CaSR River and CaSR Land Recipes

etc/clusters/eccc-science.json

@@ -1,26 +1,21 @@
 {
     "scheduler": "pbs",
     "specs": {
-        "cpus": 1,
-        "time": "04:00:00",
+        "cpus": 8,
+        "time": "01:00:00",
         "nodes": 1,
-        "partition": "",
-        "account": "",
-        "mem": "8000M"
+        "mem": "16000M"
     },
     "modules": {
         "preload": [
-            "module -q purge",
-            "module -q load StdEnv/2023",
-            "module -q load gcc/12.3"
-        ],
-        "gdal": "module -q load gdal/3.9.1",
-        "cdo": "module -q load cdo/2.2.2",
-        "ncks": "module -q load nco/5.1.7"
-    },
-    "executables": {
-        "gdal": "",
-        "nco": "",
-        "cdo": ""
+		"module -q purge",
+		". ssmuse-sh -x /fs/ssm/main/opt/gcc/gcc-4.9.1"
+	],
+        "compiler": ". ssmuse-sh -x /fs/ssm/main/opt/gcc/gcc-4.9.1", 
+	"mpi": ". ssmuse-sh -x /fs/ssm/main/opt/openmpi/openmpi-2.1.1/gcc--hpcx-1.8",
+	"gdal": ". ssmuse-sh -x /fs/ssm/main/opt/gdal/gdal-3.1.3",
+        "cdo": ". r.load.dot crd/ccrm/main/opt/cdo/cdo_2.1.1_rhel-8-amd64-64",
+        "ncl": ". r.load.dot comm/eccc/all/opt/ncl-ncarg/6.4.0/ncl_6.4.0_all",
+	"nco": " . r.load.dot cmd/cmds/ext/master/nco_5.0.5-3_rhel-8-amd64-64"
     }
 }

etc/schedulers/pbs.json

@@ -0,0 +1,6 @@
+{
+	"environment_variables": {
+		"array_task_id": "$PBS_ARRAY_INDEX",
+		"array_job_id": "$PBS_JOBID"
+	}
+}

etc/schedulers/pbs.m4

@@ -3,8 +3,8 @@
 `#'PBS -l select=__NODES__:ncpus=__CPUS__:mem=__MEM__
 `#'PBS -l walltime=__TIME__
 `#'PBS -N DATA-__SCRIPTNAME__
-`#'PBS -e __LOGDIR__/datatool_$PBS_JOBID-$PBS_ARRAY_INDEX_err.txt
-`#'PBS -o __LOGDIR__/datatool_$PBS_JOBID-$PBS_ARRAY_INDEX.txt
+`#'PBS -e __LOGDIR__/datatool_err.txt
+`#'PBS -o __LOGDIR__/datatool_log.txt
 ifdef(`__ACCOUNT__', `#PBS -A '__ACCOUNT__, `dnl')
 ifdef(`__PARTITION__', `#PBS -q '__PARTITION__, `dnl')
 ifdef(`__EMAIL__',

examples/Casr_land_example.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+# Meteorological Data Processing Workflow
+# Copyright (C) 2022, University of Saskatchewan
+#
+# This file is part of Meteorological Data Processing Workflow
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# This is a simple example to extract ECCC Casr Land (2.1) data for the 
+# South Saskatchewan River Basin (SSRB) approximate extents
+# from Jan 2015 to Dec 2017.
+
+# As is mentioned on the main webpage of the repository, it is
+# recommended to submit annual jobs for this dataset.
+
+# This example is meant to be called from the home directory, as is required by GC Science PBS job submission
+cd datatool
+echo "The current directory is: $(pwd)"
+
+# chunking done on an 'annual' basis
+./extract-dataset.sh  --dataset="casr" \
+  --dataset-dir="/home/gol000/store6/reanalysis/post_processing/casr_land_v2p1_masking/outdir/outnetcdf_all" \
+  --output-dir="$HOME/scratch/casr_land/" \
+  --start-date="2015-01-01" \
+  --end-date="2017-12-30" \
+  --lat-lims=49,54  \
+  --lon-lims=-120,-98 \
+  --variable="CaSR_Land_v2.1_TRAF_Aggregated,CaSR_Land_v2.1_SWE_Land" \
+  --prefix="casrland_21_" \
+  --cluster="./etc/clusters/eccc-science.json" \
+  --email="[email protected]" \
+  -j;
+

