-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathACDD_conf.yaml
executable file
·196 lines (195 loc) · 9.7 KB
/
ACDD_conf.yaml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
################################################################
# USER OPTIONS
# Settings to manage cmorisation and set tables/variables to process
cmor:
# If test true it will just run the setup but not launch the job automatically
test: false
# working directory if default uses current directory
appdir: default
# output directory for all generated data (CMORISED files & logs)
# if default it is set to /scratch/$project/$user/MOPPER_OUTPUT<exp>
outpath: default
# if true override files already exsiting in outpath
override: !!bool true
# location of input data must point to dir above experiment;
# and experiment subdir must contain atmos/[,ocean/, ice/]
datadir: /g/data/...
# from exp_to_process: local name of experiment
exp: expname
# Interval to cmorise inclusive of end_date
# NB this will be used to select input files to include.
# Use also hhmm if you want more control on subdaily data
# start_date = "20220222T0000"
# sometimes this can be defined at end of timestep so to get all data for your last day
# you should use 0000 time of next day
start_date: "19800101"
end_date: "20201231"
# select one of: [CM2, ESM1.5, OM2[-025], AUS2200]
# if adding a new version other defaults might need to be set
# see documentation
access_version: CM2
# reference date for time units (set as 'default' to use start_date)
reference_date: 1970-01-01
# Path and file templates can be changed based on the experiment.
# The example below should be considered a minimum requirement.
# Consider adding 'table_id" if using the "all tables" option to list
# the variables to process as variables can be present at same frequency
# in more than one tables
path_template: "{product_version}/{frequency}"
# date_range is automatically added at the end of filename
file_template: "{variable_id}_{source_id}_{experiment_id}_{frequency}"
# maximum file size in MB: this is meant as uncompressed, compression might reduce it by 50%
max_size: 8192
# deflate_level sets the internal compression level,
# level 4-6 good compromise between reducing size and write/read speed
# shuffle 0: off 1:on Shuffle reduces size without impacting speed
deflate_level: 4
shuffle: 1
# Variables to CMORise:
# CMOR table/variable to process; default is 'all'.
# 'all' will use all the tables listed in the mapping file
# Or create a yaml file listing variables to process (VAR_SUBSET[_LIST]).
# each line: <table: [var1, var2, var3 ..]>
tables: CMIP6_Amon
variable_to_process: tas
var_subset: !!bool False
var_subset_list: ''
# if subhr data is included specify actual frequency as ##min
subhr: 10min
# model vertical levels number
levnum: 85
# Mappings, vocab and tables settings
# default=data/dreq/cmvme_all_piControl_3_3.csv
# Leave as set unless publishing for CMIP6
dreq: default
force_dreq: !!bool False
dreq_years: !!bool False
# mapping file created with cli_db.py based on the actual model output
master_map: "localdata/map_expname.csv"
# CMOR tables path, these define what variables can be extracted
# see documentation to add new tables/variables
# use this to indicate the path used for new or modified tables
# these will be used in preference to the package tables
tables_path: ""
# Ancil files are needed only for specific variables when
# grid information is not fully available from output
# you can usually leave these empty if processing only atmos
# ancillary files relative path to <appdir> or fullpath
ancils_path: "localdata/ancils"
# grid ocean is the auscom grid file t retrieve lat/lon and their vertices
# example is for om2, cm2, esm1.5 versions
grid_ocean: "grid_spec.auscom.20110618.nc"
grid_seaIce: ""
mask_ocean: ""
# to supply land area fraction if not available in output
land_frac: ""
# to supply tile area fraction if not available in output
tile_frac: ""
# used for atmospheric hybrid coordinates
orog: ""
# defines Controlled Vocabularies and required attributes
# leave ACDD to follow NCI publishing requirements
_control_vocabulary_file: "ACDD_CV.json"
# leave this empty unless is CMIP6
_cmip6_option:
_AXIS_ENTRY_FILE: "ACDD_coordinate.json"
_FORMULA_VAR_FILE: "ACDD_formula_terms.json"
grids: "ACDD_grids.json"
# Additional NCI information:
# NCI project to charge compute; $PROJECT = your default project
project: v45
# additional NCI projects to be included in the storage flags, comma separated list
addprojs: []
# queue and memory (GB) per CPU (depends on queue),
# hugemem is recommended for high reoslution data and/or derived variables
# hugemem requires a minimum of 6 cpus this is handled by the code
queue: hugemem
mem_per_cpu: 32
max_cpus: 24
# Mopper uses multiprocessing to produce files in parallel, usually 1 cpu per worker
# is a good compromise, occasionally you might want to pass a higher number
# if running out of memory
cpuxworker: 1
# walltime in "hh:mm:ss"
walltime: '8:00:00'
mode: custom
# conda_env to use by default hh5 analysis3-unstable
# as this has the code and all dependecies installed
# you can override that by supplying the env to pass to "source"
# Ex
# conda_env: <custom-env-path>/bin/activate
# to allow other settings use "test: true" and modify mopper_job.sh manually
conda_env: default
#
# Global attributes: these will be added to each files comment unwanted ones
# Using ACDD CV vocab to check validity of global attributes
# see data/custom-cmor-tables/ACDD_CV.json
# For CMIP6 global attributes explanation:
# https://docs.google.com/document/d/1h0r8RZr_f3-8egBMMh7aqLwy3snpD6_MrDz1q8n5XUk/edit
attrs:
Conventions: "CF-1.7, ACDD-1.3"
title: "ACCESS CM2 historical simulation ...."
