Merge pull request #1073 from CliMA/kp/ten-yr-leaderboard

Update leaderboard for longer run of snowy land

Author: ph-kev

.buildkite/Manifest-v1.11.toml

@@ -2,7 +2,7 @@
 
 julia_version = "1.11.4"
 manifest_format = "2.0"
-project_hash = "4fe4935d5d45f04880ac419a664997320feb94e4"
+project_hash = "556cc366c0974a7c1af7cf9d7cb51d21d3254f47"
 
 [[deps.ADTypes]]
 git-tree-sha1 = "e2478490447631aedba0823d4d7a80b2cc8cdb32"
@@ -365,9 +365,9 @@ weakdeps = ["SparseArrays"]
 
 [[deps.ClimaAnalysis]]
 deps = ["Artifacts", "Dates", "Interpolations", "NCDatasets", "NaNStatistics", "OrderedCollections", "Reexport", "Statistics", "Unitful"]
-git-tree-sha1 = "1cae1cd626bd636bba0e1a4a681e0296372848bc"
+git-tree-sha1 = "0a9f4a6de147d0a9dc09f2e8f702f76dd6777e07"
 uuid = "29b5916a-a76c-4e73-9657-3c8fd22e65e6"
-version = "0.5.15"
+version = "0.5.16"
 weakdeps = ["GeoMakie", "Makie"]
 
     [deps.ClimaAnalysis.extensions]

.buildkite/Project.toml

@@ -41,7 +41,7 @@ Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 Thermodynamics = "b60c26fb-14c3-4610-9d3e-2d17fe7ff00c"
 
 [compat]
-ClimaAnalysis = "0.5.15"
+ClimaAnalysis = "0.5.16"
 ClimaTimeSteppers = "0.7, 0.8"
 Statistics = "1"
 Flux = "0.15"

Artifacts.toml

@@ -165,6 +165,13 @@ git-tree-sha1 = "4cc329093b0dbc3443db36e7c01133267ac94d37"
 [forty_yrs_era5_land_forcing_data]
 git-tree-sha1 = "f269a0b057b9f438b4caafdef17da73746310787"
 
+[era5_monthly_averages_surface_single_level_1979_2024]
+git-tree-sha1 = "6cddb07eeee2dd46dc5a19e9b2f706302ddba2c9"
+
+    [[era5_monthly_averages_surface_single_level_1979_2024.download]]
+    sha256 = "46b422722d98c89c6bc0b8641bff259db1caee253f45389ddf9eb9c2d31ed605"
+    url = "https://caltech.box.com/shared/static/jbgtyt6oq9lxvk8il5zzck6k581q7f3k.gz"
+
 [huang_van_genuchten_data]
 git-tree-sha1 = "39a344685d74346f89c4858c183565554494fc01"
 

experiments/long_runs/leaderboard/data_sources.jl

@@ -1,4 +1,5 @@
 import ClimaAnalysis
+import ClimaLand
 
 """
     get_sim_var_dict(diagnostics_folder_path)
@@ -66,14 +67,48 @@ function get_sim_var_dict(diagnostics_folder_path)
             )
             return sim_var
         end
+
+    sim_var_dict["lhf"] =
+        () -> begin
+            sim_var = get(
+                ClimaAnalysis.SimDir(diagnostics_folder_path),
+                short_name = "lhf",
+            )
+            sim_var =
+                ClimaAnalysis.shift_to_start_of_previous_month(sim_var)
+            return sim_var
+        end
+
+    sim_var_dict["shf"] =
+        () -> begin
+            sim_var = get(
+                ClimaAnalysis.SimDir(diagnostics_folder_path),
+                short_name = "shf",
+            )
+            sim_var =
+                ClimaAnalysis.shift_to_start_of_previous_month(sim_var)
+            return sim_var
+        end
+
+    sim_var_dict["swu"] =
+        () -> begin
+            sim_var = get(
+                ClimaAnalysis.SimDir(diagnostics_folder_path),
+                short_name = "swu",
+            )
+            sim_var =
+                ClimaAnalysis.shift_to_start_of_previous_month(sim_var)
+            return sim_var
+        end
     return sim_var_dict
 end
 
 """
-    get_obs_var_dict()
+    get_obs_var_dict(data_source)
 
 Return a dictionary mapping short names to `OutputVar` containing preprocessed
-observational data. This is used by the function `compute_leaderboard`.
+observational data. This is used by the function `compute_leaderboard`.The
+argument `data_source` can either be "ERA5" or "ILAMB".
 
