Budgets

workflowr

• Summary
• Checks
• Past versions

Last updated: 2022-07-29

Checks: 7 0

Knit directory: emlr_obs_analysis/analysis/

This reproducible R Markdown analysis was created with workflowr (version 1.7.0). 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(20210412)

The command set.seed(20210412) 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: f04d8ed

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 f04d8ed. 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:    data/
    Ignored:    output/other/
    Ignored:    output/publication/

Untracked files:
    Untracked:  figure/

Unstaged changes:
    Modified:   analysis/_site.yml
    Modified:   analysis/child/budget_analysis_plot_data.Rmd
    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/surface_equi_budgets.Rmd) and HTML (docs/surface_equi_budgets.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
html	08c00b4	jens-daniel-mueller	2022-07-16	Build site.
Rmd	cbde57a	jens-daniel-mueller	2022-07-16	include surfave equilibrium analysis

---

version_id_pattern <- "e"
config <- "MLR_basins"

1 Read files

print(version_id_pattern)

[1] "e"

# identify required version IDs

Version_IDs_1 <- list.files(path = "/nfs/kryo/work/jenmueller/emlr_cant/observations",
                            pattern = paste0("v_1", "e"))

Version_IDs_2 <- list.files(path = "/nfs/kryo/work/jenmueller/emlr_cant/observations",
                            pattern = paste0("v_2", "e"))

Version_IDs_3 <- list.files(path = "/nfs/kryo/work/jenmueller/emlr_cant/observations",
                            pattern = paste0("v_3", "e"))

Version_IDs <- c(Version_IDs_1, Version_IDs_2, Version_IDs_3)

# print(Version_IDs)

1.1 Global

for (i_Version_IDs in Version_IDs) {
  # i_Version_IDs <- Version_IDs[1]
  
  # print(i_Version_IDs)
  
  path_version_data     <-
    paste(path_observations,
          i_Version_IDs,
          "/data/",
          sep = "")
  
  # load and join data files
  
  dcant_budget_global <-
    read_csv(paste(path_version_data,
                   "dcant_budget_global.csv",
                   sep = ""))
  
  dcant_budget_global_mod_truth <-
    read_csv(paste(
      path_version_data,
      "dcant_budget_global_mod_truth.csv",
      sep = ""
    ))
  
  dcant_budget_global_bias <-
    read_csv(paste(path_version_data,
                   "dcant_budget_global_bias.csv",
                   sep = ""))
  
  lm_best_predictor_counts <-
    read_csv(paste(path_version_data,
                   "lm_best_predictor_counts.csv",
                   sep = ""))
  
  lm_best_dcant <-
    read_csv(paste(path_version_data,
                   "lm_best_dcant.csv",
                   sep = ""))
  
  dcant_budget_global <- bind_rows(dcant_budget_global,
                                      dcant_budget_global_mod_truth)
  
  dcant_budget_global <- dcant_budget_global %>%
    mutate(Version_ID = i_Version_IDs)
  
  dcant_budget_global_bias <- dcant_budget_global_bias %>%
    mutate(Version_ID = i_Version_IDs)
  
  lm_best_predictor_counts <- lm_best_predictor_counts %>%
    mutate(Version_ID = i_Version_IDs)
  
  lm_best_dcant <- lm_best_dcant %>%
    mutate(Version_ID = i_Version_IDs)

  params_local <-
    read_rds(paste(path_version_data,
                   "params_local.rds",
                   sep = ""))
  
  params_local <- bind_cols(
    Version_ID = i_Version_IDs,
    MLR_basins := str_c(params_local$MLR_basins, collapse = "|"),
    tref1 = params_local$tref1,
    tref2 = params_local$tref2)
  
  tref <- read_csv(paste(path_version_data,
                         "tref.csv",
                         sep = ""))
  
  params_local <- params_local %>%
    mutate(
      median_year_1 = sort(tref$median_year)[1],
      median_year_2 = sort(tref$median_year)[2],
      duration = median_year_2 - median_year_1,
      period = paste(median_year_1, "-", median_year_2)
    )
  
  if (exists("dcant_budget_global_all")) {
    dcant_budget_global_all <-
      bind_rows(dcant_budget_global_all, dcant_budget_global)
  }
  
  if (!exists("dcant_budget_global_all")) {
    dcant_budget_global_all <- dcant_budget_global
  }
  
  if (exists("dcant_budget_global_bias_all")) {
    dcant_budget_global_bias_all <-
      bind_rows(dcant_budget_global_bias_all,
                dcant_budget_global_bias)
  }

  if (!exists("dcant_budget_global_bias_all")) {
    dcant_budget_global_bias_all <- dcant_budget_global_bias
  }
  
    
  if (exists("lm_best_predictor_counts_all")) {
    lm_best_predictor_counts_all <-
      bind_rows(lm_best_predictor_counts_all, lm_best_predictor_counts)
  }
  
  if (!exists("lm_best_predictor_counts_all")) {
    lm_best_predictor_counts_all <- lm_best_predictor_counts
  }
    
  if (exists("lm_best_dcant_all")) {
    lm_best_dcant_all <-
      bind_rows(lm_best_dcant_all, lm_best_dcant)
  }
  
  if (!exists("lm_best_dcant_all")) {
    lm_best_dcant_all <- lm_best_dcant
  }
  
  if (exists("params_local_all")) {
    params_local_all <- bind_rows(params_local_all, params_local)
  }
  
  if (!exists("params_local_all")) {
    params_local_all <- params_local
  }
  
  
}

rm(
  dcant_budget_global,
  dcant_budget_global_bias,
  dcant_budget_global_mod_truth,
  lm_best_predictor_counts,
  lm_best_dcant,
  params_local,
  tref
)

1.2 Basins

# Version_IDs <- Version_IDs[1:length(Version_IDs)-1]

for (i_Version_IDs in Version_IDs) {
  # i_Version_IDs <- Version_IDs[1]
  
  # print(i_Version_IDs)
  
  path_version_data     <-
    paste(path_observations,
          i_Version_IDs,
          "/data/",
          sep = "")
  
  # load and join data files
  
  dcant_budget_basin_AIP <-
    read_csv(paste(path_version_data,
                   "dcant_budget_basin_AIP.csv",
                   sep = ""))
  
  dcant_budget_basin_AIP_mod_truth <-
    read_csv(paste(
      path_version_data,
      "dcant_budget_basin_AIP_mod_truth.csv",
      sep = ""
    ))
  
    
  dcant_budget_basin_AIP <- bind_rows(dcant_budget_basin_AIP,
                                      dcant_budget_basin_AIP_mod_truth)
  
  dcant_budget_basin_AIP_bias <-
    read_csv(paste(path_version_data,
                   "dcant_budget_basin_AIP_bias.csv",
                   sep = ""))
  
  dcant_slab_budget_bias <-
    read_csv(paste0(path_version_data,
                    "dcant_slab_budget_bias.csv"))

  dcant_slab_budget <-
    read_csv(paste0(path_version_data,
                    "dcant_slab_budget.csv"))

  dcant_budget_basin_AIP <- dcant_budget_basin_AIP %>%
    mutate(Version_ID = i_Version_IDs)
  
  dcant_budget_basin_AIP_bias <- dcant_budget_basin_AIP_bias %>%
    mutate(Version_ID = i_Version_IDs)
  
  dcant_slab_budget <- dcant_slab_budget %>%
    mutate(Version_ID = i_Version_IDs)
  
  dcant_slab_budget_bias <- dcant_slab_budget_bias %>%
    mutate(Version_ID = i_Version_IDs)
  
  if (exists("dcant_budget_basin_AIP_all")) {
    dcant_budget_basin_AIP_all <-
      bind_rows(dcant_budget_basin_AIP_all, dcant_budget_basin_AIP)
  }
  
  if (!exists("dcant_budget_basin_AIP_all")) {
    dcant_budget_basin_AIP_all <- dcant_budget_basin_AIP
  }
  
  if (exists("dcant_budget_basin_AIP_bias_all")) {
    dcant_budget_basin_AIP_bias_all <-
      bind_rows(dcant_budget_basin_AIP_bias_all,
                dcant_budget_basin_AIP_bias)
  }
  
  if (!exists("dcant_budget_basin_AIP_bias_all")) {
    dcant_budget_basin_AIP_bias_all <- dcant_budget_basin_AIP_bias
  }
  
  if (exists("dcant_slab_budget_all")) {
    dcant_slab_budget_all <-
      bind_rows(dcant_slab_budget_all, dcant_slab_budget)
  }
  
  if (!exists("dcant_slab_budget_all")) {
    dcant_slab_budget_all <- dcant_slab_budget
  }
  
  if (exists("dcant_slab_budget_bias_all")) {
    dcant_slab_budget_bias_all <-
      bind_rows(dcant_slab_budget_bias_all,
                dcant_slab_budget_bias)
  }
  
  if (!exists("dcant_slab_budget_bias_all")) {
    dcant_slab_budget_bias_all <- dcant_slab_budget_bias
  }
  
