Last updated: 2021-11-26

Checks: 7 0

Knit directory: bgc_argo_r_argodata/

This reproducible R Markdown analysis was created with workflowr (version 1.6.2). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.

R Markdown file: up-to-date

Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.

Environment: empty

Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.

Seed: set.seed(20211008)

The command set.seed(20211008) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.

Session information: recorded

Great job! Recording the operating system, R version, and package versions is critical for reproducibility.

Cache: none

Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.

File paths: relative

Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

Repository version: 9b5df99

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version 9b5df99. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated: 


Ignored files:
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/
    Ignored:    output/

Untracked files:
    Untracked:  code/creating_dataframe.R
    Untracked:  code/creating_map.R
    Untracked:  code/merging_oceanSODA_Argo.R
    Untracked:  code/pH_data_timeseries.R

Unstaged changes:
    Modified:   analysis/_site.yml
    Modified:   code/Workflowr_project_managment.R

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.

These are the previous versions of the repository in which changes were made to the R Markdown (analysis/loading_data.Rmd) and HTML (docs/loading_data.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.

File Version Author Date Message
Rmd 9b5df99 pasqualina-vonlanthendinenna 2021-11-26 added oceanSODA page
html 3cc9e64 pasqualina-vonlanthendinenna 2021-11-23 Build site.
Rmd 308d007 pasqualina-vonlanthendinenna 2021-11-23 switched reccap biomes to loading data
Rmd f43074c pasqualina-vonlanthendinenna 2021-11-23 switched reccap biomes to loading data
html 105630e pasqualina-vonlanthendinenna 2021-11-22 Build site.
Rmd 82f09d0 pasqualina-vonlanthendinenna 2021-11-22 separated Southern Ocean regions
html 77a890b pasqualina-vonlanthendinenna 2021-11-20 Build site.
Rmd 8c2cee7 pasqualina-vonlanthendinenna 2021-11-20 corrected offset plot
Rmd fb2fb74 pasqualina-vonlanthendinenna 2021-11-19 corrected offset plot
html 578ae8c pasqualina-vonlanthendinenna 2021-11-19 Build site.
Rmd ae64132 pasqualina-vonlanthendinenna 2021-11-19 added offset pH plot
html ab70649 pasqualina-vonlanthendinenna 2021-11-19 Build site.
Rmd 171aa37 pasqualina-vonlanthendinenna 2021-11-19 updated loading pH data and color palettes
html 75399eb pasqualina-vonlanthendinenna 2021-11-18 Build site.
Rmd 131582d pasqualina-vonlanthendinenna 2021-11-18 updated loading pH data and color palettes
html c9a5284 pasqualina-vonlanthendinenna 2021-11-18 Build site.
Rmd 0a03c5a pasqualina-vonlanthendinenna 2021-11-18 updated loading pH data and color palettes
Rmd c696726 pasqualina-vonlanthendinenna 2021-11-17 updated loading pH data and color palettes
html 7a01367 pasqualina-vonlanthendinenna 2021-11-12 Build site.
Rmd 59073c1 pasqualina-vonlanthendinenna 2021-11-12 added NE Pacific oxygen
html 284003d pasqualina-vonlanthendinenna 2021-11-11 Build site.
html 6276d6c pasqualina-vonlanthendinenna 2021-11-11 Build site.
html a103f60 pasqualina-vonlanthendinenna 2021-11-05 Build site.
Rmd 31576f9 pasqualina-vonlanthendinenna 2021-11-05 changed QC flag maps
html fbd5bac pasqualina-vonlanthendinenna 2021-11-04 Build site.
Rmd 5bcdcda pasqualina-vonlanthendinenna 2021-11-04 added calibration description
html 68977a1 pasqualina-vonlanthendinenna 2021-10-26 Build site.
html b57291a pasqualina-vonlanthendinenna 2021-10-26 Build site.
html bba33bf pasqualina-vonlanthendinenna 2021-10-26 Build site.
Rmd 4bc1859 pasqualina-vonlanthendinenna 2021-10-26 run with full data
html aa7280d jens-daniel-mueller 2021-10-22 Build site.
Rmd ca7ba6b jens-daniel-mueller 2021-10-22 adding revised code
html d84c904 pasqualina-vonlanthendinenna 2021-10-22 Build site.
html 8ecdb43 pasqualina-vonlanthendinenna 2021-10-22 Build site.
Rmd 2b22099 pasqualina-vonlanthendinenna 2021-10-22 edited text
html c81f21c pasqualina-vonlanthendinenna 2021-10-21 Build site.
html b55928d pasqualina-vonlanthendinenna 2021-10-21 Build site.
Rmd 58c24b6 pasqualina-vonlanthendinenna 2021-10-21 timeseries attempt 2, added description
html 62d8519 pasqualina-vonlanthendinenna 2021-10-20 Build site.
html b8feac2 pasqualina-vonlanthendinenna 2021-10-20 Build site.
html 701fffa pasqualina-vonlanthendinenna 2021-10-20 Build site.
Rmd b88a839 pasqualina-vonlanthendinenna 2021-10-20 adding revised code
html d3a081c jens-daniel-mueller 2021-10-19 Build site.
Rmd f460b9a jens-daniel-mueller 2021-10-19 code review jens
html c5e1577 pasqualina-vonlanthendinenna 2021-10-18 Build site.
Rmd 8cc0106 pasqualina-vonlanthendinenna 2021-10-18 added description in loading_data
html 305873e pasqualina-vonlanthendinenna 2021-10-18 Build site.
Rmd 6b484e7 pasqualina-vonlanthendinenna 2021-10-18 added description in loading_data
html 83724a0 pasqualina-vonlanthendinenna 2021-10-14 Build site.
html 4840e49 pasqualina-vonlanthendinenna 2021-10-12 Build site.
Rmd 2fb35f7 pasqualina-vonlanthendinenna 2021-10-12 added reading data in page
html ff925ab pasqualina-vonlanthendinenna 2021-10-11 Build site.
Rmd 7e0cf34 pasqualina-vonlanthendinenna 2021-10-11 added reading data in page

Task

Using the argodata package to load in bgc argo data from the server and store it in a dataframe with the corresponding metadata

