Full Citation

Title: Using Neural Networks to Predict Micro-Spatial Economic Growth

Citation Type: Working Paper

Publication Year: 2021

ISBN:

ISSN:

DOI: 10.3386/W29569

NSFID:

PMCID:

PMID:

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.

Url: https://www.nber.org/papers/w29569

User Submitted?: No

Authors: Khachiyan, Arman; Thomas, Anthony; Zhou, Huye; Hanson, Gordon H.; Cloninger, Alex; Rosing, Tajana; Khandelwal, Amit

Series Title: NBER Working Paper Series

Publication Number: 29569

Institution: National Bureau of Economic Research

Pages: 1-35

Publisher Location: Cambridge, MA

Data Collections: IPUMS NHGIS

Topics: Population Data Science

Countries: