crs-l2-svalbard-polar-areas

Rerun

import geopandas as gpd

# Load the data to check CRS and structure
gdf = gpd.read_file('svalbard_glaciers_wgs84.gpkg')

print(f"CRS: {gdf.crs}")
print(f"Columns: {gdf.columns}")
print(f"First 5 rows:")
print(gdf.head())
print(f"Total number of features: {len(gdf)}")

import geopandas as gpd
import pandas as pd

# Load data
gdf = gpd.read_file('svalbard_glaciers_wgs84.gpkg')

# Svalbard is roughly at 78 deg N.
# We need a projection suitable for area measurement in Svalbard.
# NSIDC Sea Ice Polar Stereographic (EPSG:3413) is common for high latitudes.
# Or UTM zones. Svalbard is in UTM zones 33, 34, 35.
# However, Polar Stereographic is generally better for area across a large high-latitude region.
# EPSG:3413 (NSIDC Sea Ice Polar Stereographic North) is a good candidate.
# Let's use EPSG:3413.

target_crs = "EPSG:3413"

# Project to the chosen CRS
gdf_projected = gdf.to_crs(target_crs)

# Calculate area in m^2 and convert to km^2
gdf_projected['area_km2'] = gdf_projected.geometry.area / 10**6

# Get bounding box in the projected CRS
# bounds returns (minx, miny, maxx, maxy)
gdf_projected['bbox_minx_polar'] = gdf_projected.geometry.bounds.minx
gdf_projected['bbox_miny_polar'] = gdf_projected.geometry.bounds.miny
gdf_projected['bbox_maxx_polar'] = gdf_projected.geometry.bounds.maxx
gdf_projected['bbox_maxy_polar'] = gdf_projected.geometry.bounds.maxy

# Get EPSG code
epsg_code = gdf_projected.crs.to_epsg()

# Select top 20 by area descending
top_20 = gdf_projected.sort_values(by='area_km2', ascending=False).head(20)

# Prepare final dataframe with requested columns
# columns: name, area_km2, bbox_minx_polar, bbox_miny_polar, bbox_maxx_polar, bbox_maxy_polar, crs_epsg
result = pd.DataFrame({
    'name': top_20['name'],
    'area_km2': top_20['area_km2'],
    'bbox_minx_polar': top_20['bbox_minx_polar'],
    'bbox_miny_polar': top_20['bbox_miny_polar'],
    'bbox_maxx_polar': top_20['bbox_maxx_polar'],
    'bbox_maxy_polar': top_20['bbox_maxy_polar'],
    'crs_epsg': epsg_code
})

# Save to CSV
result.to_csv('svalbard_glaciers_top20.csv', index=False)

print("Top 20 glaciers processed and saved to svalbard_glaciers_top20.csv")
print(result.head())

import geopandas as gpd
import pandas as pd

# Load data
gdf = gpd.read_file('svalbard_glaciers_wgs84.gpkg')

# Target CRS: EPSG:3413 (NSIDC Sea Ice Polar Stereographic North)
target_crs = "EPSG:3413"

# Project to the chosen CRS
gdf_projected = gdf.to_crs(target_crs)

# Calculate area in m^2 and convert to km^2
gdf_projected['area_km2'] = gdf_projected.geometry.area / 10**6

# Get bounding box in the projected CRS
gdf_projected['bbox_minx_polar'] = gdf_projected.geometry.bounds.minx
gdf_projected['bbox_miny_polar'] = gdf_projected.geometry.bounds.miny
gdf_projected['bbox_maxx_polar'] = gdf_projected.geometry.bounds.maxx
gdf_projected['bbox_maxy_polar'] = gdf_projected.geometry.bounds.maxy

# Get EPSG code
epsg_code = gdf_projected.crs.to_epsg()

# Select top 20 by area descending
top_20 = gdf_projected.sort_values(by='area_km2', ascending=False).head(20)

# Prepare final dataframe with requested columns
# columns: name, area_km2, bbox_minx_polar, bbox_miny_polar, bbox_maxx_polar, bbox_maxy_polar, crs_epsg
result = pd.DataFrame({
    'name': top_20['name'],
    'area_km2': top_20['area_km2'],
    'bbox_minx_polar': top_20['bbox_minx_polar'],
    'bbox_miny_polar': top_20['bbox_miny_polar'],
    'bbox_maxx_polar': top_20['bbox_maxx_polar'],
    'bbox_maxy_polar': top_20['bbox_maxy_polar'],
    'crs_epsg': epsg_code
})

# Save to CSV
result.to_csv('svalbard_glaciers_top20.csv', index=False)

print(f"Successfully saved top 20 glaciers to svalbard_glaciers_top20.csv using EPSG:{epsg_code}")