def load_cpa_gdf(filepath, target_crs, slope_filter=None, layer=None):
if layer is not None:
cpa_gdf = gpd.read_file(filepath, layer=layer)
else:
cpa_gdf = gpd.read_file(filepath)
if slope_filter:
cpa_gdf = cpa_gdf.loc[cpa_gdf["m_slope"] <= slope_filter, :]
cpa_gdf = cpa_gdf.reset_index(drop=True)
cpa_gdf = cpa_gdf.to_crs(target_crs)
centroid = find_centroid(cpa_gdf)
cpa_gdf["Latitude"] = centroid.y
cpa_gdf["Longitude"] = centroid.x
cpa_gdf["cpa_id"] = cpa_gdf.index
cpa_gdf["prefSite"] = cpa_gdf["prefSite"].fillna(0)
dist_cols = [
"d_coast_sub_161kVplus", "d_coast", "d_sub_load_metro_750k_center"
]
for col in dist_cols:
mile_col = f"{col}_miles"
cpa_gdf[mile_col] = cpa_gdf[col] * 1.60934
return cpa_gdf
def load_cpa_gdf(filepath, target_crs, slope_filter=None, layer=None):
if layer is not None:
cpa_gdf = gpd.read_file(filepath, layer=layer)
else:
cpa_gdf = gpd.read_file(filepath)
if slope_filter:
cpa_gdf = cpa_gdf.loc[cpa_gdf["m_slope"] <= slope_filter, :]
cpa_gdf = cpa_gdf.reset_index(drop=True)
cpa_gdf = cpa_gdf.to_crs(target_crs)
centroid = find_centroid(cpa_gdf)
cpa_gdf["Latitude"] = centroid.y
cpa_gdf["Longitude"] = centroid.x
cpa_gdf["cpa_id"] = cpa_gdf.index
return cpa_gdf
def load_metro_areas_shapefile():
shpfile_path = (
CWD / "USA_Core_Based_Statistical_Area" / "USA_Core_Based_Statistical_Area.shp"
)
metro_areas = gpd.read_file(shpfile_path)
metro_areas = metro_areas.to_crs(epsg=4326)
metro_areas["center"] = find_centroid(metro_areas)
keep_cols = ["CBSA_ID", "NAME", "CBSA_TYPE", "POPULATION", "center", "geometry"]
# metro_areas["geometry"] = metro_areas["center"]
metro_areas = metro_areas.loc[:, keep_cols]
metro_areas["metro_id"] = metro_areas["CBSA_ID"]
metro_areas.columns = metro_areas.columns.str.lower()
metro_areas["state"] = metro_areas["name"].str.split(", ").str[-1]
metro_areas = metro_areas.loc[~metro_areas.state.isin(["AK", "HI", "PR"]), :]
return metro_areas
def transmission_line_distance(trans_constraints_df,
ipm_shapefile,
settings,
units="mile"):
logger.info("Calculating transmission line distance")
ipm_shapefile["geometry"] = ipm_shapefile.buffer(0.01)
model_polygons = ipm_shapefile.dissolve(by="model_region")
model_polygons = model_polygons.to_crs(epsg=4326)
region_centroids = find_centroid(model_polygons)
distances = [
single_line_distance(line_name, region_centroids, units=units)
for line_name in trans_constraints_df["Transmission Path Name"]
]
trans_constraints_df[f"distance_{units}"] = distances
trans_constraints_df[f"distance_{units}"] = trans_constraints_df[
f"distance_{units}"]
return trans_constraints_df
def main(
fn_prefix: str = "",
additional_metros: Optional[List[str]] = typer.Option(None),
):
logger.info("Loading states, voronoi, and CPAs")
us_states = load_us_states_gdf()
# metro_voronoi_gdf = gpd.read_file("large_metro_voronoi.geojson")
cpa_gdf = load_cpa_gdf(
"OffshoreWind_CPA_BLUA_20210125",
target_crs=us_states.crs,
)
# Specify fixed (OTRG3) and floating (OTRG10), with cutoff at 50m
cpa_gdf["TRG"] = "OTRG13"
cpa_gdf.loc[cpa_gdf["m_seafloorDepth"] >= -50, "TRG"] = "OTRG3"
ipm_gdf = load_ipm_shapefile()
metro_gdf = load_metro_areas_shapefile()
largest_metros = find_largest_cities(
metro_areas_gdf=metro_gdf,
ipm_gdf=ipm_gdf,
min_population=750000,
additional_metros=additional_metros,
)
logger.info("Finding nearest MSA to assign IPM Region and cbsa_id")
