11.6. Open Buildings from Google#
The dataset contains 1.8 billion building detections, across an inference area of 58M km2 within Africa, South Asia, South-East Asia, Latin America and the Caribbean. This large-scale open dataset contains the outlines of buildings derived from high-resolution satellite imagery. The project is based in Google’s Ghana office, focusing on the continent of Africa and the Global South at large.
The current dataset is in its 3rd version (v3), covering detections from Sub-Saharan Africa, South and South-East Asia, Latin America and the Caribbean.
For each building in this dataset, they include the polygon describing its footprint on the ground, a confidence score indicating how sure they are that this is a building, and a Plus Code corresponding to the center of the building. There is no information about the type of building, its street address, or any details other than its geometry.
More information about the project can be found here.
11.6.1. Download the data#
The dataset consists of 3 parts: building polygons, building points and score thresholds.
The data can be downloaded from a map or using a provided notebook. This example uses the map option by accessing here.
Note: Since they did not have data for Türkiye, we downloaded data for Patagonia, Argentina.
# !pip install geopandas folium
import pandas as pd
import geopandas as gpd
from shapely import wkt
import random
import folium
google_bld = pd.read_csv('../../data/mapping-exposure-infrastructure-google/bdb_buildings.csv.gz')
google_bld['geometry'] = google_bld['geometry'].apply(wkt.loads)
google_bld_gdf = gpd.GeoDataFrame(data = google_bld, crs = 'epsg:4326', geometry = google_bld['geometry'])
type(google_bld_gdf)
geopandas.geodataframe.GeoDataFrame
idx = list(google_bld_gdf.index)
idx_shuffled= random.shuffle(idx) # Shuffle indices to avoid spatial oversampling
m = google_bld_gdf.loc[idx[:10000]].explore(name = 'Open Building')
folium.LayerControl().add_to(m)
m