  ; ***********************************************

  print("2 - Read in variable")

  if(variable_list[k](0) .eq. "ppt") then
  	variable = MACA_f->ppt(:,:,:)
  end if

  if(variable_list[k](0) .eq. "tdmean") then
  	variable = MACA_f->tdmean(:,:,:)
  end if

  if(variable_list[k](0) .eq. "tmax") then
  	variable = MACA_f->tmax(:,:,:)
  end if

  if(variable_list[k](0) .eq. "tmin") then
  	variable = MACA_f->tmin(:,:,:)
  end if

  lat = MACA_f->lat
  lon = MACA_f->lon
  time = MACA_f->time
  description = variable at long_name
  

  ; ***********************************************
  ; CREATE US-SUBSET OF THE GLOBAL DATA
  ; ***********************************************

  print("3 - Create lat/lon subset")

  ; let's choose latitudes of 
    latind = (/25,50/)

  ; let's choose longitudes of 
    lonind = (/-118,-92/)

  lti = ind_nearest_coord(latind,lat,0)  ; lti, lni = variables, ind_nearest_coord = pre-defined functions to determine the indices of locations closest to the coordinate array, needed later to define var_subdomain_3D
  lni = ind_nearest_coord(lonind,lon,0)

  lat_subdomain = lat(lti(0):lti(1))
  lon_subdomain = lon(lni(0):lni(1))

  var_subdomain_3D = variable(:,lti(0):lti(1),lni(0):lni(1))  ; define the subdomain based on latind and lonind


  ; ***********************************************
  ; 3 - WRITE THE SUBSET INTO NEW netCDF FILE
  ; ***********************************************

  print("4 - Write subset into new netCDF file")

    netCDF1 = True    ; Output format is NetCDF

  if (netCDF1) then
    diro = "~/NIFA/MACAv2/subset_lat_lon/" + RCP_out_list[h](0) + "/" + model_list[j](0) + "/"
    filo = variable_list[k](0) + "_lat_lon.nc"

  end if

  setfileoption("nc","Format","LargeFile")

  if (netCDF1) then
    system("/bin/rm -f "+ diro + filo)   ; removes old files with the same name if they are present
    ncdf = addfile(diro + filo,"c")

    setfileoption(ncdf,"DefineMode",True)

    ; create attributes
    fAtt = True
    fAtt at title = "MACAv2 data, RCP: " + RCP_out_list[h](0) + " Climate model: " + model_list[j](0) + " Variable: " + variable_list[k](0)
    fAtt at description = description
    fAtt at Conventions = "None"
    fAtt at creation_date = systemfunc("date")

    fileattdef(ncdf,fAtt)

    dimNames = (/"time","lat","lon"/)
    dimSizes = (/dimsizes(time),dimsizes(lat_subdomain),dimsizes(lon_subdomain)/)
    dimUnlim = (/True,False,False/)

    filedimdef(ncdf,dimNames,dimSizes,dimUnlim)

    filevardef(ncdf,"time",typeof(time),(/"time"/))
    filevardef(ncdf,"lat",typeof(lat_subdomain),(/"lat"/))
    filevardef(ncdf,"lon",typeof(lon_subdomain),(/"lon"/))
    filevardef(ncdf,"var",typeof(var_subdomain_3D),(/"time","lat","lon"/))

    ; now write all the variables to the file

    ncdf->time = (time)
    ncdf->lat  = (lat_subdomain)
    ncdf->lon  = (lon_subdomain)
    ncdf->var  = (var_subdomain_3D)

  end if

  print("**** DONE ****")
  print("")

  delete([/variable,var_subdomain_3D,lat,lon/])


    end do   ; end variable list loop

  end do  ; end model list loop

end do  ; end RCP list loop

end



Toni Klemm, Ph.D.
Postdoctoral Research Associate
Department of Ecosystem Science and Management
College of Agriculture and Life Sciences
Texas A&M University, College Station, TX
Contributor to the Early Career Climate Forum <http://www.eccforum.org/>
www.toni-klemm.de <http://www.toni-klemm.de/> | @toniklemm <http://twitter.com/toniklemm>








-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.ucar.edu/pipermail/ncl-talk/attachments/20180907/8a4cb76d/attachment.html>