crs-l2-svalbard-polar-areas

Rerun

import geopandas as gpd

def inspect_gpkg(path):
    try:
        gdf = gpd.read_file(path)
        print(f"Shape: {gdf.shape}")
        print(f"CRS: {gdf.crs}")
        print(f"Columns: {gdf.columns.tolist()}")
        print(f"First 5 rows:\n{gdf.head()}")
    except Exception as e:
        print(f"Error: {e}")

if __name__ == "__main__":
    inspect_gpkg('svalbard_glaciers_wgs84.gpkg')

import geopandas as gpd
import pandas as pd

def solve():
    # Load the data
    input_file = 'svalbard_glaciers_wgs84.gpkg'
    gdf = gpd.read_file(input_file)

    # Svalbard is located at high latitudes (roughly 74 to 81 N).
    # For accurate area measurements in Svalbard, North Pole Stereographic 
    # projection is often preferred. 
    # EPSG:3413 is NSIDC Sea Ice Polar Stereographic North.
    # EPSG:3031 is ETRS89-extended / LAEA Europe, which is good for Europe.
    # Let's use EPSG:3413 (North Polar Stereographic) as it's designed for the poles.
    # Another option is EPSG:3411 or similar, but 3413 is very standard for arctic.
    # Actually, let's check if there's a local Svalbard specific one or just use 
    # a standard Polar Stereographic.
    
    target_crs = 'EPSG:3413'
    
    # Project to the chosen CRS
    gdf_projected = gdf.to_crs(target_crs)
    
    # Calculate area in square meters, then convert to km2
    gdf_projected['area_km2'] = gdf_projected.geometry.area / 10**6
    
    # Get top 20 by area
    top_20 = gdf_projected.sort_values(by='area_km2', ascending=False).head(20).copy()
    
    # Calculate bboxes in the projected CRS
    # bbox is (minx, miny, maxx, maxy)
    top_20['bbox_minx_polar'] = top_20.geometry.bounds.minx
    top_20['bbox_miny_polar'] = top_20.geometry.bounds.miny
    top_20['bbox_maxx_polar'] = top_20.geometry.bounds.maxx
    top_20['bbox_maxy_polar'] = top_20.geometry.bounds.maxy
    
    # The EPSG code of the projection used
    epsg_code = int(target_crs.split(':')[-1])
    top_20['crs_epsg'] = epsg_code
    
    # Select and rename columns for output
    # Requirements: name, area_km2, bbox_minx_polar, bbox_miny_polar, bbox_maxx_polar, bbox_maxy_polar, crs_epsg
    output_columns = [
        'name', 'area_km2', 'bbox_minx_polar', 'bbox_miny_polar', 
        'bbox_maxx_polar', 'bbox_maxy_polar', 'crs_epsg'
    ]
    
    final_df = top_20[output_columns]
    
    # Write to CSV
    output_file = 'svalbard_glaciers_top20.csv'
    final_df.to_csv(output_file, index=False)
    print(f"Successfully saved top 20 glaciers to {output_file}")

if __name__ == "__main__":
    solve()