update GEM Europe gas tracker to May 2024 version (#1235)

doc/release_notes.rst

@@ -9,6 +9,9 @@ Release Notes
 
 Upcoming Release
 ================
+
+* Update GEM Europe Gas Tracker to May 2024 version.
+
 * Add investment period dependent CO2 sequestration potentials
 
 * Add option to produce hydrogen from solid biomass (flag ``solid biomass to hydrogen``), combined with carbon capture

rules/build_sector.smk

@@ -93,10 +93,7 @@ rule build_gas_network:
 
 rule build_gas_input_locations:
     input:
-        gem=storage(
-            "https://globalenergymonitor.org/wp-content/uploads/2023/07/Europe-Gas-Tracker-2023-03-v3.xlsx",
-            keep_local=True,
-        ),
+        gem="data/gem/Europe-Gas-Tracker-2024-05.xlsx",
         entry="data/gas_network/scigrid-gas/data/IGGIELGN_BorderPoints.geojson",
         storage="data/gas_network/scigrid-gas/data/IGGIELGN_Storages.geojson",
         regions_onshore=resources("regions_onshore_elec_s{simpl}_{clusters}.geojson"),

rules/retrieve.smk

@@ -280,6 +280,23 @@ if config["enable"]["retrieve"]:
             os.remove(params["zip"])
 
 
+if config["enable"]["retrieve"]:
+
+    rule retrieve_gem_europe_gas_tracker:
+        output:
+            "data/gem/Europe-Gas-Tracker-2024-05.xlsx",
+        run:
+            import requests
+
+            response = requests.get(
+                "https://globalenergymonitor.org/wp-content/uploads/2024/05/Europe-Gas-Tracker-2024-05.xlsx",
+                headers={"User-Agent": "Mozilla/5.0"},
+            )
+            with open(output[0], "wb") as f:
+                f.write(response.content)
+
+
+
 if config["enable"]["retrieve"]:
     # Some logic to find the correct file URL
     # Sometimes files are released delayed or ahead of schedule, check which file is currently available

scripts/build_gas_input_locations.py

@@ -36,15 +36,20 @@ def build_gem_lng_data(fn):
         "Gran Canaria LNG Terminal",
     ]
 
+    status_list = ["Operating", "Construction"]  # noqa: F841
+
     df = df.query(
-        "Status != 'Cancelled' \
+        "Status in @status_list \
+              & FacilityType == 'Import' \
               & Country != @remove_country \
               & TerminalName != @remove_terminal \
-              & CapacityInMtpa != '--'"
+              & CapacityInMtpa != '--' \
+              & CapacityInMtpa != 0"
     )
 
     geometry = gpd.points_from_xy(df["Longitude"], df["Latitude"])
-    return gpd.GeoDataFrame(df, geometry=geometry, crs="EPSG:4326")
+    gdf = gpd.GeoDataFrame(df, geometry=geometry, crs="EPSG:4326")
+    return gdf
 
 
 def build_gem_prod_data(fn):
@@ -54,8 +59,10 @@ def build_gem_prod_data(fn):
     remove_country = ["Cyprus", "Türkiye"]  # noqa: F841
     remove_fuel_type = ["oil"]  # noqa: F841
 
+    status_list = ["operating", "in development"]  # noqa: F841
+
     df = df.query(
-        "Status != 'shut in' \
+        "Status in @status_list \
               & 'Fuel type' != 'oil' \
               & Country != @remove_country \
               & ~Latitude.isna() \
@@ -64,7 +71,7 @@ def build_gem_prod_data(fn):
 
     p = pd.read_excel(fn, sheet_name="Gas extraction - production")
     p = p.set_index("GEM Unit ID")
-    p = p[p["Fuel description"] == "gas"]
+    p = p[p["Fuel description"].str.contains("gas")]
 
     capacities = pd.DataFrame(index=df.index)
     for key in ["production", "production design capacity", "reserves"]:
@@ -85,7 +92,8 @@ def build_gem_prod_data(fn):
     )
 
     geometry = gpd.points_from_xy(df["Longitude"], df["Latitude"])
-    return gpd.GeoDataFrame(df, geometry=geometry, crs="EPSG:4326")
+    gdf = gpd.GeoDataFrame(df, geometry=geometry, crs="EPSG:4326")
+    return gdf
 
 
 def build_gas_input_locations(gem_fn, entry_fn, sto_fn, countries):
@@ -134,8 +142,7 @@ if __name__ == "__main__":
         snakemake = mock_snakemake(
             "build_gas_input_locations",
             simpl="",
-            clusters="5",
-            configfiles="config/test/config.overnight.yaml",
+            clusters="128",
         )
 
     configure_logging(snakemake)