examples/Casr_riv_example.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+# Meteorological Data Processing Workflow
+# Copyright (C) 2022, University of Saskatchewan
+#
+# This file is part of Meteorological Data Processing Workflow
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# This is a simple example to extract ECCC Casr Rivers (2.1) data near the 
+# South Sask River Gauge (WSC 05HG001)
+# from Jan 2015 to Dec 2017.
+
+# As is mentioned on the main webpage of the repository, it is
+# recommended to submit annual jobs for this dataset.
+
+# This example is meant to be called from the home directory, as is required by GC Science PBS job submission
+cd datatool
+echo "The current directory is: $(pwd)"
+
+# chunking done on an 'annual' basis
+./extract-dataset.sh  --dataset="casrriv" \
+  --dataset-dir="/home/shyd500/data/ppp6/casr_rivers_v2p1_postproc/full_domain/" \
+  --output-dir="$HOME/scratch/casr_riv/" \
+  --start-date="2015-01-01" \
+  --end-date="2017-12-30" \
+  --lat-lims=52,52.5  \
+  --lon-lims=-107,-106.5 \
+  --variable="disc" \
+  --prefix="casrriv_21_" \
+  --cluster="./etc/clusters/eccc-science.json" \
+  --email="[email protected]" \
+  -j;
+

examples/Casrv3p1_example.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+# Meteorological Data Processing Workflow
+# Copyright (C) 2022, University of Saskatchewan
+#
+# This file is part of Meteorological Data Processing Workflow
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+# This is a simple example to extract ECCC CasrV3.1 data for the 
+# South Saskatchewan River Basin (SSRB) approximate extents
+# from Jan 2015 to Dec 2018.
+
+# As is mentioned on the main webpage of the repository, it is
+# recommended to submit annual jobs for this dataset.
+
+# This example is meant to be called from the home directory, as is required by GC Science PBS job submission
+cd datatool
+echo "The current directory is: $(pwd)"
+
+# chunking done on an 'annual' basis
+./extract-dataset.sh  --dataset="casr" \
+  --dataset-dir="/home/scar700/data/ppp6/CaSRv3.1/postproc_casr4caspar_20250416/link2out4pilot_netcdf/" \
+  --output-dir="$HOME/scratch/casr31_output/" \
+  --start-date="2018-01-01" \
+  --end-date="2018-12-30" \
+  --lat-lims=49,54  \
+  --lon-lims=-120,-98 \
+  --variable="CaSR_v3.1_P_TT_1.5m,CaSR_v3.1_A_PR0_SFC" \
+  --prefix="casrv3.1_" \
+  --cluster="./etc/clusters/eccc-science.json" \
+  --email="[email protected]" \
+  -j;
+

examples/rdrs_example_ssrb_1980_2018.sh

@@ -30,15 +30,16 @@ cd ..
 echo "The current directory is: $(pwd)"
 
 # chunking done on an 'annual' basis
-./extract-dataset.sh  --dataset=RDRS \
-  --dataset-dir="/project/rpp-kshook/Model_Output/RDRSv2.1" \
-  --output-dir="$HOME/scratch/rdrs_output/" \
+./extract-dataset.sh  --dataset=CaSR \
+  --dataset-dir="/home/scar700/data/ppp6/CaSRv3.1/postproc_casr4caspar_20250416/link2out4pilot_netcdf" \
+  --output-dir="$HOME/scratch/casr31_output/" \
   --start-date="1980-01-01" \
   --end-date="2018-12-30" \
   --lat-lims=49,54  \
   --lon-lims=-120,-98 \
-  --variable="RDRS_v2.1_P_P0_SFC,RDRS_v2.1_P_HU_1.5m,RDRS_v2.1_P_TT_1.5m,RDRS_v2.1_P_UVC_10m,RDRS_v2.1_A_PR0_SFC,RDRS_v2.1_P_FB_SFC,RDRS_v2.1_P_FI_SFC" \
-  --prefix="rdrsv2.1_" \
-  --email="[email protected]" \
+  --variable="CaSR_v3.1_P_TT_1.5m,CaSR_v3.1_A_PR0_SFC" \
+  --prefix="casrv3.1_" \
+  --cluster="./etc/clusters/eccc_science.json"
+  --email="[email protected]" \
   -j;
 

extract-dataset.sh

@@ -550,7 +550,13 @@ function call_processing_func () {
         --arg "ensembleArr" "${ensemble}" \
         --arg "modelArr" "${model}" \
         --arg "scenarioArr" "${scenario}" \
-        '$ARGS.named | with_entries(.value |= split(","))' \
+	'{
+      	  startDateArr: ($startDateArr | split(",")),
+	  endDateArr: ($endDateArr | split(",")),
+          ensembleArr: ($ensembleArr | split(",")),
+          modelArr: ($modelArr | split(",")),
+          scenarioArr: ($scenarioArr | split(","))
+ 	 }'  
       )"
 