Set cache directory

The cache directory stores previously downloaded files to access them more quickly. Cached files are used indefinitely by default because of the considerable time it takes to refresh them. If you use a persistent cache, you should update the index files regularly by using argo_update_global() (data files are also updated occasionally; update these using argo_update_data())

# set cache directory
argo_set_cache_dir(cache_dir = path_argo)

# check cache directory
argo_cache_dir()
[1] "/nfs/kryo/work/updata/bgc_argo_r_argodata"
# check argo mirror
argo_mirror()
[1] "https://data-argo.ifremer.fr"
argo_update_global(max_global_cache_age = Inf)  # age argument: age of the cached files to update in hours (Inf means always use the cached file, and -Inf means always download from the server) 
# ex: max_global_cache_age = 5 updates files that have been in the cache for more than 5 hours, max_global_cache_age = 0.5 updates files that have been in the cache for more than 30 minutes, etc.
argo_update_data(max_data_cache_age = Inf)

Load index files

Load in the synthetic (merged core and bgc) index files (uses the data stored on the ifremer server by default), keeping only delayed-mode data.

File Types

A core-Argo profile contains the CTD sensor parameters (pressure, temperature, salinity) that are measured with the same vertical sampling scheme and at the same location and time. Additional parameters from other sensors are stored in the b-Argo profile files.

A b-Argo profile contains all the parameters from a float, except the core-Argo parameters temperature, pressure, and salinity. A float that performs only CTD measurements does not have a b-Argo file. The vertical level PRES is the simple and unambiguous link between the parameters in the core-Argo and b-Argo files. The same PRES is recorded in the core-Argo and b-Argo files. PRES is the only parameter duplicated in core-Argo and b-Argo profile files.

To facilitate the use of BGC-Argo data, the regional data centers merge each b-Argo file with its corresponding core-Argo file into one synthetic (s-Argo) file. The goal of a simplified s-Argo file is to co-locate as many BGC observations as possible while preserving the character of the sampling pattern, i.e., sample interval, number of samples, and approximate pressure locations. Data come from the single c- and b-Argo files. The synthetic pressure axis is constructed from the BGC sampling levels from each cycle. This means that there is no fixed vertical grid for all floats and all cycles.

The co-location takes different vertical attachments of BGC sensors into account by displacing the pressure location, which is not the case in the c- and b-files. The single-cycle s–file profiles contain all the c-file parameter observations in their original location and resolution.

The adjusted pressure parameter (pres_adjusted) is only available in the core- and s-Argo profile files. The variables profile_pres_qc, pres_adjusted, and pres_adjusted_error, are not duplicated in the b-Argo files.

Data Modes

Delayed-mode data are denoted by data_mode = 'D', and are quality-checked by PIs, who apply any necessary adjustments. For the core CTD data, delayed-mode data is generally available 12 months after the transmission of raw data, because the raw data is usually of good quality. Their delayed-mode assessment involves evaluation of the long-term sensor stability, which typically requires a float record of 12 months. Incorrect QC flag attribution and erroneous raw data not flagged during real-time procedures are corrected in delayed-mode.

Delayed-mode BGC data may be available as early as 5-6 cycles after initial data transmission as the raw data are typically unfit for scientific usage. Adjustments significantly increase the accuracy of these data. In b- and s-Argo profile files, the variable parameter_data_mode indicates the mode of each parameter. Biogeochemical parameters in the same file may receive their delayed-mode adjustments at different times.

Synthetic files info: https://archimer.ifremer.fr/doc/00445/55637/80863.pdf

Argo User Manual: https://archimer.ifremer.fr/doc/00187/29825/86414.pdf

bgc_index <- argo_global_synthetic_prof() %>%
  argo_filter_data_mode(data_mode = 'delayed') %>%  # load in delayed-mode data
  argo_filter_date(date_min = '2013-01-01',
                   date_max = Sys.time())  
Loading argo_global_synthetic_prof()
# check the dates 
# max(bgc_subset$date, na.rm = TRUE)
# min(bgc_subset$date, na.rm = TRUE)

# checking alternative functions
# argo_global_meta(download = NULL, quiet = FALSE)

# argo_global_prof(download = NULL, quiet = FALSE)
# laods in core-argo files (CTD data)

# argo_global_tech(download = NULL, quiet = FALSE)
# An argo technical file contains technical information from an Argo float. This information is registered for each cycle performed by the float. 

# argo_global_traj(download = NULL, quiet = FALSE)
# argo_global_bio_traj(download = NULL, quiet = FALSE)
# load the trajectory files, which contain all received Argos and GPS locations of Argo floats. A trajectory file often contains core and BGC measurements performed at various intermediate times during the cycle and outside the vertical profiles. The full profiles collected upon ascent are not included and are stored in the profile files. 

# argo_global_bio_prof(download = NULL, quiet = FALSE)
# A B-Argo profile file contains all the parameters from a float, except the core-Argo parameters temperature, pressure, and salinity. A float that performs only CTD measurements does not have a B-Argo file

# argo_global_synthetic_prof(download = NULL, quiet = FALSE)

Read data

Read in the adjusted bgc and core variables corresponding to the index files downloaded above, with their quality control flags. (can take a while)

bgc_data <- argo_prof_levels(
  path = bgc_index,
  vars =
    c(
      'PRES_ADJUSTED',
      'PRES_ADJUSTED_QC',
      'PRES_ADJUSTED_ERROR',
      'PSAL_ADJUSTED',
      'PSAL_ADJUSTED_QC',
      'PSAL_ADJUSTED_ERROR',
      'TEMP_ADJUSTED',
      'TEMP_ADJUSTED_QC',
      'TEMP_ADJUSTED_ERROR',
      'DOXY_ADJUSTED',
      'DOXY_ADJUSTED_QC',
      'DOXY_ADJUSTED_ERROR',
      'NITRATE_ADJUSTED',
      'NITRATE_ADJUSTED_QC',
      'NITRATE_ADJUSTED_ERROR',
      'PH_IN_SITU_TOTAL_ADJUSTED',
      'PH_IN_SITU_TOTAL_ADJUSTED_QC',
      'PH_IN_SITU_TOTAL_ADJUSTED_ERROR'
    ),
  quiet = TRUE
) 
# read in the profiles (takes a while)

The data is read in from the cached files stored in the path specified in set_argo_cache_dir() (in this case, /nfs/kryo/work/updata/bgc_argo_r_argodata). To download data directly from the files stored on the ifremer server, set max_global_cache_age and max_data_cache_age to -Inf, which will force a new download.

