config_cam_baseline_example.yaml

#==============================
#config_cam_baseline_example.yaml

#This is the main CAM diagnostics config file
#for doing comparisons of a CAM run against
#another CAM run, or a CAM baseline simulation.

#Currently, if one is on NCAR's Casper or
#Cheyenne machine, then only the diagnostic output
#paths are needed, at least to perform a quick test
#run (these are indicated with "MUST EDIT" comments).
#Running these diagnostics on a different machine,
#or with a different, non-example simulation, will
#require additional modifications.
#
#Config file Keywords:
#--------------------
#
#1.  Using ${xxx} will substitute that text with the
#    variable referenced by xxx. For example:
#
#    cam_case_name: cool_run
#    cam_climo_loc: /some/where/${cam_case_name}
#
#    will set "cam_climo_loc" in the diagnostics package to:
#    /some/where/cool_run
#
#    Please note that currently this will only work if the
#    variable only exists in one location in the file.
#
#2.  Using ${<top_level_section>.xxx} will do the same as
#    keyword 1 above, but specifies which sub-section the
#    variable is coming from, which is necessary for variables
#    that are repeated in different subsections.  For example:
#
#    diag_basic_info:
#      cam_climo_loc:  /some/where/${diag_cam_climo.start_year}
#
#    diag_cam_climo:
#      start_year: 1850
#
#    will set "cam_climo_loc" in the diagnostics package to:
#    /some/where/1850
#
#Finally, please note that for both 1 and 2 the keywords must be lowercase.
#This is because future developments will hopefully use other keywords
#that are uppercase. Also please avoid using periods (".") in variable
#names, as this will likely cause issues with the current file parsing
#system.
#--------------------
#
##==============================
#
# This file doesn't (yet) read environment variables, so the user must
# set this themselves. It is also a good idea to search the doc for 'user'
# to see what default paths are being set for output/working files.
#
# Note that the string 'USER-NAME-NOT-SET' is used in the jupyter script
# to check for a failure to customize
#
user: 'USER-NAME-NOT-SET'


#This first set of variables specify basic info used by all diagnostic runs:
diag_basic_info:

    #Is this a model vs observations comparison?
    #If "false" or missing, then a model-model comparison is assumed:
    compare_obs: false

    #Generate HTML website (assumed false if missing):
    #Note:  The website files themselves will be located in the path
    #specified by "cam_diag_plot_loc", under the "<diag_run>/website" subdirectory,
    #where "<diag_run>" is the subdirectory created for this particular diagnostics run
    #(usually "case_vs_obs_XXX" or "case_vs_baseline_XXX").
    create_html: true

    #Location of observational datasets:
    #Note: this only matters if "compare_obs" is true and the path
    #isn't specified in the variable defaults file.
    obs_data_loc: /glade/campaign/cgd/amp/amwg/ADF_obs

    #Location where re-gridded and interpolated CAM climatology files are stored:
    cam_regrid_loc: /glade/derecho/scratch/${user}/ADF/regrid

    #Overwrite CAM re-gridded files?
    #If false, or missing, then regridding will be skipped for regridded variables
    #that already exist in "cam_regrid_loc":
    cam_overwrite_regrid: false

    #Location where diagnostic plots are stored:
    cam_diag_plot_loc: /glade/derecho/scratch/${user}/ADF/plots

    #Location of ADF variable plotting defaults YAML file:
    #If left blank or missing, ADF/lib/adf_variable_defaults.yaml will be used
    #Uncomment and change path for custom variable defaults file
    #defaults_file: /some/path/to/defaults/file.yaml

    #Vertical pressure levels (in hPa) on which to plot 3-D variables
    #when using horizontal (e.g. lat/lon) map projections.
    #If this config option is missing, then no 3-D variables will be plotted on
    #horizontal maps.  Please note too that pressure levels must currently match
    #what is available in the observations file in order to be plotted in a
    #model vs obs run:
    plot_press_levels: [200,850]