experiment_id: exp-id
# Use to provide a short description of the experiment.
# It will be written to file as "summary"
exp_description: "A global simulation of ...."
product_version: v1.0
date_created: "2023-05-12"
# NB source and source_id need to be defined in ACDD_CV.json
# if using new different model configuration
# currently available: AUS2200, ACCESS-ESM1-5, ACCESS-CM2,
# ACCESS-OM2, ACCESS-OM2-025
source_id: 'ACCESS-CM2'
# AUS2200 description
source: "ACCESS - CM2 ..."
# ACCESS-CM2 description
#source: "ACCESS-CM2 (2019): aerosol: UKCA-GLOMAP-mode, atmos: MetUM-HadGEM3-GA7.1 (N96; 192 x 144 longitude/latitude; 85 levels; top level 85 km), atmosChem: none, land: CABLE2.5, landIce: none, ocean: ACCESS-OM2 (GFDL-MOM5, tripolar primarily 1deg; 360 x 300 longitude/latitude; 50 levels; top grid cell 0-10 m), ocnBgchem: none, seaIce: CICE5.1.2 (same grid as ocean)"
# ACCESS-ESM1.5 description
#source: "ACCESS-ESM1.5 (2019): aerosol: CLASSIC (v1.0), atmos: HadGAM2 (r1.1, N96; 192 x 145 longitude/latitude; 38 levels; top level 39255 m), atmosChem: none, land: CABLE2.4, landIce: none, ocean: ACCESS-OM2 (MOM5, tripolar primarily 1deg; 360 x 300 longitude/latitude; 50 levels; top grid cell 0-10 m), ocnBgchem: WOMBAT (same grid as ocean), seaIce: CICE4.1 (same grid as ocean)"
license: "https://creativecommons.org/licenses/by/4.0/"
institution: University of ...
# not required
organisation: Centre of Excellence for Climate Extremes
# see here: https://acdguide.github.io/Governance/tech/keywords.html
# use of FOR codes is reccomended
keywords: "Climate change processes, Adverse weather events, Cloud physics"
references: ""
# contact email of person running post-processing or author
contact: <contact-email>
creator_name: <main-author-name>
creator_email: <main-author-email>
creator_url: <main-author-researcher-id>
# not required details of any contributor including who run post processing
# if different from creator. If more than one spearate with commas
# see here for datacite contributor role definitions:
# https://datacite-metadata-schema.readthedocs.io/en/4.5_draft/properties/recommended_optional/property_contributor.html#a-contributortype
contributor_name: <contributor1>, <contributor2>
contributor_role: data_curator, data_curator
contributor_email: <contributor1-email>, <contributor2-email>
contributor_url: <contributor1-researcher-id>, <contributor2-researcher-id>
# Not required use if publishing, otherwise comment out
#publisher_name:
#publisher_email:
# The following refer to the entire dataset rather than the specific file
time_coverage_start: 1980-01-01
time_coverage_end: 2020-12-31
geospatial_lat_min: -90.0
geospatial_lat_max: 90.0
geospatial_lon_min: -180.0
geospatial_lon_max: 180.0
# The following attributes will be added automatically:
# experiment, frequency, realm, variable
# Add below whatever other global attributes you want to add
forcing: "GHG, Oz, SA, Sl, Vl, BC, OC, (GHG = CO2, N2O, CH4, CFC11, CFC12, CFC113, HCFC22, HFC125, HFC134a)"
calendar: "proleptic_gregorian"
grid: "native atmosphere N96 grid (192 x 144 latxlon)"
# nearest value from cmip6 is 2.5 km
nominal_resolution: "250 km"
#
# Parent experiment details if any
# if parent=false, all parent fields are automatically set to "no parent".
# If true, defined values are used.
parent: !!bool false
# CMOR will add a tracking_id if you want to define a prefix add here
tracking_id_prefix:
comment: "post-processed using ACCESS-MOPPeR v1.2.0 https://doi.org/10.5281/zenodo.14322348"