BEGIN:VCALENDAR
PRODID:-//T4Science Presentation Calendar//
VERIONS:2.0
BEGIN:VEVENT
SUMMARY:Measuring Economic Development with Daytime Satellite Imagery (by 
 Paul A. Raschky)
DTSTART:20190919T100000Z
DTEND:20190919T113000Z
DTSTAMP:20190812T103711Z
UID:presentation-96.series-5
DESCRIPTION:This paper proposes a methodology for predicting subnational e
 conomic development using high-resolution\, daytime satellite imagery. We 
 collected high-resolution satellite images and corresponding open-source g
 round-truth data for over 28 million 1km x 1km grid cells covering 25 Euro
 pean countries. We first use a standard random forest model to identify a 
 subset of features from the ground truth data (e.g. buildings\, roads) tha
 t best predict fixed capital at the EU-NUTSII level. We then train a convo
 lutional neural network (CNN) to extract the relevant features from each d
 aytime satellite image. The resulting measures are used to predict fixed c
 apital at the EU-NUTSII level. In the  final step\, the predicted capital 
 values are used in a standard development accounting framework to construc
 t 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.
LOCATION:SR Wegener Center\, Brandhofgasse 5\, 1st floor
ORGANIZER;CN="Douglas Maraun";ROLE=CHAIR:MAILTO:douglas.maraun@uni-graz.at
END:VEVENT
END:VCALENDAR