    #Longitude line on which to center all lat/lon maps.
    #If this config option is missing then the central
    #longitude will default to 180 degrees E.
    central_longitude: 180

    #Number of processors on which to run the ADF.
    #If this config variable isn't present then
    #the ADF defaults to one processor.  Also, if
    #you set it to "*" then it will default
    #to all of the processors available on a
    #single node/machine:
    num_procs: 8

    #If set to true, then redo all plots even if they already exist.
    #If set to false, then if a plot is found it will be skipped:
    redo_plot: false

#This second set of variables provides info for the CAM simulation(s) being diagnosed:
diag_cam_climo:

    # History file list of strings to match
    # eg. cam.h0 or ocn.pop.h.ecosys.nday1 or hist_str: [cam.h2,cam.h0]  
    # Only affects timeseries as everything else uses the created timeseries 
    # Default: 
    hist_str: cam.h0a

    #Calculate climatologies?
    #If false, the climatology files will not be created:
    calc_cam_climo: true

    #Overwrite CAM climatology files?
    #If false, or not prsent, then already existing climatology files will be skipped:
    cam_overwrite_climo: false

    #Name of CAM case (or CAM run name):
    cam_case_name: b.e23_alpha17f.BLT1850.ne30_t232.098

    #Case nickname
    #NOTE: if nickname starts with '0' - nickname must be in quotes!
    # ie '026a' as opposed to 026a
    #If missing or left blank, will default to cam_case_name
    case_nickname: #cool nickname

    #Location of CAM history (h0) files:
    #Example test files
    cam_hist_loc: /glade/campaign/cgd/amp/amwg/ADF_test_cases/${diag_cam_climo.cam_case_name}

    #Location of CAM climatologies (to be created and then used by this script)
    cam_climo_loc: /glade/derecho/scratch/${user}/ADF/${diag_cam_climo.cam_case_name}/climo

    #model year when time series files should start:
    #Note:  Leaving this entry blank will make time series
    #       start at earliest available year.
    start_year: 10

    #model year when time series files should end:
    #Note:  Leaving this entry blank will make time series
    #       end at latest available year.
    end_year: 14

    #Do time series files exist?
    #If True, then diagnostics assumes that model files are already time series.
    #If False, or if simply not present, then diagnostics will attempt to create
    #time series files from history (time-slice) files:
    cam_ts_done: false

    #Save interim time series files?
    #WARNING:  This can take up a significant amount of space,
       #          but will save processing time the next time
    cam_ts_save: true

    #Overwrite time series files, if found?
    #If set to false, then time series creation will be skipped if files are found:
    cam_overwrite_ts: false

    #Location where time series files are (or will be) stored:
    cam_ts_loc: /glade/derecho/scratch/${user}/ADF/${diag_cam_climo.cam_case_name}/ts

    #TEM diagnostics
    #---------------
    #TEM history file number
    #If missing or blank, ADF will default to h4
    tem_hist_str: cam.h4

    #Location where TEM files are stored:
    #NOTE: If path not specified or commented out, TEM calculation/plots will be skipped!
    cam_tem_loc: /glade/derecho/scratch/${user}/${diag_cam_climo.cam_case_name}/tem/

    #Overwrite TEM files, if found?
    #If set to false, then TEM creation will be skipped if files are found:
    overwrite_tem: false

    #----------------------

    #You can alternatively provide a list of cases, which will make the ADF
    #apply the same diagnostics to each case separately in a single ADF session.
    #All of the config variables below show how it is done, and are the only ones
    #that need to be lists.  This also automatically enables the generation of
    #a "main_website" in "cam_diag_plot_loc" that brings all of the different cases
    #together under a single website.

    #Also please note that config keywords cannot currently be used in list mode.

