Add basic handling of GFED4 BB4CMIP data

.gitignore

@@ -1,12 +1,14 @@
 # Processed data
 data/national/ceds/processed
 data/national/gfed/processed
+data/national/gfed-bb4cmip/processed
 
 # CEDS data
 data/national/ceds/data_raw
 
 # GFED data
 data/national/gfed/data_raw
+data/national/gfed-bb4cmip/data_raw
 
 # pixi stuff
 .pixi

data/national/gfed-bb4cmip/data_raw/README.md

@@ -0,0 +1,51 @@
+Biomass burning data is on the ESGF here: https://aims2.llnl.gov/search?project=input4MIPs&activeFacets=%7B%22mip_era%22%3A%22CMIP6Plus%22%2C%22institution_id%22%3A%22DRES%22%7D
+
+Download the data of interest here.
+This can be done with the following commands
+and [esgpull](https://esgf.github.io/esgf-download/)
+(if you're not on a unix-based system,
+create a virtual environment using whatever environment manager you like
+then remove `venv/bin/` from all the commands below).
+
+```sh
+# Install esgpull
+# (see note above for non-unix systems)
+python3 -m venv venv
+venv/bin/pip install esgpull
+venv/bin/esgpull self install
+
+# In the diaglog that pops up, install here
+# to ensure that the paths in the notebooks behave.
+venv/bin/esgpull config api.index_node esgf-node.llnl.gov
+```
+
+Then, check that the installation worked correctly by running
+
+```sh
+venv/bin/esgpull config
+```
+
+The output should look something like
+
+```
+─────────────────── /path/to/emissions_harmonization_historical/data/national/gfed-bb4cmip/data_raw/config.toml ───────────────────
+[paths]
+...
+data = "/path/to/emissions_harmonization_historical/data/national/gfed-bb4cmip/data_raw/data"
+...
+
+[api]
+index_node = "esgf-node.llnl.gov"
+...
+```
+
+Then, download the data
+
+```sh
+# Comma-separated list
+# You can search with esgpull search e.g. `venv/bin/esgpull search --all project:input4MIPs mip_era:CMIP6Plus source_id:DRES-CMIP-BB4CMIP7-1-0 grid_label:gn`
+variable_ids_to_grab="BC,CH4,CO,CO2,N2O,NH3,NOx,OC,SO2,gridcellarea"
+venv/bin/esgpull add --tag bb4cmip --track variable_id:"${variable_ids_to_grab}" project:input4MIPs mip_era:CMIP6Plus source_id:DRES-CMIP-BB4CMIP7-1-0 grid_label:gn
+venv/bin/esgpull update -y --tag bb4cmip
+venv/bin/esgpull download
+```

notebooks/0103_GFED4-BB4CMIP-prepare.py

@@ -0,0 +1,59 @@
+# ---
+# jupyter:
+#   jupytext:
+#     text_representation:
+#       extension: .py
+#       format_name: percent
+#       format_version: '1.3'
+#       jupytext_version: 1.16.4
+#   kernelspec:
+#     display_name: Python 3 (ipykernel)
+#     language: python
+#     name: python3
+# ---
+
+# %%
+from collections import defaultdict
+
+import xarray as xr
+
+from emissions_harmonization_historical.constants import DATA_ROOT
+
+# %%
+raw_data_path = DATA_ROOT / "national/gfed-bb4cmip/data_raw/data"
+raw_data_path
+
+# %% [markdown]
+# Group raw data into variable groups which can be used for processing.
+
+# %%
+bb4cmip_files = list(raw_data_path.rglob("*.nc"))
+bb4cmip_file_groups = defaultdict(list)
+
+for file in bb4cmip_files:
+    variable = file.name.split("_")[0]
+    bb4cmip_file_groups[variable].append(file)
+
+bb4cmip_file_groups.keys()
+
+# %% [markdown]
+# An example of loading data.
+
+# %%
+cell_area = xr.open_mfdataset(bb4cmip_file_groups["gridcellarea"])
+cell_area
+
+# %%
+gas = "BC"
+gas_ds = xr.open_mfdataset(bb4cmip_file_groups["BC"])
+gas_ds
+
+# %%
+global_sum_emissions = (gas_ds["BC"] * cell_area["gridcellarea"]).sum(["latitude", "longitude"]).compute()
+global_sum_emissions
+
+# %%
+global_sum_emissions.plot()
+
+# %%
+global_sum_emissions.groupby("time.year").mean().plot()

pyproject.toml

@@ -50,6 +50,7 @@ h5py = ">=3.11.0,<4"
 netcdf4 = ">=1.7.1,<2"
 h5netcdf = ">=1.4.0,<2"
 pooch = ">=1.8.2,<2"
+nc-time-axis = ">=1.4.1,<2"
 
 [tool.pixi.pypi-dependencies]
 emissions_harmonization_historical = { path = ".", editable = true }