Read meta data

Read in the corresponding metadata:

bgc_metadata <- argo_prof_prof(path = bgc_index)
Extracting from 138158 files
# bgc_history = argo_prof_history(path = bgc_subset, quiet = TRUE)
# ?????
# returns blank output (0 observations of 0 variables)
# the same occurs if HISTORY_PARAMETER, HISTORY_ACTION, and HISTORY_QCTEST are added into the vars argument when loading the data 
# HISTORY_ACTION : Name of the action (either 'QCP$' for QC test performed, or 'QCF$' for QC test failed)
# HISTORY_PARAMETER : name of the parameter on which the action is performed 
# HISTORY_QCTEST : this field records the code of the QC test performed when ACTION is 'QCP$' or the QC test failed when ACTION is 'QCF$'

# bgc_calibration <- argo_prof_calib(path = bgc_subset, quiet = TRUE)
# contains the variables: 
# PARAMETER: name of the calibrated parameter(s) 
# SCIENTIFIC_CALIB_EQUATION : calibration equation applied to the parameter (if no adjustment is necessary or the data is not adjustable, this field records 'none')
# SCIENTIFIC_CALIB_COEFFICIENT : calibration coefficients for this equation (if no adjustment is necessary or the data is not adjustable, this field records 'none')
# SCIENTIFIC_CALIB_COMMENT : comment about this calibration
# if the delayed-mode adjusted value is the same as the raw value (CTD data) the comment records 'no adjustment necessary'; if the delayed-mode adjusted value has a QC flag of '4', the comment records 'bad data; not adjustable'. 
# SCIENTIFIC_CALIB_DATE : date when the calibration was performed

Join data

Join the metadata and data together into one dataset

bgc_merge <- full_join(bgc_data, bgc_metadata) %>% 
  select(-c(profile_chla_qc:profile_cdom_qc),
        -c(profile_cndc_qc:profile_up_radiance555_qc)) %>% 
    rename(lon = longitude, 
          lat = latitude) %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>% 
  mutate(
    lat = cut(lat, seq(-90, 90, 1), seq(-89.5, 89.5, 1)), 
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 1), seq(20.5, 379.5, 1)), 
    lon = as.numeric(as.character(lon))) %>% 
  mutate(depth = swDepth(pres_adjusted, latitude =  lat), 
         .before = pres_adjusted)
Joining, by = c("file", "n_prof")
# bgc_merge_test <- full_join(bgc_data, bgc_calibration) (not sure why but it crashes R every time)

Write data

Full data

path_argo_preprocessed <- paste0(path_argo, "/preprocessed_bgc_data")

bgc_index %>%
  write_rds(file = paste0(path_argo_preprocessed, "/bgc_index.rds"))

# bgc_calibration %>%
#  write_rds(file = paste0(path_argo_preprocessed, "/bgc_calibration.rds"))

bgc_data %>%
  write_rds(file = paste0(path_argo_preprocessed, "/bgc_data.rds"))

bgc_merge %>%
  write_rds(file = paste0(path_argo_preprocessed, "/bgc_merge.rds"))

pH data

# create a dataframe of full pH data (only good data) with corresponding CTD and metadata, in a 1x1º longitude/latitude grid 
ph_merge_1x1 <- bgc_merge %>% 
  select(-c(doxy_adjusted:nitrate_adjusted_error),
         -c(profile_doxy_qc, profile_nitrate_qc)) %>% 
  filter(ph_in_situ_total_adjusted_qc == '1') %>% 
  mutate(year = year(date),
         month = month(date),
         .after = n_prof)


# create a dataframe of pH data in the surface ocean (upper 20 m of the watercolumn), in a 1x1º longitude/latitude grid
ph_surface_1x1 <- ph_merge_1x1 %>% 
  filter(between(depth, 0, 20)) 

# create a dataframe of pH for the surface ocean (upper 20 m of the watercolumn) in a 2x2º longitude/latitude grid 
ph_surface_2x2 <- ph_surface_1x1 %>%
  mutate(
    lat = cut(lat, seq(-90, 90, 2), seq(-89, 89, 2)), 
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 2), seq(21, 379, 2)), 
    lon = as.numeric(as.character(lon))
   )   # regrid into 2x2º grid 
bgc_metadata <- bgc_metadata %>%
  rename(lon = longitude,
         lat = latitude) %>%
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>%
  mutate(
    lat = cut(lat, seq(-90, 90, 1), seq(-89.5, 89.5, 1)),
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 1), seq(20.5, 379.5, 1)),
    lon = as.numeric(as.character(lon))
  ) %>% 
  select(
    -c(profile_chla_qc:profile_cdom_qc),
    -c(profile_cndc_qc:profile_up_radiance555_qc)
  )

Add in RECCAP biome separations to the pH data

path_basin_mask <- "/nfs/kryo/work/updata/reccap2/"

# load in the RECCAP biome separations 
region_masks_all <-
  stars::read_ncdf(paste(
    path_basin_mask, "RECCAP2_region_masks_all_v20210412.nc", sep = "")) %>%
  as_tibble() %>% 
  mutate(seamask = as.factor(seamask))
no 'var' specified, using open_ocean, atlantic, pacific, indian, arctic, southern, seamask, coast
other available variables:
 lon, lat
Warning in .get_nc_projection(meta$attribute, rep_var, all_coord_var): No
projection information found in nc file.
# harmonise the latitude longitude bands of the biomes to the pH data (2x2 grid)
region_masks_all_seamask_2x2 <- region_masks_all %>% 
  select(lat, lon, seamask) %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>% 
  mutate(
    lat = cut(lat, seq(-90, 90, 2), seq(-89, 89, 2)),
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 2), seq(21, 379, 2)),
    lon = as.numeric(as.character(lon))
  )

region_masks_all_seamask_1x1 <- region_masks_all %>% 
  select(lat, lon, seamask) %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>% 
  mutate(
    lat = cut(lat, seq(-90, 90, 1), seq(-89.5, 89.5, 1)),
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 1), seq(20.5, 379.5, 1)),
    lon = as.numeric(as.character(lon))
  )

region_masks_all <- region_masks_all %>% 
  select(-seamask) %>% 
  pivot_longer(open_ocean:southern, 
               names_to = 'region',
               values_to = 'value') %>% 
  mutate(value = as.factor(value))