}

rm(
  dcant_budget_basin_AIP,
  dcant_budget_basin_AIP_bias,
  dcant_budget_basin_AIP_mod_truth,
  dcant_slab_budget,
  dcant_slab_budget_bias
)

1.3 Basins hemisphere

# Version_IDs <- Version_IDs[1:length(Version_IDs)-1]

for (i_Version_IDs in Version_IDs) {
  # i_Version_IDs <- Version_IDs[1]
  
  # print(i_Version_IDs)
  
  path_version_data     <-
    paste(path_observations,
          i_Version_IDs,
          "/data/",
          sep = "")
  
  # load and join data files
  
  dcant_budget_basin_MLR <-
    read_csv(paste(path_version_data,
                   "dcant_budget_basin_MLR.csv",
                   sep = ""))
  
  dcant_budget_basin_MLR_mod_truth <-
    read_csv(paste(
      path_version_data,
      "dcant_budget_basin_MLR_mod_truth.csv",
      sep = ""
    ))
  
    
  dcant_budget_basin_MLR <- bind_rows(dcant_budget_basin_MLR,
                                      dcant_budget_basin_MLR_mod_truth)
  

  dcant_budget_basin_MLR <- dcant_budget_basin_MLR %>%
    mutate(Version_ID = i_Version_IDs)

  if (exists("dcant_budget_basin_MLR_all")) {
    dcant_budget_basin_MLR_all <-
      bind_rows(dcant_budget_basin_MLR_all, dcant_budget_basin_MLR)
  }
  
  if (!exists("dcant_budget_basin_MLR_all")) {
    dcant_budget_basin_MLR_all <- dcant_budget_basin_MLR
  }

  
}

rm(
  dcant_budget_basin_MLR,
  dcant_budget_basin_MLR_mod_truth
)

1.4 Steady state

for (i_Version_IDs in Version_IDs) {
  # i_Version_IDs <- Version_IDs[1]
  
  # print(i_Version_IDs)
  
  path_version_data     <-
    paste(path_observations,
          i_Version_IDs,
          "/data/",
          sep = "")
  
  # load and join data files
  
  dcant_obs_budget <-
    read_csv(paste0(path_version_data,
                    "anom_dcant_obs_budget.csv"))
  
  dcant_obs_budget <- dcant_obs_budget %>%
    mutate(Version_ID = i_Version_IDs)
  
  if (exists("dcant_obs_budget_all")) {
    dcant_obs_budget_all <-
      bind_rows(dcant_obs_budget_all, dcant_obs_budget)
  }
  
  if (!exists("dcant_obs_budget_all")) {
    dcant_obs_budget_all <- dcant_obs_budget
  }
  
}


rm(dcant_obs_budget)

1.5 Atm CO2

co2_atm <-
  read_csv(paste(path_preprocessing,
                 "co2_atm.csv",
                 sep = ""))

all_predictors <- c("saltempaouoxygenphosphatenitratesilicate")

params_local_all <- params_local_all %>%
  mutate(MLR_predictors = str_remove_all(all_predictors,
                                         MLR_predictors))

dcant_budget_global_all <- dcant_budget_global_all %>%
  filter(estimate == "dcant", 
         method == "total") %>% 
  select(-c(estimate, method)) %>% 
  rename(dcant = value)

dcant_budget_global_all_depth <- dcant_budget_global_all

dcant_budget_global_all <- dcant_budget_global_all %>%
  filter(inv_depth == params_global$inventory_depth_standard)

dcant_budget_global_bias_all <- dcant_budget_global_bias_all %>%
  filter(estimate == "dcant") %>%
  select(-c(estimate))

dcant_budget_global_bias_all_depth <- dcant_budget_global_bias_all

dcant_budget_global_bias_all <- dcant_budget_global_bias_all %>%
  filter(inv_depth == params_global$inventory_depth_standard)

dcant_budget_basin_AIP_all <- dcant_budget_basin_AIP_all %>%
  filter(estimate == "dcant", 
         method == "total") %>% 
  select(-c(estimate, method)) %>% 
  rename(dcant = value)

dcant_budget_basin_AIP_all_depth <- dcant_budget_basin_AIP_all

dcant_budget_basin_AIP_all <- dcant_budget_basin_AIP_all %>%
  filter(inv_depth == params_global$inventory_depth_standard)

dcant_budget_basin_AIP_bias_all <- dcant_budget_basin_AIP_bias_all %>%
  filter(estimate == "dcant") %>% 
  select(-c(estimate))

dcant_budget_basin_AIP_bias_all_depth <- dcant_budget_basin_AIP_bias_all

dcant_budget_basin_AIP_bias_all <- dcant_budget_basin_AIP_bias_all %>%
  filter(inv_depth == params_global$inventory_depth_standard)

dcant_budget_basin_MLR_all <- dcant_budget_basin_MLR_all %>%
  filter(estimate == "dcant", 
         method == "total") %>% 
  select(-c(estimate, method)) %>% 
  rename(dcant = value)

# dcant_budget_basin_MLR_all_depth <- dcant_budget_basin_MLR_all

dcant_budget_basin_MLR_all <- dcant_budget_basin_MLR_all %>%
  filter(inv_depth == params_global$inventory_depth_standard)

# dcant_budget_basin_MLR_bias_all <- dcant_budget_basin_MLR_bias_all %>%
#   filter(estimate == "dcant") %>% 
#   select(-c(estimate))
# 
# dcant_budget_basin_MLR_bias_all_depth <- dcant_budget_basin_MLR_bias_all
# 
# dcant_budget_basin_MLR_bias_all <- dcant_budget_basin_MLR_bias_all %>%
#   filter(inv_depth == params_global$inventory_depth_standard)

2 Bias thresholds

global_bias_rel_max <- 10
global_bias_rel_max

[1] 10

regional_bias_rel_max <- 20
regional_bias_rel_max

[1] 20

3 Individual cases

3.1 Global

3.1.1 Absoulte values

legend_title = expression(atop(Delta * C[ant],
                               (mu * mol ~ kg ^ {
                                 -1
                               })))

dcant_budget_global_all %>%
  ggplot(aes(period, dcant, col = MLR_basins)) +
  geom_jitter(width = 0.05, height = 0) +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(. ~ data_source) +
  ylim(0,NA) +
  theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank())

Past versions of cases_absolute_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.1.2 Biases

dcant_budget_global_bias_all %>%
  ggplot(aes(period, dcant_bias, col=MLR_basins)) +
  geom_hline(yintercept = 0) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(atop(Delta * C[ant] ~ bias,
                               (PgC)))) +
  geom_point() +
  theme(axis.text.x = element_blank(),
        axis.title.x = element_blank())