     # job chunk variable information
@@ -563,7 +569,15 @@ function call_processing_func () {
         --arg "dateIter" "$dateIter" \
         --arg "ensembleIter" "$ensembleIter" \
         --arg "modelIter" "$modelIter" \
-        '$ARGS.named'
+	'{
+      	  ensembleLen: $ensembleLen,
+	  modelLen: $modelLen,
+	  scenarioLen: $scenarioLen,
+	  dateLen: $dateLen,
+	  dateIter: $dateIter,
+	  ensembleIter: $ensembleIter,
+	  modelIter: $modelIter
+	}'
       )"
 
     # scheduler information
@@ -584,8 +598,14 @@ function call_processing_func () {
         --arg "logDir" "$logDir" \
         --arg "email" "$email" \
         --arg "parsable" "$parsable" \
-        --argjson "specs" "$(jq -r '.specs' $cluster)" \
-        '$ARGS.named + $specs | del(.specs)' \
+	--argjson specs "$(jq '.specs' "$cluster")" \
+	'{
+      	  jobArrlen: $jobArrLen,
+	  scriptName: $scriptName,
+	  logDir: $logDir,
+	  email: $email,
+	  parsable: $parsable
+	} + $specs'
       )"
 
     # job script information
@@ -604,8 +624,18 @@ function call_processing_func () {
          --arg "latLims" "${funcArgs[latLims]}" \
          --arg "lonLims" "${funcArgs[lonLims]}" \
          --arg "prefix" "${funcArgs[prefixStr]}" \
-         --arg "cache" "${funcArgs[cache]}" \
-        '$ARGS.named' \
+	 --arg "cache" "${funcArgs[cache]}" \
+	 '{
+      	   scriptFile: $scriptFile,
+	   datasetDir: $datasetDir,
+	   variable: $variable,
+	   outputDir: $outputDir,
+	   timeScale: $timeScale,
+	   latLims: $latLims,
+	   lonLims: $lonLims,
+	   prefix: $prefix,
+	   cache: $cache
+	 }'
       )"
 
     # job module init information - not JSON as echoed as is
@@ -743,11 +773,15 @@ case "${dataset,,}" in
     call_processing_func "$recipePath/eccc-rdrs/rdrs.sh" "6months"
     ;;
 
-  # ECCC RDRS
+  # ECCC CaSR
   "casr" | "casrv3.1")
     call_processing_func "$recipePath/eccc-casr/casr.sh" "3months"
     ;;
 
+  # ECCC Casr Rivers
+  "casrriv" | "casr_riv_v2.1")
+    call_processing_func "$recipePath/eccc-casrriv/casrriv.sh" "3months"
+    ;;
   # ====================
   # Observation datasets
   # ====================

var/repos/builtin/recipes/eccc-casr/casr.sh

@@ -191,12 +191,12 @@ latLims="${minLat},${maxLat}"
 lonLims="${minLon},${maxLon}"
 
 # extract the associated indices corresponding to $latLims and $lonLims
-coordIdx="$(ncl -nQ 'coord_file='\"$domainFile\" 'minlat='"$minLat" 'maxlat='"$maxLat" 'minlon='"$minLon" 'maxlon='"$maxLon" "$coordIdxScript")"
+coordIdx="$(singularity exec $NCL_SINGULARITY_IMAGE ncl -nQ 'coord_file='\"$domainFile\" 'minlat='"$minLat" 'maxlat='"$maxLat" 'minlon='"$minLon" 'maxlon='"$maxLon" "$coordIdxScript")"
 
 # if spatial index out-of-bound, i.e., 'ERROR' is return
 if [[ "${coordIdx}" == "ERROR" ]]; then
   # extract the closest index values
-  coordIdx="$(ncl -nQ 'coord_file='\"$domainFile\" 'minlat='"$minLat" 'maxlat='"$maxLat" 'minlon='"$minLon" 'maxlon='"$maxLon" "$coordClosestIdxScript")"
+  coordIdx="$(singularity exec $NCL_SINGULARITY_IMAGE ncl -nQ 'coord_file='\"$domainFile\" 'minlat='"$minLat" 'maxlat='"$maxLat" 'minlon='"$minLon" 'maxlon='"$maxLon" "$coordClosestIdxScript")"
 fi
 
 # parse the output index for latitude and longitude