# harmonise the lat/lon of the regional separations to our pH data 
region_masks_all_1x1 <- region_masks_all %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>% 
  mutate(
    lat = cut(lat, seq(-90, 90, 1), seq(-89.5, 89.5, 1)), 
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 1), seq(20.5, 379.5, 1)), 
    lon = as.numeric(as.character(lon))
)

region_masks_all_2x2 <- region_masks_all %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>% 
  mutate(
    lat = cut(lat, seq(-90, 90, 2), seq(-89, 89, 2)),
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 2), seq(21, 379, 2)),
    lon = as.numeric(as.character(lon))
  )

# add the region names to the surface pH dataframes
ph_surface_2x2 <- inner_join(ph_surface_2x2, region_masks_all_2x2)
Joining, by = c("lat", "lon")
ph_surface_1x1 <- inner_join(ph_surface_1x1, region_masks_all_1x1)
Joining, by = c("lat", "lon")
ph_merge_1x1 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/ph_merge_1x1.rds"))

ph_surface_1x1 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/ph_surface_1x1.rds"))

ph_surface_2x2 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/ph_surface_2x2.rds"))

bgc_metadata %>%
  write_rds(file = paste0(path_argo_preprocessed, "/bgc_metadata.rds"))

region_masks_all_seamask_1x1 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/region_masks_all_seamask_1x1.rds"))

region_masks_all_seamask_2x2 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/region_masks_all_seamask_2x2.rds"))

region_masks_all_1x1 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/region_masks_all_1x1.rds"))

region_masks_all_2x2 %>% 
  write_rds(file = paste0(path_argo_preprocessed, "/region_masks_all_2x2.rds"))

oceanSODA pH data

OceanSODA <-
  tidync::hyper_tibble(paste(
    path_updata,
    "/pco2_oceansoda-ethz/OS-ETHZ-GRaCER-v2021a_1982-2020.nc",
    sep = ""
  ))

OceanSODA <- OceanSODA %>% 
  mutate(date = as.Date(time, origin = '1982-01-15'),
         year = year(date)) %>% 
  select(year, date, lat, lon, ph_total, ph_total_uncert) %>% 
  mutate(lon = if_else(lon < 20, lon + 360, lon)) %>%
  mutate(
    lat = cut(lat, seq(-90, 90, 1), seq(-89.5, 89.5, 1)),
    lat = as.numeric(as.character(lat)),
    lon = cut(lon, seq(20, 380, 1), seq(20.5, 379.5, 1)),
    lon = as.numeric(as.character(lon))
  ) %>% 
  filter(year >= 2013)
  
OceanSODA %>% 
  write_rds(file = paste0(path_argo_preprocessed, '/OceanSODA.rds'))

Data set description

Columns

The resulting dataframe contains:

  • the file name (file column)

  • the sampling level (n_level column)

  • the number of profiles per file (n_prof column; Each single-cycle synthetic profile has the dimension n_prof = 1).

  • adjusted values for pressure (PRES, in dbar), salinity (PSAL, in psu), temperature (TEMP, in degrees C), dissolved oxygen (DOXY, in µmol kg-1), pH (PH_IN_SITU_TOTAL), and nitrate (NITRATE, in µmol kg-1) (parameter_adjusted columns). This column is mandatory, so if no adjustment was performed (i.e. parameter_adjusted does not exist), FillValue is inserted (e.g., temp_adjusted:FillValue = 99999.f). If the raw value did not require adjustment in delayed-mode, then parameter_adjusted = parameter.

  • a quality control flag associated with these adjusted values (parameter_adjusted_qc columns). If an adjusted value does not exist (e.g., temp_adjusted = 99999.f), then FillValue is inserted (e.g., temp_adjusted_qc = " ").

  • an error estimate on the adjustment of the measurement (parameter_adjusted_error columns). If no adjusted value exists (e.g., temp_adjusted = 99999.f), then FillValue is inserted (e.g., temp_adjusted_error = 99999.f)

  • WMO float identifier (platform_number column)

  • name of the project in charge of the float (project_name column)

  • name of principal investigator in charge of the float (pi_name column)

  • float cycle number (cycle_number column; cycle 0 is the launch cycle during which technical data or configuration information is transmitted; cycle 1 is the first complete cycle)

  • descending (D) or ascending (A) profile (direction column). Profile measurements are taken on ascent, occasionally during descent (rarely both).

  • code for the data centre in charge of the float data management (data_centre column)

  • the type of float (platform_type column)

  • firmware version of the float (firmware_version column)

  • instrument type from the WMO code table 1770 (wmo_inst_type column)

  • the date and time at which the measurement was taken, in UTC (date column)

  • a quality control flag for the date and time value (date_qc column)

  • the date and time of the profile location (date_location column)

  • latitude in degrees N (latitude column)

  • longitude in degrees E (longitude column)

  • quality control flag on the position (position_qc column)

  • name of the system in charge of positioning the float locations (positioning_system column)

  • unique number of the mission to which this float belongs (config_mission_number column,

  • a global quality control flag on the profile of the parameter (profile_parameter_qc column; FillValue = " ")

QC flags

QC flags for values (‘parameter_adjusted_qc’ columns) are between 1 and 8, where:
1 is ‘good’ data,
2 is ‘probably good’ data,
3 is ‘probably bad’ data,
4 is ‘bad’ data,
5 is ‘value changed’,
8 is ‘estimated value’,
9 is ‘missing value’ (data parameter will record FillValue)
(6 and 7 are not used).