Past versions of cases_bias_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

p_global_bias <-
  dcant_budget_global_bias_all %>%
  ggplot() +
  geom_hline(yintercept = global_bias_rel_max * c(-1, 1),
             linetype = 2) +
  geom_hline(yintercept = 0) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(Delta * C[ant] ~ bias ~ ("%")),
       title = "Model-based assesment") +
  theme(axis.title.x = element_blank()) +
  geom_point(aes(period, dcant_bias_rel, col = MLR_basins),
  alpha = 0.7) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1),
        axis.title.x = element_blank())

p_global_bias

Past versions of cases_bias_global-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all %>%
  group_by(period) %>%
  summarise(
    dcant_bias_sd = sd(dcant_bias),
    dcant_bias = mean(dcant_bias),
    dcant_bias_rel_sd = sd(dcant_bias_rel),
    dcant_bias_rel = mean(dcant_bias_rel)
  ) %>%
  ungroup() %>%
  kable() %>%
  kable_styling() %>%
  scroll_box(height = "300px")

period	dcant_bias_sd	dcant_bias	dcant_bias_rel_sd	dcant_bias_rel
1994 - 2004	1.3065036	0.9881667	7.406483	5.601852
1994 - 2014	1.6884054	1.1473333	4.389117	2.982566
2004 - 2014	0.9859429	0.2083333	4.733738	1.000256

3.2 Basins

3.2.1 Absoulte values

dcant_budget_basin_AIP_all %>%
  ggplot(aes(period, dcant, col = MLR_basins)) +
  geom_jitter(width = 0.05, height = 0) +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(basin_AIP ~ data_source) +
  ylim(0,NA) +
  theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank())

Past versions of cases_absolute-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.2.2 Biases

dcant_budget_basin_AIP_bias_all %>%
  ggplot(aes(period, dcant_bias, col=MLR_basins)) +
  geom_hline(yintercept = 0) +
  geom_point() +
  facet_grid(basin_AIP ~ .)

Past versions of cases_bias-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_basin_AIP_bias_all %>%
  ggplot() +
  geom_tile(aes(y = 0, height = regional_bias_rel_max * 2,
                x = "2004 - 2014", width = Inf,
                fill = "bias\nthreshold"), alpha = 0.5) +
  geom_hline(yintercept = 0) +
  scale_fill_manual(values = "grey70", name = "") +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(Delta ~ C[ant] ~ bias)) +
  theme(axis.title.x = element_blank()) +
  geom_jitter(aes(period, dcant_bias_rel, col = MLR_basins),
              width = 0.05, height = 0) +
  facet_grid(. ~ basin_AIP)

Past versions of cases_bias-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

p_regional_bias <- 
  dcant_budget_basin_AIP_bias_all %>%
  ggplot() +
  geom_hline(yintercept = regional_bias_rel_max * c(-1,1),
             linetype = 2) +
  geom_hline(yintercept = 0) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(Delta * C[ant] ~ bias ~ ("%")),
       title = "Model-based assesment") +
  theme(axis.title.x = element_blank()) +
  geom_point(aes(period, dcant_bias_rel, col = MLR_basins),
             alpha = 0.7) +
    theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank()) +
  facet_grid(. ~ basin_AIP) +
  theme(
  strip.background = element_blank(),
  strip.text.x = element_blank()
)

p_regional_bias

Past versions of cases_bias-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.3 Slab budgets

3.3.1 Absolute values

dcant_slab_budget_all %>%
  filter(data_source == "obs",
         period != "1994 - 2014") %>% 
  ggplot(aes(MLR_basins, dcant, fill = gamma_slab)) +
  geom_hline(yintercept = 0, col = "red") +
  geom_col() +
  scale_fill_scico_d(direction = -1) +
  facet_grid(basin_AIP ~ period)

Past versions of slab_budgets-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_slab_budget_all %>%
  filter(data_source == "obs",
         period != "1994 - 2014") %>%
  group_by(basin_AIP) %>%
  group_split() %>%
  map(
    ~ ggplot(data = .x,
             aes(MLR_basins, dcant, fill = gamma_slab)) +
      geom_hline(yintercept = 0) +
      geom_col() +
      scale_fill_scico_d(direction = -1) +
      labs(title = paste("data_source:", unique(.x$basin_AIP))) +
      facet_grid(gamma_slab ~ period)
  )

[[1]]

Past versions of slab_budgets_individual-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Past versions of slab_budgets_individual-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[3]]

Past versions of slab_budgets_individual-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.3.2 Bias

dcant_slab_budget_bias_all %>%
  filter(period != "1994 - 2014") %>%
  group_by(basin_AIP) %>%
  group_split() %>%
  # head(1) %>% 
  map(
    ~ ggplot(data = .x,
             aes(gamma_slab, dcant_bias, fill = gamma_slab)) +
      geom_col() +
      coord_flip() +
      scale_x_discrete(limits = rev) +
      scale_fill_scico_d(direction = -1) +
      facet_grid(period ~ MLR_basins) +
      labs(title = paste("data_source:", unique(.x$basin_AIP)))
    )

[[1]]

Warning: Removed 70 rows containing missing values (position_stack).

Past versions of slab_budgets_bias-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Warning: Removed 60 rows containing missing values (position_stack).

Past versions of slab_budgets_bias-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[3]]

Warning: Removed 96 rows containing missing values (position_stack).

Past versions of slab_budgets_bias-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.3.3 Spread

dcant_slab_budget_all %>%
  filter(period != "1994 - 2014",
         data_source != "mod_truth") %>%
  group_by(data_source, basin_AIP, gamma_slab, period) %>%
  summarise(dcant_range = max(dcant) - min(dcant)) %>%
  ungroup() %>%
  group_split(basin_AIP) %>%
  # head(1) %>%
  map(
    ~ ggplot(data = .x,
             aes(gamma_slab, dcant_range, fill = gamma_slab)) +
      geom_col() +
      coord_flip() +
      scale_x_discrete(limits = rev) +
      scale_fill_scico_d(direction = -1) +
      facet_grid(period ~ data_source) +
      labs(title = paste("data_source:", unique(.x$basin_AIP)))
  )

`summarise()` has grouped output by 'data_source', 'basin_AIP', 'gamma_slab'.
You can override using the `.groups` argument.

[[1]]

Past versions of slab_budgets_spread-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Past versions of slab_budgets_spread-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[3]]

Past versions of slab_budgets_spread-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.4 Basins hemisphere

3.4.1 Absoulte values

dcant_budget_basin_MLR_all %>%
  ggplot(aes(period, dcant, col = MLR_basins)) +
  geom_jitter(width = 0.05, height = 0) +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(basin ~ data_source) +
  ylim(0,NA) +
  theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank())

Past versions of cases_absolute_basins_hemisphere-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

3.4.2 Biases

dcant_budget_basin_MLR_bias_all <-
  dcant_budget_basin_MLR_all %>%
  filter(data_source %in% c("mod", "mod_truth")) %>%
  pivot_wider(names_from = data_source,
              values_from = dcant) %>%
  mutate(dcant_bias = mod - mod_truth,
         dcant_bias_rel = 100*(mod - mod_truth)/mod_truth)
  
dcant_budget_basin_MLR_bias_all %>%   
  ggplot(aes(period, dcant_bias, col=MLR_basins)) +
  geom_hline(yintercept = 0) +
  geom_point() +
  facet_grid(basin ~ .)