    #cam_case_name:
    #    - b.e23_alpha17f.BLT1850.ne30_t232.098
    #    - b.e23_alpha17f.BLT1850.ne30_t232.095

    #Case nickname
    #NOTE: if nickname starts with '0' - nickname must be in quotes!
    # ie '026a' as opposed to 026a
    #If missing or left blank, will default to cam_case_name
    #case_nickname:
    #    - cool nickname
    #    - cool nickname 2

    #calc_cam_climo:
    #    - true
    #    - true

    #cam_overwrite_climo:
    #    - false
    #    - false

    #cam_hist_loc:
    #    - /glade/campaign/cgd/amp/amwg/ADF_test_cases/b.e23_alpha17f.BLT1850.ne30_t232.098
    #    - /glade/campaign/cgd/amp/amwg/ADF_test_cases/b.e23_alpha17f.BLT1850.ne30_t232.095

    #cam_climo_loc:
    #    - /some/where/you/want/to/have/climo_files/ #MUST EDIT!
    #    - /the/same/or/some/other/climo/files/location

    #start_year:
    #    - 10
    #    - 10

    #end_year:
    #    - 14
    #    - 14

    #cam_ts_done:
    #    - false
    #    - false

    #cam_ts_save:
    #    - true
    #    - true

    #cam_overwrite_ts:
    #    - false
    #    - false

    #cam_ts_loc:
    #    - /some/where/you/want/to/have/time_series_files
    #    - /same/or/different/place/you/want/files

    #TEM diagnostics
    #---------------
    #TEM history file number
    #If missing or blank, ADF will default to h4
    #tem_hist_str:
    #    - cam.h4
    #    - cam.h#

    #Location where TEM files are stored:
    #NOTE: If path not specified or commented out, TEM calculation/plots will be skipped!
    #cam_tem_loc:
    #    - /some/where/you/want/to/have/TEM_files/
    #    - /same/or/different/place/you/want/TEM_files/

    #Overwrite TEM files, if found?
    #If set to false, then TEM creation will be skipped if files are found:
    #overwrite_tem:
    #    - false
    #    - true

    #----------------------


#This third set of variables provide info for the CAM baseline climatologies.
#This only matters if "compare_obs" is false:
diag_cam_baseline_climo:

    # History file list of strings to match
    # eg. cam.h0 or ocn.pop.h.ecosys.nday1 or hist_str: [cam.h2,cam.h0]  
    # Only affects timeseries as everything else uses the created timeseries 
    # Default: 
    hist_str: cam.h0a

    #Calculate cam baseline climatologies?
    #If false, the climatology files will not be created:
    calc_cam_climo: true

    #Overwrite CAM climatology files?
    #If false, or not present, then already existing climatology files will be skipped:
    cam_overwrite_climo: false

    #Name of CAM baseline case:
    cam_case_name: b.e23_alpha17f.BLT1850.ne30_t232.093

    #Baseline case nickname
    #NOTE: if nickname starts with '0' - nickname must be in quotes!
    # ie '026a' as opposed to 026a
    #If missing or left blank, will default to cam_case_name
    case_nickname: #cool nickname

    #Location of CAM baseline history (h0) files:
    #Example test files
    cam_hist_loc: /glade/campaign/cgd/amp/amwg/ADF_test_cases/${diag_cam_baseline_climo.cam_case_name}

    #Location of baseline CAM climatologies:
    cam_climo_loc: /glade/derecho/scratch/${user}/ADF/${diag_cam_baseline_climo.cam_case_name}/climo

    #model year when time series files should start:
    #Note:  Leaving this entry blank will make time series
    #       start at earliest available year.
    start_year: 10

    #model year when time series files should end:
    #Note:  Leaving this entry blank will make time series
    #       end at latest available year.
    end_year: 14

    #Do time series files need to be generated?
    #If True, then diagnostics assumes that model files are already time series.
    #If False, or if simply not present, then diagnostics will attempt to create
    #time series files from history (time-slice) files:
    cam_ts_done: false

    #Save interim time series files for baseline run?
    #WARNING:  This can take up a significant amount of space:
    cam_ts_save: true

    #Overwrite baseline time series files, if found?
    #If set to false, then time series creation will be skipped if files are found:
    cam_overwrite_ts: false

