Using Neural Networks to Predict Micro-Spatial Economic Growth

Arman Khachiyan, Anthony Thomas, Huye Zhou, Gordon Hanson, Alex Cloninger, Tajana Rosing and Amit Khandelwal

No 29569, NBER Working Papers from National Bureau of Economic Research, Inc

Abstract: We apply deep learning to daytime satellite imagery to predict changes in income and population at high spatial resolution in US data. For grid cells with lateral dimensions of 1.2km and 2.4km (where the average US county has dimension of 55.6km), our model predictions achieve R2 values of 0.85 to 0.91 in levels, which far exceed the accuracy of existing models, and 0.32 to 0.46 in decadal changes, which have no counterpart in the literature and are 3-4 times larger than for commonly used nighttime lights. Our network has wide application for analyzing localized shocks.

JEL-codes: R0 (search for similar items in EconPapers)
Date: 2021-12
New Economics Papers: this item is included in nep-big, nep-cmp, nep-cwa, nep-geo and nep-ure
Note: ITI
References: Add references at CitEc
Citations:

Published as Arman Khachiyan & Anthony Thomas & Huye Zhou & Gordon Hanson & Alex Cloninger & Tajana Rosing & Amit K. Khandelwal, 2022. "Using Neural Networks to Predict Microspatial Economic Growth," American Economic Review: Insights, American Economic Association, vol. 4(4), pages 491-506, December.

Downloads: (external link)
http://www.nber.org/papers/w29569.pdf (application/pdf)

Related works:
Journal Article: Using Neural Networks to Predict Microspatial Economic Growth (2022)
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:nbr:nberwo:29569

Ordering information: This working paper can be ordered from
http://www.nber.org/papers/w29569

Access Statistics for this paper

More papers in NBER Working Papers from National Bureau of Economic Research, Inc National Bureau of Economic Research, 1050 Massachusetts Avenue Cambridge, MA 02138, U.S.A.. Contact information at EDIRC.
Bibliographic data for series maintained by ().