Brick Kiln Dataset for Pakistan's IGP Region Using AI

This dataset represents the first geospatial mapping of brick kiln sites in the IGP region of Pakistan, providing an invaluable resource for understanding the spatial distribution of these sites. Each data point captures a brick kiln's precise location, including coordinates, state, and other important information, standardized in Coordinate Reference System (CRS) EPSG:4326 (WGS 84). This dataset, to the best of our knowledge, is the first of its kind to consolidate and geolocate brick kiln operations across this region, where air pollution impacts from kiln emissions are a significant environmental and public health concern.

In addition to the primary geolocation data, the dataset also includes an initial, secondary estimation of emissions (PM10, PM2.5, NOx, and SOx) from these sites. This supplementary information supports preliminary risk assessments, emphasizing proximity-based exposure for populations and sensitive areas (e.g., schools, hospitals) within a 1 km radius of each kiln site. 

The dataset is made available in multiple formats to facilitate wide usage across spatial analysis platforms:

Geojson (.geojson)

Shapefile (.shp)

Comma-Separated Values (.csv)

Metadata:

Geographic Coverage: IGP - Pakistan

CRS: EPSG:4326 (WGS 84)

1. Dataset - Main Version

Columns:

id: Unique identifier for each brick kiln site.

lat: Latitude of the brick kiln in decimal degrees.

lon: Longitude of the brick kiln in decimal degrees.

state: Administrative state or region of the kiln.

type: Classification of brick kiln (FCBK or ZigZag).

schools1km: Number of schools within a 1 km radius.

hosp1km: Number of hospitals within a 1 km radius.

pop1km: Estimated population within a 1 km radius.

2. Dataset - Estimates Version

Columns:

Basic ID & Location: id, lat, lon, state, type (to allow for cross-referencing with the Main Version).

Production Data:

avg_bricks: Average number of kilns in operation per day.

dailyprod(kg): Estimated daily production of bricks in kilograms.

seasonprod(kg): Seasonal production in kilograms (Excluding the Monsoon and Smog Days)

Emission Estimates:

Daily Emissions:

pm2.5d(kg): Daily PM2.5 emissions in kilograms.

pm10d(kg): Daily PM10 emissions in kilograms.

noxd(kg): Daily NOx emissions in kilograms.

soxd(kg): Daily SOx emissions in kilograms.

Seasonal Emissions:

pm2.5s(kg): Seasonal PM2.5 emissions in kilograms.

pm10s(kg): Seasonal PM10 emissions in kilograms.

noxs(kg): Seasonal NOx emissions in kilograms.

soxs(kg): Seasonal SOx emissions in kilograms.

Funding Sources: This research and data collection were funded by Amazon Web Services (AWS) and Smith School of Enterprise and The Environment (University of Oxford).