Past versions of cases_bias_basins_hemisphere-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_basin_MLR_bias_all %>%
  ggplot() +
  geom_tile(aes(y = 0, height = regional_bias_rel_max * 2,
                x = "2004 - 2014", width = Inf,
                fill = "bias\nthreshold"), alpha = 0.5) +
  geom_hline(yintercept = 0) +
  scale_fill_manual(values = "grey70", name = "") +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(Delta ~ C[ant] ~ bias)) +
  theme(axis.title.x = element_blank()) +
  geom_jitter(aes(period, dcant_bias_rel, col = MLR_basins),
              width = 0.05, height = 0) +
  facet_grid(. ~ basin)

Past versions of cases_bias_basins_hemisphere-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

p_regional_bias <- 
  dcant_budget_basin_MLR_bias_all %>%
  ggplot() +
  geom_hline(yintercept = regional_bias_rel_max * c(-1,1),
             linetype = 2) +
  geom_hline(yintercept = 0) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = expression(Delta * C[ant] ~ bias ~ ("%")),
       title = "Model-based assesment") +
  theme(axis.title.x = element_blank()) +
  geom_point(aes(period, dcant_bias_rel, col = MLR_basins),
             alpha = 0.7) +
    theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank()) +
  facet_grid(. ~ basin) +
  theme(
  strip.background = element_blank(),
  strip.text.x = element_blank()
)

p_regional_bias

Past versions of cases_bias_basins_hemisphere-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_basin_MLR_bias_all %>%
  group_by(period, basin) %>%
  summarise(
    dcant_bias_sd = sd(dcant_bias),
    dcant_bias = mean(dcant_bias),
    dcant_bias_rel_sd = sd(dcant_bias_rel),
    dcant_bias_rel = mean(dcant_bias_rel)
  ) %>%
  ungroup() %>%
  kable() %>%
  kable_styling() %>%
  scroll_box(height = "300px")

`summarise()` has grouped output by 'period'. You can override using the
`.groups` argument.

period	basin	dcant_bias_sd	dcant_bias	dcant_bias_rel_sd	dcant_bias_rel
1994 - 2004	Indian	0.8988402	0.2878333	18.644270	5.9704072
1994 - 2004	N_Atlantic	0.2309416	0.1580000	11.837086	8.0984111
1994 - 2004	N_Pacific	0.1040801	0.6063333	3.832110	22.3244968
1994 - 2004	S_Atlantic	0.3200784	0.0238333	12.803135	0.9533333
1994 - 2004	S_Pacific	0.9098706	-0.0881667	16.098206	-1.5599198
1994 - 2014	Indian	1.2906108	0.5946667	12.352707	5.6916794
1994 - 2014	N_Atlantic	0.3528335	-0.2485000	8.213071	-5.7844507
1994 - 2014	N_Pacific	0.2336234	0.1365000	4.001771	2.3381295
1994 - 2014	S_Atlantic	0.4347148	0.4691667	8.219225	8.8706120
1994 - 2014	S_Pacific	1.5262131	0.1951667	12.115687	1.5493107
2004 - 2014	Indian	0.6824666	0.2503333	12.130583	4.4495793
2004 - 2014	N_Atlantic	0.1361094	-0.3148333	5.804239	-13.4257285
2004 - 2014	N_Pacific	0.1737189	-0.4923333	5.564348	-15.7698057
2004 - 2014	S_Atlantic	0.3080641	0.5073333	11.045682	18.1905103
2004 - 2014	S_Pacific	0.6768243	0.2586667	9.745490	3.7245020

4 Ensemble

4.1 Global

dcant_budget_global_all_in <- dcant_budget_global_all %>% 
  filter(data_source %in% c("mod", "obs"))

dcant_budget_global_ensemble <- dcant_budget_global_all_in %>% 
  group_by(data_source, period, tref2) %>% 
  summarise(dcant_mean = mean(dcant),
            dcant_sd = sd(dcant),
            dcant_range = max(dcant)- min(dcant)) %>% 
  ungroup()

`summarise()` has grouped output by 'data_source', 'period'. You can override
using the `.groups` argument.

4.1.1 Mean

legend_title = expression(Delta * C[ant]~(PgC))

ggplot() +
  geom_col(data = dcant_budget_global_ensemble,
           aes(x = period,
               y = dcant_mean),
           fill = "darkgrey") +
  geom_errorbar(
    data = dcant_budget_global_ensemble,
    aes(
      x = period,
      y = dcant_mean,
      ymax = dcant_mean + dcant_sd,
      ymin = dcant_mean - dcant_sd
    ),
    width = 0.1
  ) +
  geom_point(
    data = dcant_budget_global_all,
    aes(period, dcant, col = MLR_basins),
    alpha = 0.7,
    position = position_jitter(width = 0.2, height = 0)
  ) +
  scale_y_continuous(limits = c(0,70), expand = c(0,0)) +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(. ~ data_source) +
  labs(y = legend_title) +
  theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank())

Past versions of ensemble_mean_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

p_global_dcant <- ggplot() +
  geom_col(data = dcant_budget_global_ensemble %>% 
             filter(data_source == "obs"),
           aes(x = period,
               y = dcant_mean),
           fill = "darkgrey") +
    geom_point(
    data = dcant_budget_global_all %>% 
             filter(data_source == "obs"),
    aes(period, dcant, col = MLR_basins),
    alpha = 0.7,
    position = position_jitter(width = 0.1, height = 0)
  ) +
  geom_errorbar(
    data = dcant_budget_global_ensemble %>% 
             filter(data_source == "obs"),
    aes(
      x = period,
      y = dcant_mean,
      ymax = dcant_mean + dcant_sd,
      ymin = dcant_mean - dcant_sd
    ),
    width = 0.1
  ) +
  scale_y_continuous(limits = c(0,70), expand = c(0,0)) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = legend_title,
       title = "Observation-based results") +
  theme(axis.text.x = element_blank(),
        axis.title.x = element_blank())

p_global_dcant_bias <-
p_global_dcant / p_global_bias +
  plot_layout(guides = 'collect',
              heights = c(2,1))

p_global_dcant_bias

Past versions of ensemble_mean_global-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

# ggsave(plot = p_global_dcant_bias,
#        path = here::here("output/publication"),
#        filename = "Fig_global_dcant_budget.png",
#        height = 5,
#        width = 5)

rm(p_global_bias, p_global_dcant, p_global_dcant_bias)

4.1.2 Mean vs atm CO2

dcant_ensemble <- dcant_budget_global_ensemble %>% 
  filter(data_source == "obs",
         period != "1994 - 2014") %>% 
  select(year = tref2, dcant_mean, dcant_sd)

tcant_S04 <- bind_cols(year = 1994, dcant_mean = 118, dcant_sd = 19)

tcant_ensemble <- full_join(dcant_ensemble, tcant_S04)

Joining, by = c("year", "dcant_mean", "dcant_sd")

tcant_ensemble <- left_join(tcant_ensemble, co2_atm)

Joining, by = "year"

co2_atm_pi <- bind_cols(pCO2 = 280, dcant_mean = 0, year = 1750, dcant_sd = 0)

tcant_ensemble <- full_join(tcant_ensemble, co2_atm_pi)

Joining, by = c("year", "dcant_mean", "dcant_sd", "pCO2")

tcant_ensemble <- tcant_ensemble %>% 
  arrange(year) %>% 
  mutate(tcant = cumsum(dcant_mean),
         tcant_sd = cumsum(dcant_sd))

tcant_ensemble %>% 
  ggplot(aes(pCO2, tcant, ymin = tcant - tcant_sd, ymax = tcant + tcant_sd)) +
  geom_ribbon(fill = "grey80") +
  geom_point() +
  geom_line() +
  scale_x_continuous(breaks = seq(280, 400, 30),
                     sec.axis = dup_axis(labels =  c(1750, 1940, 1980, 2000, 2015),
                                         name = "Year")) +
  geom_text(aes(label = year), nudge_x = -5, nudge_y = 5) +
  labs(x = expression(Atmospheric~pCO[2]~(µatm)),
       y = expression(Total~oceanic~C[ant]~(PgC)))

Past versions of mean_tcant_over_atm_co2-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

# ggsave(path = "output/publication",
#        filename = "Fig_global_dcant_budget_vs_atm_pCO2.png",
#        height = 4,
#        width = 7)

4.1.3 Sum decades

dcant_budget_global_all_in_sum <-
  dcant_budget_global_all_in %>%
  filter(period != "1994 - 2014") %>%
  arrange(tref1) %>%
  group_by(data_source, MLR_basins) %>%
  mutate(dcant = dcant + lag(dcant)) %>% 
  ungroup() %>%
  drop_na() %>% 
  mutate(estimate = "sum")

dcant_budget_global_all_in_sum <-
  bind_rows(
    dcant_budget_global_all_in_sum,
    dcant_budget_global_all_in %>%
      filter(period == "1994 - 2014") %>%
      mutate(estimate = "direct")
  )

ggplot() +
  geom_point(
    data = dcant_budget_global_all_in_sum,
    aes(estimate, dcant, col = MLR_basins),
    alpha = 0.7,
    position = position_jitter(width = 0, height = 0)
  ) +
  scale_y_continuous(limits = c(0,70), expand = c(0,0)) +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(. ~ data_source) +
  theme(axis.text.x = element_text(angle = 45, hjust=1),
        axis.title.x = element_blank())