 To add a variable for the leaderboard, add a key-value pair to the dictionary
 `obs_var_dict` whose key is the short name of the variable and the value is an
@@ -86,7 +121,23 @@ dates.
 
 The variable should have only three dimensions: latitude, longitude, and time.
 """
-function get_obs_var_dict()
+function get_obs_var_dict(data_source)
+    if uppercase(data_source) == "ILAMB"
+        return get_ilamb_obs_var_dict()
+    elseif uppercase(data_source) == "ERA5"
+        return get_era5_obs_var_dict()
+    else
+        error("Did not expect $data_source for the data source")
+    end
+end
+
+"""
+    get_ilamb_obs_var_dict()
+
+Get ILAMB observational data. See `get_obs_var_dict` for more information for
+how to add new variables.
+"""
+function get_ilamb_obs_var_dict()
     # Dict for loading in observational data
     obs_var_dict = Dict{String, Any}()
     obs_var_dict["et"] =
@@ -143,12 +194,93 @@ function get_obs_var_dict()
     return obs_var_dict
 end
 
+"""
+    get_era5_obs_var_dict()
+
+Get ERA5 observational data. See `get_obs_var_dict` for more information for
+how to add new variables.
+"""
+function get_era5_obs_var_dict()
+    obs_var_dict = Dict{String, Any}()
+    era5_data_path = joinpath(
+        ClimaLand.Artifacts.era5_monthly_averages_single_level_path(),
+        "era5_monthly_averages_surface_single_level_197901-202410.nc",
+    )
+
+    obs_var_dict["lhf"] =
+        (start_date) -> begin
+            obs_var = ClimaAnalysis.OutputVar(
+                era5_data_path,
+                "mslhf",
+                new_start_date = start_date,
+                shift_by = Dates.firstdayofmonth,
+            )
+            (ClimaAnalysis.units(obs_var) == "W m**-2") && (
+                obs_var = ClimaAnalysis.convert_units(
+                    obs_var,
+                    "W m^-2",
+                    conversion_function = units -> units * -1.0,
+                )
+            )
+            return obs_var
+        end
+
+    obs_var_dict["shf"] =
+        (start_date) -> begin
+            obs_var = ClimaAnalysis.OutputVar(
+                era5_data_path,
+                "msshf",
+                new_start_date = start_date,
+                shift_by = Dates.firstdayofmonth,
+            )
+
+            (ClimaAnalysis.units(obs_var) == "W m**-2") && (
+                obs_var = ClimaAnalysis.convert_units(
+                    obs_var,
+                    "W m^-2",
+                    conversion_function = units -> units * -1.0,
+                )
+            )
+
+            return obs_var
+        end
+
+    obs_var_dict["lwu"] =
+        (start_date) -> begin
+            obs_var = ClimaAnalysis.OutputVar(
+                era5_data_path,
+                "msuwlwrf",
+                new_start_date = start_date,
+                shift_by = Dates.firstdayofmonth,
+            )
+            (ClimaAnalysis.units(obs_var) == "W m**-2") &&
+                (obs_var = ClimaAnalysis.set_units(obs_var, "W m^-2"))
+            return obs_var
+        end
+
+    obs_var_dict["swu"] =
+        (start_date) -> begin
+            obs_var = ClimaAnalysis.OutputVar(
+                era5_data_path,
+                "msuwswrf",
+                new_start_date = start_date,
+                shift_by = Dates.firstdayofmonth,
+            )
+
+            (ClimaAnalysis.units(obs_var) == "W m**-2") &&
+                (obs_var = ClimaAnalysis.set_units(obs_var, "W m^-2"))
+            return obs_var
+        end
+    return obs_var_dict
+end
+
 """
     get_mask_dict()
 
 Return a dictionary mapping short names to a function which takes in `sim_var`,
 a `OutputVar` containing simulation data, and `obs_var`, a `OutputVar`
-containing observational data, and return a masking function.
+containing observational data, and return a masking function. The argument
+`data_source` is either `ILAMB` or `ERA5`.
 
