Enable EAMxx CMORization, E3SM Diags and add ts-level vertical regrid #827
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,190 @@ | ||
| # Example: EAMxx → CMIP and e3sm_diags, contributed by Shixuan Zhang. | ||
| # Reproduces the cfg from issue #820 plus e3sm_diags-related tasks. | ||
| # (https://github.com/E3SM-Project/zppy/issues/820) | ||
| # | ||
| # Demonstrates: | ||
| # - EAMxx CMORization end-to-end (issue #817) | ||
| # - The fix to the fragile component-detection gate (now uses prc_typ), | ||
| # so input_component="eamxx" with input_files="AVERAGE.nmonths_x1" works | ||
| # - EAMxx-specific ncremap flags (--ps_nm=${file}/ps, --vrt_in=vert_L128.nc) | ||
| # auto-emitted when prc_typ == 'eamxx' | ||
| # - climo, ts, e3sm_to_cmip, and e3sm_diags wiring for an EAMxx run | ||
| # | ||
| # Run with: zppy -c examples/post.v3.eamxx.cfg | ||
| [default] | ||
| input = /pscratch/sd/z/zhan391/e3smv4_project/ne256pg2_ne256pg2.F20TR-SCREAMv1.July-1.spanc800.2xauto.acc150.n0032.test2.1 | ||
| output = /pscratch/sd/c/chengzhu/tests/ne256pg2_ne256pg2.F20TR-SCREAMv1.July-1.spanc800.2xauto.acc150.n0032.test2.1 | ||
| case = ne256pg2_ne256pg2.F20TR-SCREAMv1.July-1.spanc800.2xauto.acc150.n0032.test2.1 | ||
| www = /global/cfs/cdirs/e3sm/www/chengzhu/tests/zppy_for_eamxx | ||
| partition = "debug" | ||
| account = "e3sm" | ||
| campaign = "water_cycle" | ||
| debug = False | ||
| #environment_commands = "source /global/common/software/e3sm/anaconda_envs/test_e3sm_unified_1.13.0rc10_pm-cpu.sh" | ||
|
|
||
| [climo] | ||
| active = True | ||
| walltime = "2:00:00" | ||
| years = "1995:2004:10", | ||
|
|
||
| [[ atm_monthly_180x360_aave ]] | ||
| # The following e3sm_diags sets require it: | ||
| # "lat_lon", "zonal_mean_xy", "zonal_mean_2d", "polar", "cosp_histogram", | ||
| # "meridional_mean_2d", "annual_cycle_zonal_mean", "zonal_mean_2d_stratosphere", | ||
| # "aerosol_aeronet", "aerosol_budget" | ||
| input_component = "eamxx" | ||
| case = "1ma_ne30pg2" | ||
| input_files = "AVERAGE.nmonths_x1" | ||
| frequency = "monthly" | ||
| input_subdir = "run/" | ||
| mapping_file = map_ne30pg2_to_cmip6_180x360_aave.20200201.nc | ||
|
|
||
| # [[ atm_monthly_diurnal_8xdaily_180x360_aave ]] | ||
| # # Skip for now, the ncclimo call underneath depends on improved eamxx metadata | ||
| # # The following e3sm_diags sets require it: | ||
| # # "diurnal_cycle" | ||
| # input_component = "eamxx" | ||
| # case = "3ha_ne30pg2" | ||
| # input_files = "AVERAGE.nhours_x3" | ||
| # input_subdir = "run/" | ||
| # frequency = "diurnal_8xdaily" | ||
| # mapping_file = map_ne30pg2_to_cmip6_180x360_aave.20200201.nc | ||
| # vars = "precip_liq_surf_mass_flux,precip_ice_surf_mass_flux" | ||
| # # Bump nodes for a potential performance issue in ncclimo for processing eamxx high freq data. | ||
| # nodes = 12 | ||
|
|
||
| [[ land_monthly_climo ]] | ||
| active = True | ||
| # This subtask is a dependency for the e3sm_diags task's lnd_monthly_mvm_lnd subtask. | ||
| # The following e3sm_diags sets require it: | ||
| # "lat_lon_land" | ||