# cpa_metro = ckdnearest(
# cpa_gdf.reset_index(drop=True), largest_metros.reset_index(drop=True)
# )
# cpa_metro = cpa_metro.drop(columns=["lat2", "lon2"])
# Only 3 CPAs get assigned to PJM_SMAC, and it causes errors when clustering.
# smac_filter = cpa_metro.loc[cpa_metro.IPM_Region == "PJM_SMAC", :].index
# cpa_metro.loc[smac_filter, "IPM_Region"] = "PJM_EMAC"
# cpa_metro.loc[smac_filter, "metro_id"] = "37980"
logger.info("Matching CPAs with VCE sites")
site_locations = load_site_locations()
site_locations = site_locations.rename(columns={
"Latitude": "latitude",
"Longitude": "longitude"
})
cpa_vce_site = ckdnearest(cpa_gdf.copy(), site_locations.copy())
cpa_vce_site = cpa_vce_site.drop(columns=["lat2", "lon2"])
# Load substations and join with states so we know the state location. Use this
# for offshore wind landing in NJ so it doesn't delivery to NY_Z_J
substation_gdf = load_substations()
substation_gdf = gpd.sjoin(substation_gdf, us_states, how="left")
landfall_points = gpd.read_file("landfall/landfall.gdb")
landfall_points = landfall_points.to_crs(crs="EPSG:4326")
landfall_points["center"] = find_centroid(landfall_points)
landfall_points["latitude"] = landfall_points.center.y
landfall_points["longitude"] = landfall_points.center.x
landfall_points = gpd.sjoin(
landfall_points,
us_states.set_geometry(us_states.buffer(0.03)),
how="left").drop_duplicates(subset=["ORIG_FID"])
cpa_vce_interconnect_distances = calc_interconnect_distances(
cpa_gdf=cpa_vce_site,
landfall_gdf=landfall_points,
substation_gdf=substation_gdf,
metro_gdf=largest_metros,
)
cpa_vce_lcoe = calc_interconnect_costs_lcoe(cpa_vce_interconnect_distances)
metro_ipm_map = (largest_metros[[
"metro_id", "IPM_Region"
]].drop_duplicates().set_index("metro_id"))
cpa_vce_lcoe["ipm_region"] = cpa_vce_lcoe["delivery_metro"].map(
metro_ipm_map["IPM_Region"])
cpa_vce_lcoe["metro_id"] = cpa_vce_lcoe["delivery_metro"]
logger.info("Writing results to file")
# cpa_vce_lcoe.drop(columns=["geometry"]).to_csv("base_offshorewind_lcoe.csv", index=False, float_format='%.5f')
geodata_cols = [
"cpa_id",
# "state",
"Site",
"metro_id",
"IPM_Region",
"interconnect_annuity",
"lcoe",
"geometry",
]
keep_cols = [
"Area",
"Latitude",
"Longitude",
"cpa_id",
"Site",
"ORIG_FID",
"substation_id",
"d_coast_miles",
"d_coast_sub_161kVplus_miles",
"d_sub_load_metro_750k_center_miles",
"site_shore_miles",
"shore_substation_miles",
"substation_metro_miles",
"land_substation_capex",
"substation_metro_capex",
"offshore_spur_capex",
"interconnect_capex",
"interconnect_annuity",
"TRG",
"ipm_region",
"interconnect_capex",
"offshore_wind_cf",
"lcoe",
"metro_id",
"prefSite",
"turbineType",
"STATE_NAME",
]
cpa_vce_lcoe[keep_cols].sort_values("cpa_id").drop_duplicates().to_csv(
f"{fn_prefix}base_offshorewind_lcoe.csv", index=False)
def load_metro_areas_shapefile():
shpfile_path = (
CWD /
"USA_Core_Based_Statistical_Area" # / "USA_Core_Based_Statistical_Area.shp"
)
metro_areas = gpd.read_file(shpfile_path)
metro_areas = metro_areas.to_crs(epsg=4326)
corrected_metro_centroids = pd.read_csv(CWD.parent / "bin" /
"msa_urban_centroids.csv")
corrected_metro_centroids["CBSA_ID"] = corrected_metro_centroids[
"CBSA_ID"].astype("str")
corrected_metro_centroids = corrected_metro_centroids.set_index("CBSA_ID")
corrected_metro_centroids = gpd.GeoDataFrame(
corrected_metro_centroids,
geometry=points_from_xy(
corrected_metro_centroids["msa_longitude"],
corrected_metro_centroids["msa_latitude"],
),
crs="EPSG:4326",
)
metro_areas["center"] = find_centroid(metro_areas)
metro_areas["corrected_center"] = metro_areas["CBSA_ID"].map(
corrected_metro_centroids["geometry"])
metro_areas["msa_center"] = metro_areas["center"]
metro_areas.loc[~metro_areas["corrected_center"].isna(),
"center"] = metro_areas["corrected_center"]
keep_cols = [
"CBSA_ID",
"NAME",
"CBSA_TYPE",
"POPULATION",
"center",
"msa_center",
"geometry",
]
# metro_areas["geometry"] = metro_areas["center"]
metro_areas = metro_areas.loc[:, keep_cols]
metro_areas["metro_id"] = metro_areas["CBSA_ID"]
metro_areas.columns = metro_areas.columns.str.lower()
metro_areas["state"] = metro_areas["name"].str.split(", ").str[-1]
metro_areas = metro_areas.loc[
~metro_areas.state.isin(["AK", "HI", "PR"]), :]
NY_Z_J_lon_lat = (-73.930488, 40.695448)
NY_Z_K_lon_lat = (-73.008906, 40.840391)
extra_metros = pd.DataFrame([["NY_Z_J", 1e6], ["NY_Z_K", 1e6]],
columns=["metro_id", "population"])
extra_metros = gpd.GeoDataFrame(
extra_metros,
geometry=points_from_xy(*zip(NY_Z_J_lon_lat, NY_Z_K_lon_lat)),
crs="EPSG:4326",
)
extra_metros["center"] = extra_metros["geometry"]
metro_areas = pd.concat([metro_areas, extra_metros],
ignore_index=True,
sort=False)
return metro_areas