Profile QC flags (‘profile_parameter_qc’ columns) are QC codes attributed to the entire profile, and indicate the number of depth levels (in %) where the value is considered to be good data (QC flags of 1, 2, 5, and 8; QC flags of 9 or " " are not used in the computation):
‘A’ means 100% of profile levels contain good data,
‘B’ means 75-<100% of profile levels contain good data,
‘C’ means 50-75% of profile levels contain good data,
‘D’ means 25-50% of profile levels contain good data,
‘E’ means >0-50% of profile levels contain good data,
‘F’ means 0% of profile levels contain good data.

Quality Control Tests

There are two levels of Argo data quality control:

  • The first level is the real-time system that performs a set of agreed automatic checks
  • The second level is the delayed-mode quality control system.

Real-time QC tests

  1. Platform identification test

If a float WMO ID cannot be matched to the correct float platform then none of the data will be distributed.

  1. Impossible date test

This test requires that the Julian Day of the float be later than 1st January 1997 and earlier than the current date of the check (in UTC time). If the date of a profile fails this test, the date of the profile should be flagged as bad data (‘4’) and none of the profile data is distributed.

  1. Impossible location test

This test requires that the observation latitude and longitude of a float be sensible, with latitude in the range -90 to 90º, and longitude in the range -180 to 180º.

If either latitude or longitude fails this test, the position is flagged as bad data (‘4’) and none of the profile data is distributed.

  1. Position on land test

This test requires that the observation latitude and longitude be located in an ocean. If a position cannot be located in an ocean, the position is flagged as bad data (‘4’) and none of the profile data is distributed.

  1. Impossible speed test

Drift speeds for floats can be generated given the positions and times of the floats when they are at the sea surface and between profiles. In all cases, we would not expect the drift speed to exceed 3 ms-1. If it does, it means either the positions or times are bad data, or a float is mislabeled. Using the multiple positions and times that are normally available for a float while at the sea surface, it is often possible to isolate the one position or time that is an error.

If an acceptable position and time can be used from the available suite, then the data can be distributed. Otherwise, the position, the time, or both, are flagged as bad data (‘4’) and the profile data is not distributed.

  1. Global range test

This test applies a gross filter on the values of TEMP, PRES, and PSAL. The ranges need to accommodate all of the expected extremes in the ocean.

  • Pressure cannot be less than -5 dbar. If PRES < -5, then PRES_QC = ‘4’, TEMP_QC = ‘4’, and PSAL_QC = ‘4’.
  • Pressure in the range -5 to -2.4 dbar should be considered ‘probably bad’ data. If -5 ≤ PRES ≤ -2.4, then PRES_QC = ‘3’, TEMP_QC = ‘3’, PSAL_QC = ‘3’.
  • Temperature should be in the range -2.5 to 40.0 ºC. Outside of this range TEMP_QC = ‘4’.
  • Salinity should be in the range 2 to 41.0 PSU. Outside of this range, PSAL_QC = ‘4’.
  • DOXY should be in the range -5 to 600 µmol kg-1. Outside of this range, DOXY_QC = '4'.
  • PH_IN_SITU_TOTAL should be in the range 7.3 to 8.5. Outside of this range, PH_IN_SITU_TOTAL_QC = '4'.
  1. Regional range test (CTD data)

This test applies to certain regions of the world where conditions can be further qualified. In this case, specific ranges for observations from the Mediterranean Sea and the Red Sea further restrict what can be accepted as reasonable values.

If a value fails this test, it is flagged as bad data (‘4’) and removed from the initial distribution. If temperature and salinity at the same pressure level both fail this test, both values are flagged as bad data (‘4’) and values for pressure, temperature, and salinity are removed from the distribution.

  1. Pressure increasing test (CTD data)

This test requires that the vertical profile has pressures that are monotonically increasing (assuming the pressure levels are ordered from smallest to largest).

If there is a region of constant pressure, all but the first of the consecutive constant pressure levels is flagged as bad data (‘4’). If there is a region where pressure reverses, all of the pressures in the reversed part of the profile are flagged as bad data (‘4’). All pressures flagged as bad data and associated temperatures and salinities are removed.

  1. Spike test

The difference between sequential measurements, where one measurement is significantly different from adjacent ones, is a spike in both size and gradient. This test does not consider differences in pressure, but assumes a sampling that adequately reproduces changes in temperature and salinity with pressure.

Test value = | V2 - (V3 + V1)/2 | - | (V3 - V1)/2 |

where V2 is the measurement being tested, and V1 and V3 are the values above and below.

Temperature: the V2 value is flagged when:

  • the test value exceeds 6.0 ºC for pressures less than 500 dbar, or
  • the test value exceeds 2.0 ºC for pressures equal to or greater than 500 dbar.

Salinity: the V2 value is flagged when:

  • the test value exceeds 0.9 PSU for pressures less than 500 dbar, or
  • the test value exceeds 0.3 PSU for pressures equal to or greater than 500 dbar.

DOXY: the V2 value is flagged when:

  • the test value exceeds 50 µmol kg-1 for pressures less than 500 dbar, or
  • the test value exceeds 25 µmol kg-1 for pressures equal to or greater than 500 dbar.

For pH:

Test value 2 = | V2 - median(V0, V1, V2, V3, V4) |

where the test value represents the anomaly of the observed pH from the median of the surrounding data. A pH data point is considered a spike and flagged as bad (‘4’) if Test Value 2 > 0.04pH

If the value V2 fails this test, it is flagged as bad data (‘4’) and is removed. If temperature and salinity both fail this test, both values are flagged as bad data (‘4’) and values for temperature, salinity and pressure are removed.

  1. Obsolete
  2. Gradient test (DOXY only)

This test is failed when the difference between vertically adjacent measurements is too steep. The test does not consider changes in depth, but assumes a sampling that adequately reproduces changes in DOXY with depth

Test value = | V2 - (V3 + V1)/2 |

where V2 is the value being tested as a spike, and V1 and V3 are the values above and below.