| input_component = "elm" | ||
| frequency = "monthly" | ||
| input_files = "elm.h0" | ||
| input_subdir = "run/" | ||
| vars = "" # Setting this as "" will tell zppy to use ALL variables | ||
|
|
||
| [[ land_monthly_180x360_traave ]] | ||
| active = True | ||
| input_component = "elm" | ||
| frequency = "monthly" | ||
| input_files = "elm.h0" | ||
| input_subdir = "run/" | ||
| mapping_file = "map_ne256pg2_to_cmip6_180x360_traave.20250301.nc" | ||
| vars = "" | ||
|
|
||
| [ts] | ||
| active = True | ||
| walltime = "00:30:00" | ||
| years = "1995:2004:5" | ||
| ts_num_years=5 | ||
| qos = "debug" | ||
|
|
||
| [[atm_monthly_180x360_aave]] | ||
| # Merged 2D+3D atm timeseries: vert_remap_vars selectively vert-remaps the | ||
| # 3D vars into a sibling ts_vert_remap/ directory, so downstream e3sm_to_cmip | ||
| # sees a single clean ts subsection. | ||
| input_component = "eamxx" | ||
| input_subdir = "run/" | ||
| case = "1ma_ne30pg2" | ||
| input_files = "AVERAGE.nmonths_x1" | ||
| frequency = "monthly" | ||
| mapping_file = map_ne30pg2_to_cmip6_180x360_aave.20200201.nc | ||
| vars="ps,surf_radiative_T,SeaLevelPressure,IceWaterPath,qv_2m,precip_liq_surf_mass_flux,precip_ice_surf_mass_flux,omega_at_500hPa,omega_at_700hPa,omega_at_850hPa,T_mid_at_700hPa,T_2m,surface_upward_latent_heat_flux,surf_sens_flux,z_mid_at_700hPa,wind_speed_10m,surf_evap,U_at_10m_above_surface,V_at_10m_above_surface,LW_clrsky_flux_dn_at_model_bot,LW_clrsky_flux_up_at_model_top,LW_flux_dn_at_model_bot,LW_flux_up_at_model_bot,LW_flux_up_at_model_top,SW_clrsky_flux_dn_at_model_bot,SW_clrsky_flux_dn_at_model_top,SW_clrsky_flux_up_at_model_bot,SW_clrsky_flux_up_at_model_top,SW_flux_dn_at_model_bot,SW_flux_dn_at_model_top,SW_flux_up_at_model_bot,SW_flux_up_at_model_top,ShortwaveCloudForcing,LongwaveCloudForcing,isccp_cldtot,U,V,T_mid,z_mid,omega,RelativeHumidity,p_mid,qv" | ||
| # NOTE: ncclimo --prc_typ=eamxx does NOT auto-extract ps/hyai/hyam/hybi/hybm | ||
| # for 3D vars the way --prc_typ=cam/eam does, so we must list them explicitly | ||
| # in extra_vars. ps is load-bearing for the vert_remap step (ts.bash:138 | ||
| # passes --ps_nm=${file}/ps to ncremap). | ||
| # If ncclimo's eamxx mode is fixed upstream to mirror cam/eam behavior, drop | ||
| # ps + hybrid coeffs here and keep only area,landfrac,ocnfrac for analysis. | ||
| extra_vars= "ps,hyai,hyam,hybi,hybm,area,landfrac,ocnfrac" | ||
| vert_remap_vars = "U,V,T_mid,z_mid,omega,RelativeHumidity,p_mid,qv" | ||
|
|
||
| [[ atm_daily_180x360_aave ]] | ||
| active = True | ||
| # This subtask is a dependency for the e3sm_diags task's atm_monthly_180x360 subtask. | ||
| # The following e3sm_diags sets require it: | ||
| # "tropical_subseasonal", "precip_pdf" | ||
| input_component = "eamxx" | ||
| case = "1da_ne30pg2" | ||
| input_files = "AVERAGE.ndays_x1" | ||
| frequency = "daily" | ||
| input_subdir = "run/" | ||
| mapping_file = map_ne30pg2_to_cmip6_180x360_aave.20200201.nc | ||
| # Needed for Wheeler Kiladis | ||
| vars = "LW_flux_up_at_model_top,precip_liq_surf_mass_flux,precip_ice_surf_mass_flux,U_at_850hPa" | ||