    #Location where time series files are (or will be) stored:
    cam_ts_loc: /glade/derecho/scratch/${user}/ADF/${diag_cam_baseline_climo.cam_case_name}/ts

    #TEM diagnostics
    #---------------
    #TEM history file number
    #If missing or blank, ADF will default to h4
    tem_hist_str: cam.h4

    #Location where TEM files are stored:
    #NOTE: If path not specified or commented out, TEM calculation/plots will be skipped!
    cam_tem_loc: /glade/derecho/scratch/${user}/${diag_cam_baseline_climo.cam_case_name}/tem/

    #Overwrite TEM files, if found?
    #If set to false, then TEM creation will be skipped if files are found:
    overwrite_tem: false


#This fourth set of variables provides settings for calling the Climate Variability
# Diagnostics Package (CVDP). If cvdp_run is set to true the CVDP will be set up and
# run in background mode, likely completing after the ADF has completed.
# If CVDP is to be run PSL, TREFHT, TS and PRECT (or PRECC and PRECL) should be listed
# in the diag_var_list variable listing.
# For more CVDP information: https://www.cesm.ucar.edu/working_groups/CVC/cvdp/
diag_cvdp_info:

    # Run the CVDP on the listed run(s)?
    cvdp_run: false

    # CVDP code path, sets the location of the CVDP codebase
    #  CGD systems path = /home/asphilli/CESM-diagnostics/CVDP/Release/v5.2.0/
    #  CISL systems path = /glade/u/home/asphilli/CESM-diagnostics/CVDP/Release/v5.2.0/
    #  github location = https://github.com/NCAR/CVDP-ncl
    cvdp_codebase_loc: /glade/u/home/asphilli/CESM-diagnostics/CVDP/Release/v5.2.0/

    # Location where cvdp codebase will be copied to and diagnostic plots will be stored
    cvdp_loc: /glade/derecho/scratch/${user}/ADF/cvdp/

    # tar up CVDP results?
    cvdp_tar: false

# This set of variables provides settings for calling NOAA's
# Model Diagnostic Task Force (MDTF) diagnostic package.
# https://github.com/NOAA-GFDL/MDTF-diagnostics
#
# If mdtf_run: true, the MDTF will be set up and 
# run in background mode, likely completing after the ADF has completed.
#
# WARNING: This currently only runs on CASPER (not derecho)
#
# The variables required depend on the diagnostics (PODs) selected. 
# AMWG-developed PODS and their required variables:
#   (Note that PRECT can be computed from PRECC & PRECL)
#  - MJO_suite: daily PRECT, FLUT, U850, U200, V200  (all required)
#  - Wheeler-Kiladis Wavenumber Frequency Spectra: daily PRECT, FLUT, U200, U850, OMEGA500
#              (will use what is available)
#  - Blocking (Rich Neale):  daily OMEGA500
#  - Precip Diurnal Cycle (Rich Neale): 3-hrly PRECT
#
# Many other diagnostics are available; see 
# https://mdtf-diagnostics.readthedocs.io/en/main/sphinx/start_overview.html

#
diag_mdtf_info:
    # Run the MDTF on the model cases
    mdtf_run: false

    # The file that will be written by ADF to input to MDTF. Call this whatever you want.
    mdtf_input_settings_filename : mdtf_input.json   

    ## MDTF code path, sets the location of the MDTF codebase and pre-compiled conda envs
    #  CHANGE if you have any: your own MDTF code, installed conda envs and/or obs_data

    mdtf_codebase_path : /glade/campaign/cgd/amp/amwg/mdtf                                                                                                                                 
    mdtf_codebase_loc  : ${mdtf_codebase_path}/MDTF-diagnostics.v3.1.20230817.ADF
    conda_root         : /glade/u/apps/opt/conda
    conda_env_root     : ${mdtf_codebase_path}/miniconda2/envs.MDTFv3.1.20230412/
    OBS_DATA_ROOT      : ${mdtf_codebase_path}/obs_data

