This paper proposes a methodology for predicting subnational economic development using high-resolution, daytime satellite imagery. We collected high-resolution satellite images and corresponding open-source ground-truth data for over 28 million 1km x 1km grid cells covering 25 European countries. We first use a standard random forest model to identify a subset of features from the ground truth data (e.g. buildings, roads) that best predict fixed capital at the EU-NUTSII level. We then train a convolutional neural network (CNN) to extract the relevant features from each daytime satellite image. The resulting measures are used to predict fixed apital at the EU-NUTSII level. In the final step, the predicted capital values are used in a standard development accounting framework to construct regional GDP per capita at the NUTSII level. The correlation between our constructed regional GDP and official GDP figures is around 0.7. As such, our methodology can be used to predict subnational and national GDP for countries were this data is either missing or unreliable.
Begin of page section:
Page settings:
End of this page section. Go to overview of page sections
Begin of page section:
Search:
Close
End of this page section. Go to overview of page sections
Search
Begin of page section:
Main navigation:
Page navigation:
- University
University
Developing solutions for the world of tomorrow - that is our mission. Our students and our researchers take on the great challenges of society and carry the knowledge out. - Research Profile
Research Profile
Scientific excellence and the courage to break new ground. Research at the University of Graz creates the foundations for making the future worth living. - Studies
Studies
Where is the best place to study? At the University of Graz. In an inspiring atmosphere of learning and research. With about 120 studies to choose from. For your way to the future. - Community
Community
The University of Graz is a hub for international research and brings together scientists and business experts. Moreover, it fosters the exchange and cooperation in study and teaching. - Spotlight
End of this page section. Go to overview of page sections
Begin of page section:
You are here:
University of Graz Events T4S-Seminar: Measuring Economic Development with Daytime Satellite Imagery
End of this page section. Go to overview of page sections
19.09.2019
12:00 - 13:30
Wegener Center
Seminarraum - 1.Stock, Brandhofgasse 5
Begin of page section:
Additional information:
End of this page section. Go to overview of page sections
End of this page section. Go to overview of page sections