Past versions of summed_decades-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

4.1.4 Mean bias

dcant_budget_global_ensemble_bias <- full_join(
  dcant_budget_global_ensemble %>%
    filter(data_source == "mod") %>% 
    select(period, dcant_mean, dcant_sd),
  dcant_budget_global_all %>%
    filter(data_source == "mod_truth",
           MLR_basins == unique(dcant_budget_global_all$MLR_basins)[1]) %>% 
    select(period, dcant)
)

Joining, by = "period"

dcant_budget_global_ensemble_bias <- dcant_budget_global_ensemble_bias %>% 
  mutate(dcant_mean_bias = dcant_mean - dcant,
         dcant_mean_bias_rel = 100 * dcant_mean_bias / dcant)

dcant_budget_global_ensemble_bias %>%
  ggplot(aes(period, dcant_mean_bias)) +
  geom_hline(yintercept = 0) +
  geom_point()

Past versions of ensemble_mean_bias_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_ensemble_bias %>%
  ggplot(aes(period, dcant_mean_bias_rel)) +
  geom_hline(yintercept = 0) +
  geom_point()

Past versions of ensemble_mean_bias_global-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

4.1.5 Vertical patterns

4.1.5.1 Absoulte values

dcant_budget_global_all_depth %>%
  filter(data_source != "mod_truth") %>% 
  group_by(data_source) %>%
  group_split() %>%
  # head(1) %>%
  map(
    ~  ggplot(data = .x,
              aes(dcant, MLR_basins, fill=period)) +
      geom_vline(xintercept = 0) +
      geom_col(position = "dodge") +
      scale_fill_brewer(palette = "Dark2") +
      facet_grid(inv_depth ~ .) +
      labs(title = paste("data_source:", unique(.x$data_source)))
  )

[[1]]

Past versions of cases_absolute_depth_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Past versions of cases_absolute_depth_global-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

4.1.5.2 Biases

dcant_budget_global_bias_all_depth %>%
  ggplot(aes(dcant_bias, MLR_basins, fill = period)) +
  geom_vline(xintercept = 0) +
  geom_col(position = "dodge") +
  scale_fill_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ .)

Past versions of cases_bias_depth_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_depth %>%
  ggplot(aes(dcant_bias_rel, MLR_basins, fill = period)) +
  geom_vline(xintercept = 0) +
  geom_col(position = "dodge") +
  scale_fill_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ .)

Past versions of cases_bias_rel_depth_global-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

rm(dcant_budget_global_all,
   dcant_budget_global_all_depth,
   dcant_budget_global_bias_all,
   dcant_budget_global_bias_all_depth,
   dcant_budget_global_ensemble,
   dcant_budget_global_ensemble_bias)

4.2 Basins

dcant_budget_basin_AIP_ensemble <- dcant_budget_basin_AIP_all %>% 
  filter(data_source %in% c("mod", "obs")) %>% 
  group_by(basin_AIP, data_source, period) %>% 
  summarise(dcant_mean = mean(dcant),
            dcant_sd = sd(dcant),
            dcant_range = max(dcant)- min(dcant)) %>% 
  ungroup()

`summarise()` has grouped output by 'basin_AIP', 'data_source'. You can override
using the `.groups` argument.

4.2.1 Mean

dcant_budget_basin_AIP_ensemble %>%
  ggplot(aes(period, dcant_mean, col=basin_AIP)) +
  geom_pointrange(aes(ymax = dcant_mean + dcant_sd,
                      ymin = dcant_mean - dcant_sd),
                  shape = 21) +
  facet_grid(. ~ data_source)

Past versions of ensemble_mean-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

p_regional_dcant <- ggplot() +
  geom_col(
    data = dcant_budget_basin_AIP_ensemble %>%
      filter(data_source == "obs"),
    aes(x = period,
        y = dcant_mean),
    fill = "darkgrey"
  ) +
  geom_point(
    data = dcant_budget_basin_AIP_all %>%
      filter(data_source == "obs"),
    aes(period, dcant, col = MLR_basins),
    position = position_jitter(width = 0.1, height = 0),
    alpha = 0.7
  ) +
  geom_errorbar(
    data = dcant_budget_basin_AIP_ensemble %>%
      filter(data_source == "obs"),
    aes(
      x = period,
      y = dcant_mean,
      ymax = dcant_mean + dcant_sd,
      ymin = dcant_mean - dcant_sd
    ),
    width = 0.1
  ) +
  scale_y_continuous(limits = c(0, 35), expand = c(0, 0)) +
  scale_color_brewer(palette = "Dark2") +
  labs(y = legend_title,
       title = "Observation-based results") +
  theme(axis.text.x = element_blank(),
        axis.title.x = element_blank()) +
  facet_grid(. ~ basin_AIP)

p_regional_dcant_bias <-
p_regional_dcant / p_regional_bias +
  plot_layout(guides = 'collect',
              heights = c(2,1))

p_regional_dcant_bias

Past versions of ensemble_mean-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

# ggsave(plot = p_regional_dcant_bias,
#        path = "output/publication",
#        filename = "Fig_regional_dcant_budget.png",
#        height = 5,
#        width = 10)

rm(p_regional_bias, p_regional_dcant, p_regional_dcant_bias)

4.2.2 Mean bias

dcant_budget_basin_AIP_ensemble_bias <- full_join(
  dcant_budget_basin_AIP_ensemble %>%
    filter(data_source == "mod") %>% 
    select(basin_AIP, period, dcant_mean, dcant_sd),
  dcant_budget_basin_AIP_all %>%
    filter(data_source == "mod_truth",
           MLR_basins == unique(dcant_budget_basin_AIP_all$MLR_basins)[1]) %>% 
    select(basin_AIP, period, dcant)
)

Joining, by = c("basin_AIP", "period")

dcant_budget_basin_AIP_ensemble_bias <- dcant_budget_basin_AIP_ensemble_bias %>% 
  mutate(dcant_mean_bias = dcant_mean - dcant,
         dcant_mean_bias_rel = 100 * dcant_mean_bias / dcant)


dcant_budget_basin_AIP_ensemble_bias %>%
  ggplot(aes(period, dcant_mean_bias, col = basin_AIP)) +
  geom_hline(yintercept = 0) +
  geom_point()

Past versions of ensemble_mean_bias-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_basin_AIP_ensemble_bias %>%
  ggplot(aes(period, dcant_mean_bias_rel, col = basin_AIP)) +
  geom_hline(yintercept = 0) +
  geom_point()

Past versions of ensemble_mean_bias-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

4.2.3 Vertical patterns

4.2.3.1 Absoulte values

dcant_budget_basin_AIP_all_depth %>%
  filter(data_source != "mod_truth") %>%
  group_by(data_source) %>%
  group_split() %>%
  # head(1) %>%
  map(
    ~  ggplot(data = .x,
              aes(dcant, MLR_basins, fill = basin_AIP)) +
      geom_vline(xintercept = 0) +
      geom_col() +
      scale_fill_brewer(palette = "Dark2") +
      facet_grid(inv_depth ~ period) +
      labs(title = paste("data_source:", unique(.x$data_source)))
  )

[[1]]

Past versions of cases_absolute_depth-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Past versions of cases_absolute_depth-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

4.2.3.2 Biases

dcant_budget_basin_AIP_bias_all_depth %>%
  ggplot(aes(dcant_bias, MLR_basins, fill = basin_AIP)) +
  geom_vline(xintercept = 0) +
  geom_col() +
  scale_fill_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of cases_bias_depth-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_basin_AIP_bias_all_depth %>%
  ggplot(aes(dcant_bias_rel, MLR_basins, fill = basin_AIP)) +
  geom_vline(xintercept = 0) +
  geom_col(position = "dodge") +
  scale_fill_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of cases_bias_rel_depth-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

