SEUS MBON Cruise Data

“Raw” data comes from https://gcoos5.geos.tamu.edu/erddap. The data hosted there has already had some processing done, but this cleans it even further.

After processing the cleaned data will be in ./data/cleaned/. A version of the cleaned data is hosted by USF IMaRS at here.

The code below is used for fetching the data. Cleaning is done per-cruise, code can be found alongside visualizations in the “Cruise Reports”.

if (!nzchar(system.file(package = "librarian"))) {
  install.packages("librarian")
}

librarian::shelf(
  quiet = TRUE,
  librarian, conflicted, ggplot2, tibble, tidyr, readr, purrr, dplyr, stringr,
  forcats, lubridate, glue, fs, magrittr, here, rerddap, cli,
)

  These packages will be installed:

  'rerddap'

  It may take some time.

also installing the dependencies 'hoardr', 'ncdf4'

conflicts_prefer(
  dplyr::filter(),
  dplyr::select()
)

[conflicted] Will prefer dplyr::filter over any other package.

[conflicted] Will prefer dplyr::select over any other package.

# source(here("R", "ctd_download.R"))

"https://gcoos5.geos.tamu.edu/erddap/" %>%
  Sys.setenv(RERDDAP_DEFAULT_URL = .)

# search for  all cruise ctd tables in ERDDAP
all_cruise_info <-
  ed_search_adv(
    query     = "Walton Smith CTD",
    # maxTime   = "2016-01-01T01:00:00Z",
    page_size = 1e4
  )

# find unique cruise names
all_cruise_ids <-
  str_extract(all_cruise_info$info$title, "(WS|SAV|WB|H)\\d{3,5}") %>%
  unique()

# print info about cruise IDs found
cli::cli_alert_info(
  c(
    "{col_green(\"Number of files queried\")}: ",
    "{nrow(all_cruise_info$info)} files\n",
    "{col_blue(\"N cruises:\")} {length(all_cruise_ids)}\n\n"
  )
)

ℹ Number of files queried: 3542 files
N cruises: 69

print(all_cruise_ids)

 [1] "WS0603"   "WS0612"   "WS0618"   "WS0623"   "WS0704"   "WS0718"  
 [7] "WS0802"   "WS0807"   "WS0901"   "WS0906"   "WS0914"   "WS0919"  
[13] "WS0923"   "WS1004"   "WS1007"   "WS1015"   "WS1018"   "WS1102"  
[19] "WS1106"   "WS1113"   "WS1116"   "WS1202"   "WS1207"   "WS1212"  
[25] "WS1418"   "WS15103"  "WS15152"  "WS15208"  "WS15264"  "WS15320" 
[31] "WS16004"  "WS16074"  "WS16207"  "WS16263"  "WS16319"  "WS17030" 
[37] "WS17086"  "WS17170"  "WS17212"  "WS17282"  "WS18008"  "WS18120" 
[43] "WS18218"  "WS18285"  "WS18351"  "WS19028"  "WS19119"  "WS19210" 
[49] "WS19266"  "WS19322"  "WS20006"  "WS20231"  "WS20279"  "WS20342" 
[55] "WS21032"  "WS21093"  "WS21151"  "WS21212"  "WS21338"  "WS22022" 
[61] "WS22072"  "WS22141"  "WS22215"  "WS22281"  "WS22337"  "WS23010" 
[67] "WS23061"  "SAV1803"  "SAV18173"

dir_data_dwnld_save <- here("data", "raw", "ctd")       # download path
dir_data_avg_save   <- here("data", "processed", "ctd") # averaged path

dir_create(dir_data_avg_save)