    # SET this to a writable dir. The ADF will place ts files here for the MDTF to read (adds the casename)
    MODEL_DATA_ROOT     : ${diag_cam_climo.cam_ts_loc}/mdtf/inputdata/model     

    # Choose diagnostics (PODs). Full list of available PODs: https://github.com/NOAA-GFDL/MDTF-diagnostics
    pod_list      :  [ "MJO_suite" ]

    # Intermediate/output file settings
    make_variab_tar: false     # tar up MDTF results
    save_ps : false     # save postscript figures in addition to bitmaps
    save_nc : false      # save netCDF files of processed data (recommend true when starting with new model data)
    overwrite: true     # overwrite results in OUTPUT_DIR; otherwise results will be saved under a unique name

    # Settings used in debugging:
    verbose  : 3       # Log verbosity level.
    test_mode: false   # Set to true for framework test. Data is fetched but PODs are not run.
    dry_run  : false   # Framework test. No external commands are run and no remote data is copied. Implies test_mode.

    # Settings that shouldn't change in ADF implementation for now
    data_type           : single_run # single_run or multi_run (only works with single right now)
    data_manager        : Local_File # Fetch data or it is local?
    environment_manager : Conda      # Manage dependencies



#+++++++++++++++++++++++++++++++++++++++++++++++++++
#These variables below only matter if you are using
#a non-standard method, or are adding your own
#diagnostic scripts.
#+++++++++++++++++++++++++++++++++++++++++++++++++++

#Note:  If you want to pass arguments to a particular script, you can
#do it like so (using the "averaging_example" script in this case):
# - {create_climo_files: {kwargs: {clobber: true}}}

#Name of time-averaging scripts being used to generate climatologies.
#These scripts must be located in "scripts/averaging":
time_averaging_scripts:
    - create_climo_files
    #- create_TEM_files #To generate TEM files, please un-comment

#Name of regridding scripts being used.
#These scripts must be located in "scripts/regridding":
regridding_scripts:
    - regrid_and_vert_interp

#List of analysis scripts being used.
#These scripts must be located in "scripts/analysis":
analysis_scripts:
    - amwg_table
    #- aerosol_gas_tables

#List of plotting scripts being used.
#These scripts must be located in "scripts/plotting":
plotting_scripts:
    - global_latlon_map
    - global_latlon_vect_map
    - zonal_mean
    - meridional_mean
    - polar_map
    - cam_taylor_diagram
    - qbo
    - ozone_diagnostics
    #- tape_recorder
    #- tem
    #- regional_map_multicase #To use this please un-comment and fill-out
                              #the "region_multicase" section below

#List of CAM variables that will be processesd:
#If CVDP is to be run PSL, TREFHT, TS and PRECT (or PRECC and PRECL) should be listed
diag_var_list:
    - SWCF
    - LWCF
    - PRECC
    - PRECL
    - PSL
    - Q
    - U
    - T
    - RELHUM
    - TREFHT
    - TS
    - TAUX
    - TAUY
    - FSNT
    - FLNT
    - LANDFRAC
    - O3

#<Add more variables here.>
# MDTF recommended variables
#    - FLUT
#    - OMEGA500
#    - PRECT
#    - PS
#    - PSL
#    - U200
#    - U850
#    - V200
#    - V850
    
# Options for multi-case regional contour plots (./plotting/regional_map_multicase.py)
# region_multicase:
#     region_spec: [slat, nlat, wlon, elon]
#     region_time_option: <calendar | zeroanchor>  # If calendar, will look for specified years. If zeroanchor will use a nyears starting from year_offset from the beginning of timeseries
#     region_start_year:
#     region_end_year:
#     region_nyear:
#     region_year_offset:
#     region_month: <NULL means look for season>
#     region_season: <NULL means use annual mean>
#     region_variables: <list of variables to try to use; allows for a subset of the total diag variables>

#END OF FILE