5 Steady state

dcant_obs_budget_all %>%
  group_by(inv_depth) %>%
  group_split() %>%
  # head(1) %>% 
  map(
    ~ ggplot(data = .x,
             aes(estimate, dcant_pos, fill = basin_AIP)) +
      scale_fill_brewer(palette = "Dark2") +
      geom_col() +
      facet_grid(MLR_basins ~ period) +
      labs(title = paste("inventory depth:",unique(.x$inv_depth)))
  )

[[1]]

Past versions of steady_state_comparison-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Past versions of steady_state_comparison-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[3]]

Past versions of steady_state_comparison-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[4]]

Past versions of steady_state_comparison-4.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[5]]

Past versions of steady_state_comparison-5.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

6 Predictor analysis

lm_best_predictor_counts_all <-
  full_join(lm_best_predictor_counts_all,
            params_local_all)

Joining, by = "Version_ID"

lm_best_predictor_counts_all <- lm_best_predictor_counts_all %>% 
  mutate(n_predictors_total = rowSums(across(aou:temp), na.rm = TRUE)/10)

lm_best_predictor_counts_all %>%
  ggplot(aes(x = MLR_basins, y = n_predictors_total)) +
  # ggdist::stat_halfeye(
  #   adjust = .5,
  #   width = .6,
  #   .width = 0,
  #   justification = -.2,
  #   point_colour = NA
  # ) +
  geom_boxplot(width = 0.5,
               outlier.shape = NA) +
  gghalves::geom_half_point(
    side = "l",
    range_scale = .4,
    alpha = .5,
    aes(col = gamma_slab)
  ) +
  scale_color_viridis_d() +
  facet_grid(basin ~ data_source)

Past versions of predictor_analysis-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

lm_best_predictor_counts_all %>%
  pivot_longer(aou:temp,
               names_to = "predictor",
               values_to = "count") %>%
  group_split(predictor) %>%
  # head(1) %>%
  map(
    ~ ggplot(data = .x,
             aes(MLR_basins, count, color = gamma_slab)) +
      geom_jitter(alpha = 0.5) +
      scale_color_viridis_d() +
      labs(title = paste0("predictor:", unique(.x$predictor))) +
      coord_cartesian(ylim = c(0, 10)) +
      facet_grid(basin ~ data_source)
  )

[[1]]

Warning: Removed 2 rows containing missing values (geom_point).

Past versions of predictor_analysis-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[2]]

Warning: Removed 42 rows containing missing values (geom_point).

Past versions of predictor_analysis-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[3]]

Warning: Removed 1 rows containing missing values (geom_point).

Past versions of predictor_analysis-4.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[4]]

Warning: Removed 5 rows containing missing values (geom_point).

Past versions of predictor_analysis-5.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[5]]

Warning: Removed 3 rows containing missing values (geom_point).

Past versions of predictor_analysis-6.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[6]]

Warning: Removed 4 rows containing missing values (geom_point).

Past versions of predictor_analysis-7.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

[[7]]

Past versions of predictor_analysis-8.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

lm_best_dcant_all <-
  full_join(lm_best_dcant_all,
            params_local_all)

Joining, by = "Version_ID"

lm_best_dcant_all %>%
  count(basin, data_source, gamma_slab, MLR_basins, period) %>%
  ggplot(aes(MLR_basins, n)) +
  geom_jitter(height = 0, alpha = 0.3) +
  facet_grid(basin ~ data_source)

Past versions of predictor_analysis-9.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

7 Drift and bias

dcant_budget_global_all_dissic %>%
  filter(estimate == "dcant") %>%
  ggplot(aes(inv_depth, value, col = !!sym(config))) +
  geom_hline(yintercept = 0) +
  scale_color_brewer(palette = "Dark2") +
  geom_point() +
  geom_path() +
  labs(y = "DIC change (PgC)") +
  facet_grid(data_source ~ period, scales = "free_y")

Past versions of drift_bias_plots-1.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition <-
  dcant_budget_global_bias_all_decomposition %>%
  filter(estimate == "dcant") %>%
  select(inv_depth, dcant_bias, contribution, !!sym(config), period) %>%
  pivot_wider(names_from = contribution,
              values_from = dcant_bias)

dcant_budget_global_bias_all_decomposition <-
  full_join(
    dcant_budget_global_bias_all_decomposition,
    dcant_budget_global_bias_all_depth %>%
      select(inv_depth, !!sym(config), period, mod_truth)
  )

Joining, by = c("inv_depth", "MLR_basins", "period")

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(`dcant offset`, `delta C* - mod_truth`, col = !!sym(config))) +
  geom_vline(xintercept = 0, col = "grey50") +
  geom_hline(yintercept = 0, col = "grey50") +
  geom_abline(intercept = 0, slope = 1) +
  geom_point() +
  coord_fixed() +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of drift_bias_plots-2.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(`dcant offset`, `C* prediction error`, col = !!sym(config))) +
  geom_vline(xintercept = 0, col = "grey50") +
  geom_hline(yintercept = 0, col = "grey50") +
  geom_abline(intercept = 0, slope = 1) +
  geom_point() +
  coord_fixed() +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of drift_bias_plots-3.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(
    `dcant offset`,
    `C* prediction error` + `delta C* - mod_truth`,
    col = !!sym(config)
  )) +
  geom_vline(xintercept = 0, col = "grey50") +
  geom_hline(yintercept = 0, col = "grey50") +
  geom_abline(intercept = 0, slope = 1) +
  geom_point() +
  coord_fixed() +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of drift_bias_plots-4.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(`dcant offset`, `C* drift`, col = !!sym(config))) +
  geom_vline(xintercept = 0, col = "grey50") +
  geom_hline(yintercept = 0, col = "grey50") +
  geom_abline(intercept = 0, slope = 1) +
  geom_point() +
  coord_fixed() +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of drift_bias_plots-5.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(
    `dcant offset` - `C* drift`,
    `C* prediction error`,
    col = !!sym(config)
  )) +
  geom_vline(xintercept = 0, col = "grey50") +
  geom_hline(yintercept = 0, col = "grey50") +
  geom_abline(intercept = 0, slope = 1) +
  geom_point() +
  coord_fixed() +
  scale_color_brewer(palette = "Dark2") +
  facet_grid(inv_depth ~ period)

Past versions of drift_bias_plots-6.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(
    x = period,
    fill = !!sym(config),
    col = !!sym(config)
  )) +
  geom_hline(yintercept = 0) +
  geom_point(
    aes(y = `dcant offset`, shape = "dcant offset"),
    position = position_nudge(x = -0.05),
    alpha = 0.5
  ) +
  geom_point(
    aes(y = `dcant offset` - `C* drift`, shape = "dcant offset - C* drift"),
    position = position_nudge(x = 0.05),
    alpha = 0.5
  ) +
  scale_color_brewer(palette = "Dark2") +
  scale_fill_brewer(palette = "Dark2") +
  scale_shape_manual(values = c(21,23)) +
  facet_grid(inv_depth ~ .)

Past versions of drift_bias_plots-7.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition <-
  dcant_budget_global_bias_all_decomposition %>%
  mutate(
    `dcant offset rel` = 100 * `dcant offset` / mod_truth,
    `dcant offset rel corr` = 100 * (`dcant offset` - `C* drift`) / mod_truth,
    `C* prediction error rel` = 100 * (`C* prediction error`) / mod_truth
  )

dcant_budget_global_bias_all_decomposition %>%
  ggplot(aes(
    x = period,
    fill = !!sym(config),
    col = !!sym(config)
  )) +
  geom_hline(yintercept = 0) +
  geom_point(
    aes(y = `dcant offset rel`, shape = "dcant offset"),
    position = position_nudge(x = -0.05),
    alpha = 0.5
  ) +
  geom_point(
    aes(y = `dcant offset rel corr`, shape = "dcant offset - C* drift"),
    position = position_nudge(x = 0.05),
    alpha = 0.5
  ) +
  scale_color_brewer(palette = "Dark2") +
  scale_fill_brewer(palette = "Dark2") +
  scale_shape_manual(values = c(21,23)) +
  facet_grid(inv_depth ~ .)