| # For this simulation's "1da_ne30pg2.AVERAGE.ndays_x1" stream, each file | ||
| # holds one daily average (1 day, 1 timestep). Override the zppy defaults | ||
| # (dpf=30, tpd=1) which assume E3SM EAM monthly h0 files; otherwise ncclimo | ||
| # treats each daily file as 30 days and silently produces ts files whose | ||
| # contents (~2 months) don't match their filenames. | ||
| dpf = 1 | ||
| tpd = 1 | ||
|
|
||
| [[ atm_monthly_glb ]] | ||
| active = True | ||
| # This subtask is a dependency for the global_time_series task. | ||
| input_component = "eam" | ||
| input_subdir = "run/" | ||
| case = "1ma_ne30pg2" | ||
| input_files = "AVERAGE.nmonths_x1" | ||
| frequency = "monthly" | ||
| mapping_file = "glb" | ||
| vars="ps,surf_radiative_T,SeaLevelPressure,IceWaterPath,qv_2m,precip_liq_surf_mass_flux,precip_ice_surf_mass_flux" | ||
|
|
||
|
|
||
| [[ rof_monthly ]] | ||
| active = True | ||
| # The following e3sm_diags sets require it: | ||
| # "streamflow" | ||
| input_component = "mosart" | ||
| frequency = "monthly" | ||
| input_files = "mosart.h0" | ||
| input_subdir = "run/" | ||
| mapping_file = "" | ||
| vars = "RIVER_DISCHARGE_OVER_LAND_LIQ" | ||
| extra_vars = 'areatotal2' | ||
|
|
||
| [e3sm_to_cmip] | ||
| active = True | ||
| frequency = "monthly" | ||
| ts_grid = "180x360_aave" | ||
| ts_num_years=5 | ||
| walltime = "00:10:00" | ||
| years = "1995:2004:5" | ||
| qos = "debug" | ||
| #environment_commands = "source /global/common/software/e3sm/anaconda_envs/load_latest_e3sm_unified_pm-cpu.sh; conda activate zi-pcmdi-diags" | ||
|
|
||
| [[atm_monthly_180x360_aave]] | ||
| # Merged subsection matching the [ts] atm_monthly_180x360_aave output. | ||
| # Without cmip_vars, e3sm_to_cmip uses its built-in default list (~41 vars). | ||
| # Uncomment to override the default ~41-var list. | ||
| #cmip_vars = "pr, cltisccp, evspsbl, hfls, hfss, huss, ps, psl, rlds, rldscs, rlus, rlut, rlutcs, rsds, rsdscs, rsdt, rsus, rsuscs, rtmt, uas, vas, sfcWind, tas, ts, ta, ua, va, zg" | ||
| input_component = "eamxx" | ||
| case = "1ma_ne30pg2" | ||
| input_files = "AVERAGE.nmonths_x1" | ||
|
|
||
|
|
||
| [e3sm_diags] | ||
| active = True | ||
| multiprocessing = True | ||
| num_workers = 8 | ||
| ref_start_yr = 1995 | ||
| ref_final_yr = 2004 | ||
| ts_num_years = 5 | ||
| walltime = "4:00:00" | ||
| years = "1995:2004:10", | ||
| case = "1ma_ne30pg2" | ||
| #environment_commands = "source /global/common/software/e3sm/anaconda_envs/load_latest_e3sm_unified_pm-cpu.sh" | ||
|
|
||
| [[ atm_monthly_180x360_aave ]] | ||
| # `e3sm_diags` is largely driven by which e3sm_diags sets are requested: | ||
| sets="lat_lon","zonal_mean_xy","zonal_mean_2d","polar","cosp_histogram","meridional_mean_2d","annual_cycle_zonal_mean","enso_diags","qbo","zonal_mean_2d_stratosphere","aerosol_aeronet","mp_partition","tropical_subseasonal","precip_pdf","streamflow", | ||
| # sets = #"tc_analysis,"diurnal_cycle"," # not yet supported for eamxx! | ||
| #climo_diurnal_frequency = "diurnal_8xdaily" | ||
