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.