Past versions of drift_bias_plots-8.png

Version	Author	Date
08c00b4	jens-daniel-mueller	2022-07-16

dcant_budget_global_bias_all_decomposition <-
  dcant_budget_global_bias_all_decomposition %>%
  pivot_longer(-c(inv_depth:period),
               names_to = "estimate",
               values_to = "value")


dcant_budget_global_bias_all_decomposition %>%
  group_by(inv_depth, estimate) %>%
  summarise(mean = mean(value),
            sd = sd(value)) %>%
  ungroup() %>%
  kable() %>%
  kable_styling() %>%
  scroll_box(height = "300px")

`summarise()` has grouped output by 'inv_depth'. You can override using the
`.groups` argument.

inv_depth	estimate	mean	sd
100	C* drift	0.2033333	0.0740032
100	C* prediction error	0.0305556	0.6095975
100	C* prediction error rel	1.4823901	17.0891603
100	dcant offset	-0.3639444	0.4647815
100	dcant offset rel	-7.0942168	12.0879048
100	dcant offset rel corr	-11.3862836	11.7830024
100	delta C* - mod_truth	-0.3946667	0.2164184
100	mod_truth	4.7563333	1.7425592
500	C* drift	1.3446667	0.4893907
500	C* prediction error	-1.0722778	1.0441114
500	C* prediction error rel	-6.0202297	6.6101724
500	dcant offset	-0.6951111	1.0088539
500	dcant offset rel	-3.7844030	6.7796786
500	dcant offset rel corr	-11.7507685	6.2656036
500	delta C* - mod_truth	0.3773333	0.1374833
500	mod_truth	16.9600000	6.2242462
1000	C* drift	3.1486667	1.1458415
1000	C* prediction error	-2.7085556	1.5370498
1000	C* prediction error rel	-11.7140573	5.4392141
1000	dcant offset	-0.6220000	1.2112693
1000	dcant offset rel	-2.5066370	5.8292086
1000	dcant offset rel corr	-16.4157066	5.1216702
1000	delta C* - mod_truth	2.0866667	0.7598902
1000	mod_truth	22.7516667	8.3557301
3000	C* drift	3.9900000	1.4521475
3000	C* prediction error	-1.8372778	1.4638905
3000	C* prediction error rel	-7.0851970	5.3558385
3000	dcant offset	0.7812778	1.3433744
3000	dcant offset rel	3.1948912	5.6702155
3000	dcant offset rel corr	-12.4492534	5.3660804
3000	delta C* - mod_truth	2.6026667	0.9469936
3000	mod_truth	25.6453333	9.4254881
10000	C* drift	3.3760000	1.2289476
10000	C* prediction error	-0.6993333	1.9501102
10000	C* prediction error rel	-2.5482904	8.0007264
10000	dcant offset	1.0708889	1.9652651
10000	dcant offset rel	4.3045292	8.1596768
10000	dcant offset rel corr	-8.7343469	7.9571634
10000	delta C* - mod_truth	1.7546667	0.6384472
10000	mod_truth	26.0420000	9.5725748

dcant_budget_global_bias_all_decomposition %>%
  group_by(inv_depth, estimate, period) %>%
  summarise(mean = mean(value),
            sd = sd(value)) %>%
  ungroup() %>%
  kable() %>%
  kable_styling() %>%
  scroll_box(height = "300px")

`summarise()` has grouped output by 'inv_depth', 'estimate'. You can override
using the `.groups` argument.

