Satellites turn “concrete”: Tracking cement with satellite data and neural networks
Alexandre d'Aspremont (),
Simon Ben Arous,
Jean-Charles Bricongne,
Benjamin Lietti () and
Baptiste Meunier
Additional contact information
Alexandre d'Aspremont: LIENS - Laboratoire d'informatique de l'école normale supérieure - DI-ENS - Département d'informatique - ENS-PSL - ENS-PSL - École normale supérieure - Paris - PSL - Université Paris Sciences et Lettres - Inria - Institut National de Recherche en Informatique et en Automatique - CNRS - Centre National de la Recherche Scientifique - CNRS - Centre National de la Recherche Scientifique, SIERRA - Statistical Machine Learning and Parsimony - DI-ENS - Département d'informatique - ENS-PSL - ENS-PSL - École normale supérieure - Paris - PSL - Université Paris Sciences et Lettres - Inria - Institut National de Recherche en Informatique et en Automatique - CNRS - Centre National de la Recherche Scientifique - CNRS - Centre National de la Recherche Scientifique - Centre Inria de Paris - Inria - Institut National de Recherche en Informatique et en Automatique, Kayrros
Simon Ben Arous: Kayrros
Benjamin Lietti: EPEE - Centre d'Etudes des Politiques Economiques - UEVE - Université d'Évry-Val-d'Essonne - Université Paris-Saclay
Post-Print from HAL
Abstract:
This paper exploits daily infrared images taken from satellites to track economic activity in advanced and emerging countries. We first develop a framework to read, clean, and exploit satellite images. Our algorithm uses the laws of physics (Planck's law) and machine learning to detect the heat produced by cement plants in activity. This allows us to monitor in real-time whether a cement plant is working. Using this on around 1,000 plants, we construct a satellitebased index. We show that using this satellite index outperforms benchmark models and alternative indicators for nowcasting the production of the cement industry as well as the activity in the construction sector. Comparing across methods, neural networks appear to yield more accurate predictions as they allow to exploit the granularity of our dataset. Overall, combining satellite images and machine learning can help policymakers to take informed and swift economic policy decisions by nowcasting accurately and in real-time economic activity.
Keywords: Big data; Data science; Machine learning; Construction; High-frequency data (search for similar items in EconPapers)
Date: 2024
Note: View the original document on HAL open archive server: https://hal.science/hal-05104995v1
References: Add references at CitEc
Citations:
Published in Journal of Econometrics, 2024, 249, pp.105923. ⟨10.1016/j.jeconom.2024.105923⟩
Downloads: (external link)
https://hal.science/hal-05104995v1/document (application/pdf)
Related works:
Journal Article: Satellites turn “concrete”: Tracking cement with satellite data and neural networks (2025) 
Working Paper: Satellites turn “concrete”: tracking cement with satellite data and neural networks (2024) 
Working Paper: Satellites Turn Concrete: Tracking Cement with Satellite Data and Neural Networks (2023) 
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:hal:journl:hal-05104995
DOI: 10.1016/j.jeconom.2024.105923
Access Statistics for this paper
More papers in Post-Print from HAL
Bibliographic data for series maintained by CCSD ().