For DOXY, V2 is flagged when:

  • the test value exceeds 50 µmol kg-1 for pressures less than 500 dbar, or

  • the test value exceeds 25 µmol kg-1 for pressures equal to or greater than 500 dbar

  1. Digit rollover test (CTD data)

Only so many bits are allowed to store temperature and salinity values in a profiling float. This range is not always large enough to accommodate conditions which are encountered in the ocean. When the range is exceeded, stored values rollover to the lower end of the range. This rollover should be detected and compensated for when profiles are constructed from the data stream of the float. This test is used to make sure the rollover is properly detected.

  • Temperature difference between adjacent pressures > 10 ºC
  • Salinity difference between adjacent pressures > 5 PSU

If a value fails this test, it is flagged as bad data (‘4’) and removed from the initial distribution. If temperature and salinity at the same pressure level both fail this test, both values are flagged as bad data (‘4’) and values for pressure, temperature, and salinity are removed from the distribution.

  1. Stuck value test

This test looks for CTD and BGC measurements in the same profile being identical.

If this occurs, all of the values affected parameter are flagged as bad data (‘4’) and removed from the distribution. If both temperature and salinity are affected, then all observed values from the profile are flagged as bad data (‘4’).

  1. Density inversion test (CTD data)

This test compares potential density between valid measurements in a profile in both directions (i.e., from top to bottom, and from bottom to top). Values of temperature and salinity at the same pressure level Pi are used to compute potential density ρi ( or σi = ρi - 1000) kg m-3, referenced to the mid-point between Pi and the next valid pressure level. A threshold of 0.03 kg m-3 is allowed for small density inversions.

From top to bottom, if the potential density calculated at the greater pressure Pi+1 is less than that calculated at the lesser pressure Pi by more than 0.03 kg m-3, both the temperature and salinity values at pressure Pi are flagged as bad data (‘4’). From bottom to top, if the potential density calculated at the lesser pressure Pi-1 is greater than that calculated at the greater pressure Pi by more than 0.03 kg m-3, both the temperature and salinity values at pressure Pi are flagged as bad data (‘4’). Bad temperature and salinity are removed from the distribution.

  1. Grey list test

This test is implemented as a mechanism for data assembly centers (DACs) to flag, in real-time, sensors that are potentially not working correctly. Each DAC manages a grey list and sends it to the GDACs. The merged grey list from all DACs is available from the GDACs.

Naming convention: xxx_greylist.csv (where xxx is the DAC name, e.g., aoml_greylist.csv, coriolis_greylist.csv, etc).

Columns: PLATFORM, PARAMETER, START_DATE, END_DATE, QC, COMMENT, DAC

The decision to insert a float parameter in the grey list comes from the PI or the delayed-mode operator. A float parameter should be put in the grey list when the sensor drift is too big to be adjusted in real-time, or when the sensor is judged to be potentially not working correctly.

The grey list concerns only real-time files. When an anomalous float is dead and the offending parameter has been adjusted in delayed-mode, it is removed from the grey list. When an anomalous float is active and the offending parameter has been partially adjusted in delayed-mode, it will remain on the grey list if real-time adjustment is not adequate.

Grey-listed parameters are flagged as probably good (‘2’), probably bad (‘3’) or bad (‘4’) data, as determined by the PI or the delayed-mode operator.

  1. Gross salinity or temperature sensor drift test (CTD)

This test is implemented to detect a sudden and significant sensor drift. It calculates the average temperature and salinity from the deepest 100 dbar of a profile and the previous good profile. Only measurements with good QC are used.

For salinity, if the difference between the two average values is more than 0.5 PSU, then all the salinity values of the profile are flagged as probably bad data (‘3’). For temperature, if the difference between the two average values is more than 1 ºC, then all the temperature values from the profile are flagged as probably bad data (‘3’).

  1. Visual QC test

This is subjective visual inspection of float measurements by an operator. This test is not mandatory before real-time data distribution.

  1. Frozen profile test (CTD data)

This test is used to detect a float that produces the same profile (with very small deviations) over and over again. Typically the differences between two profiles are of the order of 0.001 PSU for salinity and of the order 0.01 ºC for temperature.

  1. Derive temperature and salinity profiles by averaging the original profiles to get mean values for each profile in 50 dbar slabs (T_prof, T_previous_prof, S_prof, S_previous_prof). This is necessary because the floats do not sample at the same level in each profile.

  2. Obtain absolute values of the difference between the averaged temperature and salinity profiles as follows:

  • deltaT = abs(T_prof - T_previous_prof)
  • deltaS = abs(S_prof - S_previous_prof)
  1. Find the maximum, minimum, and mean of the absolute values of the averaged differences between profiles for temperature and salinity:
  • mean(deltaT), max(deltaT), min(deltaT)
  • mean(deltaS), max(deltaS), min(deltaS)
  1. To fail the test, require that:
  • max(deltaT) < 0.3 ºC
  • min(deltaT) < 0.001 ºC
  • mean(deltaT) < 0.02 ºC
  • max(deltaS) < 0.3 PSU
  • min(deltaS) < 0.001 PSU
  • mean(deltaS) < 0.004 PSU

If a profile fails this test, all measurements from this profile are flagged as bad data (‘4’). If a float fails this test over 5 consecutive cycles, it is inserted in the grey list.

  1. Deepest pressure test

This test requires that a profile has pressures that are not greater than CONFIG_ProfilePressure_dbar plus 10%. The value of CONFIG_ProfilePressure_dbar is in the meta.nc file of the float.

If there is a region of incorrect pressures, those pressures and their corresponding temperature and salinity measurements are flagged as bad data (‘4’). Pressures flagged as bad data and their associated measurements should be removed from distribution.

  1. MEDian with a distance (MEDD) test (CTD)

This test is a set of algorithms based on three main steps:

  • First, the computation of a sliding median with some customizations
  • Then, limits are computed that are at relative 2-dimension distance d from the median
  • Finally, these limits are also computed for the density profile. There is a spike if both the density profile measurement profile are out of limits. If there is no conductivity sensor, then the spikes in temperature are evaluated using a bigger d value.

Temperature and salinity values that fail this test are flagged as bad data (‘4’).

  1. pH-specific real-time QC test (PH_IN_SITU_TOTAL only)

Currently, there is no pH-specific QC test. If one is established, it will be reported with the number ‘56’.