inv_depth	estimate	period	mean	sd
100	C* drift	1994 - 2004	0.1550000	0.0000000
100	C* drift	1994 - 2014	0.3050000	0.0000000
100	C* drift	2004 - 2014	0.1500000	0.0000000
100	C* prediction error	1994 - 2004	0.7271667	0.0824607
100	C* prediction error	1994 - 2014	0.0663333	0.1301717
100	C* prediction error	2004 - 2014	-0.7018333	0.1104435
100	C* prediction error rel	1994 - 2004	21.9092096	2.4845043
100	C* prediction error rel	1994 - 2014	0.9298196	1.8246661
100	C* prediction error rel	2004 - 2014	-18.3918588	2.8942217
100	dcant offset	1994 - 2004	0.2376667	0.0824710
100	dcant offset	1994 - 2014	-0.5248333	0.1301575
100	dcant offset	2004 - 2014	-0.8046667	0.1107387
100	dcant offset rel	1994 - 2004	7.1607914	2.4848149
100	dcant offset rel	1994 - 2014	-7.3567891	1.8244669
100	dcant offset rel	2004 - 2014	-21.0866527	2.9019584
100	dcant offset rel corr	1994 - 2004	2.4907101	2.4848149
100	dcant offset rel corr	1994 - 2014	-11.6320905	1.8244669
100	dcant offset rel corr	2004 - 2014	-25.0174703	2.9019584
100	delta C* - mod_truth	1994 - 2004	-0.4900000	0.0000000
100	delta C* - mod_truth	1994 - 2014	-0.5910000	0.0000000
100	delta C* - mod_truth	2004 - 2014	-0.1030000	0.0000000
100	mod_truth	1994 - 2004	3.3190000	0.0000000
100	mod_truth	1994 - 2014	7.1340000	0.0000000
100	mod_truth	2004 - 2014	3.8160000	0.0000000
500	C* drift	1994 - 2004	1.0250000	0.0000000
500	C* drift	1994 - 2014	2.0170000	0.0000000
500	C* drift	2004 - 2014	0.9920000	0.0000000
500	C* prediction error	1994 - 2004	0.0716667	0.5245202
500	C* prediction error	1994 - 2014	-1.5845000	0.8988839
500	C* prediction error	2004 - 2014	-1.7040000	0.5093086
500	C* prediction error rel	1994 - 2004	0.6101887	4.4659023
500	C* prediction error rel	1994 - 2014	-6.2283805	3.5333487
500	C* prediction error rel	2004 - 2014	-12.4424973	3.7189379
500	dcant offset	1994 - 2004	0.3631667	0.5249501
500	dcant offset	1994 - 2014	-1.0185000	0.8988839
500	dcant offset	2004 - 2014	-1.4300000	0.5093086
500	dcant offset rel	1994 - 2004	3.0920959	4.4695620
500	dcant offset rel	1994 - 2014	-4.0035377	3.5333487
500	dcant offset rel	2004 - 2014	-10.4417671	3.7189379
500	dcant offset rel corr	1994 - 2004	-5.6350220	4.4695620
500	dcant offset rel corr	1994 - 2014	-11.9319969	3.5333487
500	dcant offset rel corr	2004 - 2014	-17.6852866	3.7189379
500	delta C* - mod_truth	1994 - 2004	0.2920000	0.0000000
500	delta C* - mod_truth	1994 - 2014	0.5660000	0.0000000
500	delta C* - mod_truth	2004 - 2014	0.2740000	0.0000000
500	mod_truth	1994 - 2004	11.7450000	0.0000000
500	mod_truth	1994 - 2014	25.4400000	0.0000000
500	mod_truth	2004 - 2014	13.6950000	0.0000000
1000	C* drift	1994 - 2004	2.3950000	0.0000000
1000	C* drift	1994 - 2014	4.7230000	0.0000000
1000	C* drift	2004 - 2014	2.3280000	0.0000000
1000	C* prediction error	1994 - 2004	-1.1805000	0.8796601
1000	C* prediction error	1994 - 2014	-4.0320000	1.3833108
1000	C* prediction error	2004 - 2014	-2.9131667	0.6254878
1000	C* prediction error rel	1994 - 2004	-7.5191083	5.6029306
1000	C* prediction error rel	1994 - 2014	-11.8146922	4.0534205
1000	C* prediction error rel	2004 - 2014	-15.8083713	3.3942250
1000	dcant offset	1994 - 2004	0.3766667	0.8793874
1000	dcant offset	1994 - 2014	-0.9016667	1.3829890
1000	dcant offset	2004 - 2014	-1.3410000	0.6256171
1000	dcant offset rel	1994 - 2004	2.3991507	5.6011939
1000	dcant offset rel	1994 - 2014	-2.6420918	4.0524776
1000	dcant offset rel	2004 - 2014	-7.2769698	3.3949269
1000	dcant offset rel corr	1994 - 2004	-12.8556263	5.6011939
1000	dcant offset rel corr	1994 - 2014	-16.4815737	4.0524776
1000	dcant offset rel corr	2004 - 2014	-19.9099197	3.3949269
1000	delta C* - mod_truth	1994 - 2004	1.5570000	0.0000000
1000	delta C* - mod_truth	1994 - 2014	3.1310000	0.0000000
1000	delta C* - mod_truth	2004 - 2014	1.5720000	0.0000000
1000	mod_truth	1994 - 2004	15.7000000	0.0000000
1000	mod_truth	1994 - 2014	34.1270000	0.0000000
1000	mod_truth	2004 - 2014	18.4280000	0.0000000
3000	C* drift	1994 - 2004	3.0410000	0.0000000
3000	C* drift	1994 - 2014	5.9850000	0.0000000
3000	C* drift	2004 - 2014	2.9440000	0.0000000
3000	C* prediction error	1994 - 2004	-0.9921667	1.2600961
3000	C* prediction error	1994 - 2014	-2.7565000	1.6879789
3000	C* prediction error	2004 - 2014	-1.7631667	0.9855921
3000	C* prediction error rel	1994 - 2004	-5.6245276	7.1434019
3000	C* prediction error rel	1994 - 2014	-7.1656962	4.3880079
3000	C* prediction error rel	2004 - 2014	-8.4653671	4.7320534
3000	dcant offset	1994 - 2004	0.9881667	1.3065036
3000	dcant offset	1994 - 2014	1.1473333	1.6884054
3000	dcant offset	2004 - 2014	0.2083333	0.9859429
3000	dcant offset rel	1994 - 2004	5.6018519	7.4064832
3000	dcant offset rel	1994 - 2014	2.9825656	4.3891166
3000	dcant offset rel	2004 - 2014	1.0002561	4.7337379
3000	dcant offset rel corr	1994 - 2004	-11.6373772	7.4064832
3000	dcant offset rel corr	1994 - 2014	-12.5758206	4.3891166
3000	dcant offset rel corr	2004 - 2014	-13.1345624	4.7337379
3000	delta C* - mod_truth	1994 - 2004	1.9330000	0.0000000
3000	delta C* - mod_truth	1994 - 2014	3.9040000	0.0000000
3000	delta C* - mod_truth	2004 - 2014	1.9710000	0.0000000
3000	mod_truth	1994 - 2004	17.6400000	0.0000000
3000	mod_truth	1994 - 2014	38.4680000	0.0000000
3000	mod_truth	2004 - 2014	20.8280000	0.0000000
10000	C* drift	1994 - 2004	2.5830000	0.0000000
10000	C* drift	1994 - 2014	5.0640000	0.0000000
10000	C* drift	2004 - 2014	2.4810000	0.0000000
10000	C* prediction error	1994 - 2004	-0.1213333	2.0951865
10000	C* prediction error	1994 - 2014	-1.0961667	2.5599351
10000	C* prediction error	2004 - 2014	-0.8805000	1.1651732
10000	C* prediction error rel	1994 - 2004	-0.6777641	11.7036446
10000	C* prediction error rel	1994 - 2014	-2.8061507	6.5533500
10000	C* prediction error rel	2004 - 2014	-4.1609565	5.5062296
10000	dcant offset	1994 - 2004	1.2286667	2.1130875
10000	dcant offset	1994 - 2014	1.5355000	2.5601133
10000	dcant offset	2004 - 2014	0.4485000	1.1656066
10000	dcant offset rel	1994 - 2004	6.8632927	11.8036391
10000	dcant offset rel	1994 - 2014	3.9308297	6.5538063
10000	dcant offset rel	2004 - 2014	2.1194651	5.5082774
10000	dcant offset rel corr	1994 - 2004	-7.5652627	11.8036391
10000	dcant offset rel corr	1994 - 2014	-9.0328444	6.5538063
10000	dcant offset rel corr	2004 - 2014	-9.6049336	5.5082774
10000	delta C* - mod_truth	1994 - 2004	1.3030000	0.0000000
10000	delta C* - mod_truth	1994 - 2014	2.6320000	0.0000000
10000	delta C* - mod_truth	2004 - 2014	1.3290000	0.0000000
10000	mod_truth	1994 - 2004	17.9020000	0.0000000
10000	mod_truth	1994 - 2014	39.0630000	0.0000000
10000	mod_truth	2004 - 2014	21.1610000	0.0000000

Session information

sessionInfo()

R version 4.1.2 (2021-11-01)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: openSUSE Leap 15.3

Matrix products: default
BLAS:   /usr/local/R-4.1.2/lib64/R/lib/libRblas.so
LAPACK: /usr/local/R-4.1.2/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] kableExtra_1.3.4   geomtextpath_0.1.0 colorspace_2.0-2   marelac_2.1.10    
 [5] shape_1.4.6        ggforce_0.3.3      metR_0.11.0        scico_1.3.0       
 [9] patchwork_1.1.1    collapse_1.7.0     forcats_0.5.1      stringr_1.4.0     
[13] dplyr_1.0.7        purrr_0.3.4        readr_2.1.1        tidyr_1.1.4       
[17] tibble_3.1.6       ggplot2_3.3.5      tidyverse_1.3.1    workflowr_1.7.0   

loaded via a namespace (and not attached):
 [1] fs_1.5.2           gghalves_0.1.1     bit64_4.0.5        lubridate_1.8.0   
 [5] gsw_1.0-6          RColorBrewer_1.1-2 webshot_0.5.2      httr_1.4.2        
 [9] rprojroot_2.0.2    tools_4.1.2        backports_1.4.1    bslib_0.3.1       
[13] utf8_1.2.2         R6_2.5.1           DBI_1.1.2          withr_2.4.3       
[17] tidyselect_1.1.1   processx_3.5.2     bit_4.0.4          compiler_4.1.2    
[21] git2r_0.29.0       textshaping_0.3.6  cli_3.1.1          rvest_1.0.2       
[25] xml2_1.3.3         labeling_0.4.2     sass_0.4.0         scales_1.1.1      
[29] checkmate_2.0.0    SolveSAPHE_2.1.0   callr_3.7.0        systemfonts_1.0.3 
[33] digest_0.6.29      svglite_2.0.0      rmarkdown_2.11     oce_1.5-0         
[37] pkgconfig_2.0.3    htmltools_0.5.2    highr_0.9          dbplyr_2.1.1      
[41] fastmap_1.1.0      rlang_1.0.2        readxl_1.3.1       rstudioapi_0.13   
[45] jquerylib_0.1.4    generics_0.1.1     farver_2.1.0       jsonlite_1.7.3    
[49] vroom_1.5.7        magrittr_2.0.1     Rcpp_1.0.8         munsell_0.5.0     
[53] fansi_1.0.2        lifecycle_1.0.1    stringi_1.7.6      whisker_0.4       
[57] yaml_2.2.1         MASS_7.3-55        grid_4.1.2         parallel_4.1.2    
[61] promises_1.2.0.1   crayon_1.4.2       haven_2.4.3        hms_1.1.1         
[65] seacarb_3.3.0      knitr_1.37         ps_1.6.0           pillar_1.6.4      
[69] reprex_2.0.1       glue_1.6.0         evaluate_0.14      getPass_0.2-2     
[73] data.table_1.14.2  modelr_0.1.8       vctrs_0.3.8        tzdb_0.2.0        
[77] tweenr_1.0.2       httpuv_1.6.5       cellranger_1.1.0   gtable_0.3.0      
[81] polyclip_1.10-0    assertthat_0.2.1   xfun_0.29          broom_0.7.11      
[85] later_1.3.0        viridisLite_0.4.0  ellipsis_0.3.2     here_1.0.1