Geospatial Analysis with GeoPandas

Overview

When working with geographic data (earthquakes, plate boundaries, etc.), using geopandas with proper coordinate projections provides accurate distance calculations and efficient spatial operations. This guide covers best practices for geospatial analysis.

Key Concepts

Geographic vs Projected Coordinate Systems

Coordinate System	Type	Units	Use Case
EPSG:4326 (WGS84)	Geographic	Degrees (lat/lon)	Data storage, display
EPSG:4087 (World Equidistant Cylindrical)	Projected	Meters	Distance calculations

Critical Rule: Never calculate distances directly in geographic coordinates (EPSG:4326). Always project to a metric coordinate system first.

Why Projection Matters

# ❌ INCORRECT: Calculating distance in EPSG:4326
# This treats degrees as if they were equal distances everywhere on Earth
gdf = gpd.GeoDataFrame(..., crs="EPSG:4326")
distance = point1.distance(point2)  # Wrong! Returns degrees, not meters

# ✅ CORRECT: Project to metric CRS first
gdf_projected = gdf.to_crs("EPSG:4087")
distance_meters = point1_proj.distance(point2_proj)  # Correct! Returns meters
distance_km = distance_meters / 1000.0

Loading Geospatial Data

From GeoJSON Files

import geopandas as gpd

# Load GeoJSON files directly
gdf_plates = gpd.read_file("plates.json")
gdf_boundaries = gpd.read_file("boundaries.json")

From Regular Data with Coordinates

from shapely.geometry import Point
import geopandas as gpd

# Convert coordinate data to GeoDataFrame
data = [
    {"id": 1, "lat": 35.0, "lon": 140.0, "value": 5.5},
    {"id": 2, "lat": 36.0, "lon": 141.0, "value": 6.0},
]

geometry = [Point(row["lon"], row["lat"]) for row in data]
gdf = gpd.GeoDataFrame(data, geometry=geometry, crs="EPSG:4326")