Real-time pH values which pass the real-time QC tests are assigned QC flags of ‘3’. The Argo goals for research-quality data require that pH values be adjusted to receive a quality flag of ‘1’.

  1. DOXY-specific real-time QC test (DOXY only)

Real-time unadjusted DOXYvalues receive QC flags of ‘3’. This is because the majority of oxygen sensors deployed on BGC Argo profiling floats are Aanderaa optodes that suffer from pre-deployment storage drift that can reduce accuracy by up to 20% or more. Because this is a known bias that affects the majority of oxygen sensors within the array, and because it can be corrected, DOXY_QC is set to ‘3’.

  1. Nitrate-specific real-time QC test (NITRATE only)

Not yet available

Test application order on vertical profiles

The Argo real-time QC tests on CTD data (temperature, salinity, pressure) are performed in the order described in the following table.

A CTD measurement with a QC flag ‘4’ is ignored by other QC tests. A measurement with QC flag ‘2’ or ‘3’ is tested by other QC tests.

A DOXY measurement with a QC flag ‘4’ or ‘3’ is ignored by other QC tests.

Note that the Test Number is different from the Application Order. The Test Number (n) is a number assigned permanently to each QC test. It is used to fill HISTORY_QCTEST in the Argo profile files. Therefore, each Test Number is uniquely associated to a QC test, and is never replaced, changed, or duplicated.

Each real-time QC test has a unique Binary ID (2n) of the unique Test Number (n) is used to record QC tests performed and failed in the variable HISTORY_QCTEST.

The QC flag assigned by a test cannot override a higher value assigned by a previous QC test.

e.g.: a QC flag ‘4’ (bad data) set by the Grey List Test cannot be decreased to QC flag ‘3’ (bad data that are potentially correctable) set by the Gross Salinity or Temperature Sensor Drift Test.

Application Order for CTD parameters Test Number (n) Binary ID (2n) Test Name
1 1 2 Platform Identification Test
2 2 4 Impossible Date Test
3 3 8 Impossible Location Test
4 4 16 Position on Land Test
5 5 32 Impossible Speed Test
6 15 32768 Grey List Test
7 19 524288 Deepest Pressure Test
8 6 64 Global Range Test
9 7 128 Regional Range Test
10 8 256 Pressure Increasing Test
11 9 512 Spike Test
12 25 33554432 MEDD Test
13 12 4096 Digit Rollover Test
14 13 8192 Stuck Value Test
15 14 16384 Density Inversion Test
16 16 65536 Gross Salinity or Temperature Sensor Drift Test
17 18 261144 Frozen Profile Test
18 17 131072 Visual QC Test

The real-time tests for BGC parameters are performed in the order described in the following table:

Application order for BGC parameters Test Number (n) Binary ID (2n) Test Name
1 19 524288 Deepest Pressure Test
2 1 2 Platform Identification Test
3 2 4 Impossible Date Test
4 3 8 Impossible Location Test
5 4 16 Position on Land Test
6 5 32 Impossible Speed Test
7 6 64 Global Range Test
8 7 128 Regional Range Test
9 9 512 Spike Test
10 11 2048 Gradient Test
11 12 4096 Digit Rollover Test
12 13 8192 Stuck Value Test
13 15 32768 Grey List Test
14 16 65536 Gross Temperature Sensor Drift Test (only for TEMP_DOXY)
15 18 261144 Frozen Profile Test
16 BGC parameter-specific tests
17 17 131072 Visual QC Test

Delayed-Mode Quality Control

The QC flags determined in delayed-mode replace those assigned in real-time because some bad data cannot be detected by the real-time tests, and some good data can be identified wrongly as bad by the real-time tests.

For vertical profile data, delayed-mode operators examine them for pointwise errors (such as spikes and jumps) and flag them appropriately. If an error is identified, both PARAM_QC and PARAM_ADJUSTED_QC record ‘4’. Conversely, if good data have wrongly been identified as bad by the real-time tests, then PARAM_QC and PARAM_ADJUSTED_QC record ‘1’.

In SD-files, the variables PROFILE_PARAMETER_QC, PARAMETER_ADJUSTED, PARAMETER_ADJUSTED_QC, and PARAMETER_ADJUSTED_ERROR are compulsory. If no adjustment in delayed-mode is necessary and if the flag is deemed assigned correctly, then PARAM_ADJUSTED = PARAMETER, PARAM_ADJUSTED_QC = PARAM_QC, and PARAM_ADJUSTED_ERROR is provided by the PI.

If no delayed-mode adjustment was performed, then PARAM_ADJUSTED = 99999.f, PARAM_ADJUSTED_QC = " ", PARAM_ADJUSTED_ERROR = 99999.f and PROFILE_PARAMETER_QC = " ".

If values are deemed unadjustable in delayed-mode, then PARAM_ADJUSTED_QC = '4', and PARAM_ADJUSTED = 99999.f and PARAM_ADJUSTED_ERROR = 99999.f.

The variable PROFILE_PARAMETER_QC is recomputed when PARAMETER_ADJUSTED_QC becomes available.

Dates

Delayed-mode operators check that the dates in the profile are in chronological order. Erroneous or missing dates are replaced with another telemetered value if available, or replaced with interpolated values and marked DATE_QC = '8'.

Location

Profile positions LONGITUDE, LATITUDE are checked for outliers. Erroneous or missing dates are replaced with another telemetered value if available, or replaced with interpolated values and marked POSITION_QC = '8'.

Pressure, Temperature, Salinity

Delayed-mode quality control of PRES and TEMP is done by subjective assessment of vertical profile plots of TEMP vs PRES and PSAL vs PRES and PRES vs TEMP and PSAL vs TEMP. This assessment is done in relation to measurements from the same float, as well as in relation to nearby floats and historical data. This assessment aims to identify: (a) erroneous data points that cannot be detected by real-time QC tests, and (b) vertical profiles that have the wrong shape.

Bad PRES data points identified by visual inspection from delayed-mode analysts are recorded with PRES_ADJUSTED_QC = '4' and PRES_QC = '4'. For these bad data points, TEMP_ADJUSTED_QC, TEMP_QC, PSAL_ADJUSTED_QC, and PSAL_QC are also set to ‘4’.