| #climo_diurnal_subsection = "atm_monthly_diurnal_8xdaily_180x360_aave" | ||
| ts_daily_subsection = "atm_daily_180x360_aave" | ||
| # ts_subsection defaults to "atm_monthly_180x360_aave" — matches the merged | ||
| # [ts] subsection above, so no explicit override needed. | ||
| grid = '180x360_aave' | ||
| short_name = 'e3sm.amip.EAMXX.test2_1' |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -46,6 +46,18 @@ def e3sm_to_cmip(config: ConfigObj, script_dir: str, existing_bundles, job_ids_f | |
| default_cmip_plevdata, | ||
| ParameterInferenceType.PATH_INFERENCE, | ||
| ) | ||
| # EAMxx needs an explicit source vertical grid file (L128); | ||
| # EAM/CAM have vertical coord info embedded in the file already. | ||
| if c["prc_typ"] == "eamxx": | ||
| default_vrt_in_file = ( | ||
| f"{c['diagnostics_base_path']}/e3sm_to_cmip_data/grids/vert_L128.nc" | ||
|
Collaborator
There was a problem hiding this comment. I see the code already had a reference to Claude says the following, emphasis my own:
Collaborator
Author
There was a problem hiding this comment.
@forsyth2 Prefixing with diagnostics_base_path should already imply the data are pre-installed. I think the current approach is fine, but feel free to update if you think it improves clarity.
Collaborator
There was a problem hiding this comment.
Yes I suppose looking at it again, that makes sense. It was just a little confusing when I was trying to figure out which tasks had |
||
| ) | ||
| set_value_of_parameter_if_undefined( | ||
| c, | ||
| "vrt_in_file", | ||
| default_vrt_in_file, | ||
| ParameterInferenceType.PATH_INFERENCE, | ||
| ) | ||
| year_sets: List[Tuple[int, int]] = get_years(c["years"]) | ||
| # Loop over year sets | ||
| for s in year_sets: | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Collaborator
There was a problem hiding this comment. @chengzhuzhang For lines 36–41, if this logic is only expected to apply to atmospheric model output, including CAM, EAM, and EAMxx, then it seems better to move these lines inside the {% if prc_typ in ('cam', 'eam', 'eamxx') -%} block at line 47. However, if we want this to also work for vertical interpolation of ocean-model output, such as MPAS-O and MPAS-SI, then the current placement looks reasonable to me.
Collaborator
Author
There was a problem hiding this comment. Noted! We can make this update when updating to include MPAS processing. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's a little inconsistent to use
vrtfor 2 of the parameters andvertfor another. But I don't know if it's worth changing (and risking breaking something else) at this point.There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good catch! Let me try to rename vert_remap_vars → vrt_remap_vars — aligns everything with NCO's vrt_ prefix to be consistent. Since these are newly added parameters, it would be good to fix before releasing to the users.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@zhangshixuan1987 just a quick note on this: you may need to rename vert_remap_vars to vrt_remap_vars. This change was made to reduce variation in parameter names.