 To add a variable to the leaderboard, add a key-value pair to the dictionary
 `mask_dict` whose key is the same short name in `sim_var_dict` and the value is
@@ -157,34 +289,55 @@ a function that takes in a `OutputVar` representing simulation data and a
 `nothing` if a masking function is not needed. The masking function is used to
 correctly normalize the global bias and global RMSE.
 """
-function get_mask_dict()
+function get_mask_dict(data_source)
     # Dict for loading in masks
     mask_dict = Dict{String, Any}()
 
-    mask_dict["et"] =
+    # LWU is found in both ERA5 and ILAMB
+    mask_dict["lwu"] =
         (sim_var, obs_var) -> begin
-            return ClimaAnalysis.make_lonlat_mask(
-                ClimaAnalysis.slice(
-                    obs_var,
-                    time = ClimaAnalysis.times(obs_var) |> first,
-                );
-                set_to_val = isnan,
-            )
+            return ClimaAnalysis.apply_oceanmask
         end
 
-    mask_dict["gpp"] =
-        (sim_var, obs_var) -> begin
-            return ClimaAnalysis.make_lonlat_mask(
-                ClimaAnalysis.slice(
-                    obs_var,
-                    time = ClimaAnalysis.times(obs_var) |> first,
-                );
-                set_to_val = isnan,
-            )
-        end
+    if uppercase(data_source) == "ILAMB"
+        mask_dict["et"] =
+            (sim_var, obs_var) -> begin
+                return ClimaAnalysis.make_lonlat_mask(
+                    ClimaAnalysis.slice(
+                        obs_var,
+                        time = ClimaAnalysis.times(obs_var) |> first,
+                    );
+                    set_to_val = isnan,
+                )
+            end
+
+        mask_dict["gpp"] =
+            (sim_var, obs_var) -> begin
+                return ClimaAnalysis.make_lonlat_mask(
+                    ClimaAnalysis.slice(
+                        obs_var,
+                        time = ClimaAnalysis.times(obs_var) |> first,
+                    );
+                    set_to_val = isnan,
+                )
+            end
+    elseif uppercase(data_source) == "ERA5"
+        mask_dict["shf"] =
+            (sim_var, obs_var) -> begin
+                return ClimaAnalysis.apply_oceanmask
+            end
+
+        mask_dict["lhf"] =
+            (sim_var, obs_var) -> begin
+                return ClimaAnalysis.apply_oceanmask
+            end
 
-    mask_dict["lwu"] = (sim_var, obs_var) -> begin
-        return nothing
+        mask_dict["swu"] =
+            (sim_var, obs_var) -> begin
+                return ClimaAnalysis.apply_oceanmask
+            end
+    else
+        error("Did not expect $data_source for the data source")
     end
     return mask_dict
 end
@@ -201,7 +354,13 @@ the value is a tuple, where the first element is the lower bound and the last
 element is the upper bound for the bias plots.
 """
 function get_compare_vars_biases_plot_extrema()
-    compare_vars_biases_plot_extrema =
-        Dict("et" => (-2.0, 2.0), "gpp" => (-6.0, 6.0), "lwu" => (-40.0, 40.0))
+    compare_vars_biases_plot_extrema = Dict(
+        "et" => (-2.0, 2.0),
+        "gpp" => (-6.0, 6.0),
+        "lwu" => (-40.0, 40.0),
+        "shf" => (-50.0, 50.0),
+        "lhf" => (-40.0, 40.0),
+        "swu" => (-50.0, 50.0),
+    )
     return compare_vars_biases_plot_extrema
 end