Bad TEMP data points are recorded with TEMP_ADJUSTED_QC = '4' and TEMP_QC = '4'. TEMP_ADJUSTED, TEMP_ADJUSTED_QC, TEMP_ADJUSTED_ERROR are filled even when the data is good and no adjustment is needed. In these cases, TEMP_ADJUSTED_ERROR can be the manufacturer’s quoted accuracy at deployment, which is 0.002 ºC.

Delayed-mode quality control of PSAL is done by checking for sensor offsets and drifts, as well as other instrument errors. Float salinity values that are considered adjustable in delayed-mode are compiled into time-series. Sufficiently long time-series are compared with statistical recommendations and uncertainties to check for sensor drift and offset.

After assessing all available information, the PI records PSAL_ADJUSTED, PSAL_ADJUSTED_QC, and PSAL_ADJUSTED_ERROR. Salinity data considered bad and unadjustable in delayed-mode are given PSAL_ADJUSTED_QC = '4', and PSAL_ADJUSTED and PSAL_ADJUSTED_ERROR are set to FillValue.

Oxygen

Raw DOXY values are adjusted in delayed-mode to account for sensor drift and bias. The errors associated with this calibration are recorded in DOXY_ADJUSTED_ERROR in µmol kg-1.

When DOXY for the whole profile is bad and cannot be adjusted, then DOXY_ADJUSTED = 99999.f, DOXY_ADJUSTED_ERROR = 99999.f, and DOXY_ADJUSTED_QC = '4'. The calibration information is recorded as SCIENTIFIC_CALIB_EQUATION = 'none', SCIENTIFIC_CALIB_EQUATION = 'none', and SCIENTIFIC_CALIB_COMMENT = 'Bad data; not adjustable'.

pH

The pH adjustment process depends on having an accurate model for pH below 1000 m, where temporal and spatial variability is minimal. pH values are adjusted using Multiple Linear Regression (MLR) methods, Linearly Interpolated Regression equations, and a neural network prediction system known as CANYON. The expected error in float pH measurements is derived from the uncertainty in the reference data as well as sensor uncertainties.

The empirical algorithms used in the adjustment process for pH are:

the MLR method of Williams et al. (2016)

the LIR method of Carter et al. (2018)

the CANYON method of Sauzede et al. (2017)

The method used for adjustment is recorded in SCIENTIFIC_CALIB_EQUATION, SCIENTIFIC_CALIB_COEFFICIENT, and SCIENTIFIC_CALIB_COMMENT

Quality control manuals

CTD data quality control: https://archimer.ifremer.fr/doc/00228/33951/32470.pdf (http://dx.doi.org/10.13155/33951)

Oxygen data quality control: https://archimer.ifremer.fr/doc/00354/46542/82301.pdf (http://dx.doi.org/10.13155/46542)

pH data quality control: https://archimer.ifremer.fr/doc/00460/57195/61336.pdf (https://doi.org/10.13155/57195)

BGC data quality control: https://archimer.ifremer.fr/doc/00298/40879/42267.pdf (http://dx.doi.org/10.13155/40879)


sessionInfo()
R version 4.0.3 (2020-10-10)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: openSUSE Leap 15.2

Matrix products: default
BLAS:   /usr/local/R-4.0.3/lib64/R/lib/libRblas.so
LAPACK: /usr/local/R-4.0.3/lib64/R/lib/libRlapack.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] oce_1.4-0           testthat_3.0.4      sf_1.0-2           
 [4] gsw_1.0-6           lubridate_1.7.9     argodata_0.0.0.9000
 [7] forcats_0.5.0       stringr_1.4.0       dplyr_1.0.5        
[10] purrr_0.3.4         readr_1.4.0         tidyr_1.1.3        
[13] tibble_3.1.3        ggplot2_3.3.5       tidyverse_1.3.0    
[16] workflowr_1.6.2    

loaded via a namespace (and not attached):
 [1] fs_1.5.0           bit64_4.0.5        progress_1.2.2     httr_1.4.2        
 [5] rprojroot_2.0.2    tools_4.0.3        backports_1.1.10   bslib_0.2.5.1     
 [9] utf8_1.2.2         R6_2.5.1           KernSmooth_2.23-17 DBI_1.1.1         
[13] colorspace_2.0-2   withr_2.4.2        tidyselect_1.1.0   prettyunits_1.1.1 
[17] bit_4.0.4          compiler_4.0.3     git2r_0.27.1       cli_3.0.1         
[21] rvest_0.3.6        RNetCDF_2.4-2      xml2_1.3.2         sass_0.4.0        
[25] scales_1.1.1       classInt_0.4-3     proxy_0.4-26       digest_0.6.27     
[29] rmarkdown_2.10     pkgconfig_2.0.3    htmltools_0.5.1.1  dbplyr_1.4.4      
[33] tidync_0.2.4       rlang_0.4.11       readxl_1.3.1       rstudioapi_0.13   
[37] jquerylib_0.1.4    generics_0.1.0     jsonlite_1.7.2     vroom_1.5.5       
[41] magrittr_2.0.1     ncmeta_0.3.0       Rcpp_1.0.7         munsell_0.5.0     
[45] fansi_0.5.0        abind_1.4-5        lifecycle_1.0.0    stringi_1.5.3     
[49] whisker_0.4        yaml_2.2.1         grid_4.0.3         blob_1.2.1        
[53] parallel_4.0.3     promises_1.2.0.1   crayon_1.4.1       haven_2.3.1       
[57] stars_0.5-2        hms_0.5.3          knitr_1.33         pillar_1.6.2      
[61] reprex_0.3.0       glue_1.4.2         evaluate_0.14      modelr_0.1.8      
[65] vctrs_0.3.8        tzdb_0.1.2         httpuv_1.6.2       cellranger_1.1.0  
[69] gtable_0.3.0       assertthat_0.2.1   xfun_0.25          lwgeom_0.2-5      
[73] broom_0.7.9        e1071_1.7-8        later_1.3.0        ncdf4_1.17        
[77] class_7.3-17       units_0.7-2        ellipsis_0.3.2