A geospatial approach to measuring economic activity
Abstract
We introduce a methodology to detect and measure economic activity using geospatial data and apply it to steel production, a major industrial pollution source worldwide. Combining plant output data with geospatial data, such as ambient air pollutants, nighttime lights, and temperature, we train machine learning models to predict plant locations and output. We identify about 88% (94%) of plants missing from the training sample within a 1 km (5 km) radius and achieve R ² above 0.8 for output prediction at a 1 km grid and at the plant level, as well as both regional and time series validations. We use the model trained on Chinese steel data to reliably detect the location and measure the total annual output of steel plants in South Korea and Iran. Our approach can be adapted to other industries and regions, and used by policymakers and researchers to track and measure industrial activity in near real time.
Related
- Techno-Economic and Geospatial Assessment of Distributed Fertilizer Production via Wastewater Ammonia Solar Electrochemical Stripping
- Economic Corridor Detection from Multi-Source Earth Observation and Commercial Geospatial Data Across Nigeria's Kilometre-Scale Grid
- RevEmo: A Conceptual Framework for Measuring the Economic Contribution of Human Moments in AI-Mediated Hospitality
- D.3. Round Table: Measuring the Economic Burden of Disease: Methods, Values and Policy Relevance
- The Economics of Belonging Measuring Economic and Social Achievement across Nations
BibTeX
@article{yang2026geospatial,
title = {{A geospatial approach to measuring economic activity}},
author = {Anton Yang and Jianwei Ai and Costas Arkolakis},
journal = {Nature Communications},
year = {2026},
month = nov,
doi = {10.1038/s41467-026-78786-1},
url = {https://www.nature.com/articles/s41467-026-78786-1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A geospatial approach to measuring economic activity
AU - Anton Yang
AU - Jianwei Ai
AU - Costas Arkolakis
PY - 2026
DA - 2026/11/03
JO - Nature Communications
DO - 10.1038/s41467-026-78786-1
UR - https://www.nature.com/articles/s41467-026-78786-1
AB - We introduce a methodology to detect and measure economic activity using geospatial data and apply it to steel production, a major industrial pollution source worldwide. Combining plant output data with geospatial data, such as ambient air pollutants, nighttime lights, and temperature, we train machine learning models to predict plant locations and output. We identify about 88% (94%) of plants missing from the training sample within a 1 km (5 km) radius and achieve R ² above 0.8 for output prediction at a 1 km grid and at the plant level, as well as both regional and time series validations. We use the model trained on Chinese steel data to reliably detect the location and measure the total annual output of steel plants in South Korea and Iran. Our approach can be adapted to other industries and regions, and used by policymakers and researchers to track and measure industrial activity in near real time.
SN - 2041-1723
ER -