Using Neural Networks to Predict Microspatial Economic Growth-Reference-Cited by-同舟云学术

Using Neural Networks to Predict Microspatial Economic Growth

Published:2022-12-01 Issue:4 Volume:4 Page:491-506
ISSN:2640-205X
Container-title:American Economic Review: Insights
language:en
Short-container-title:American Economic Review: Insights

Author:

Khachiyan Arman¹,Thomas Anthony²,Zhou Huye³,Hanson Gordon⁴,Cloninger Alex⁵,Rosing Tajana²,Khandelwal Amit K.⁶

Affiliation:

1. Department of Economics, University of San Francisco (email: )

2. Department of Computer Science and Engineering, UC San Diego (email: )

3. Department of Mathematics, UC San Diego (email: )

4. Harvard Kennedy School, Harvard University, and National Bureau of Economic Research (email: )

5. Department of Mathematics and Halıcıoğlu Data Science Institute, UC San Diego (email: )

6. Economics Division, Columbia Business School, and National Bureau of Economic Research (email: )

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 1.2 km and 2.4 km (where the average US county has dimension of 51.9 km), 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 C45, R11, R23)

Publisher

American Economic Association

Subject

Management, Monitoring, Policy and Law,Geography, Planning and Development

Link

https://pubs.aeaweb.org/doi/pdf/10.1257/aeri.20210422

Reference46 articles.

1. Abadi, Martín, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, etal 2016. "TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems." arXiv: 1603.04467.

2. Akbar, Prottoy A., Victor Couture, Gilles Duranton, and Adam Storeygard. 2018. "Mobility and Congestion in Urban India." NBER Working Paper 25218.

3. Babenko, Boris, Jonathan Hersh, David Newhouse, Anusha Ramakrishnan, and Tom Swartz. 2017. "Poverty Mapping Using Convolutional Neural Networks Trained on High and Medium Resolution Satellite Images, with an Application in Mexico." arXiv: 1711.06323.

4. Roads, Railroads, and Decentralization of Chinese Cities

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Small Area Estimation of Poverty and Wealth Using Geospatial Data: What have We Learned So Far?;Calcutta Statistical Association Bulletin;2023-12-04

2. Learning income levels and inequality from spatial and sociodemographic data in Germany;Applied Geography;2023-10

3. A Spatial Perspective on Booms and Busts: Evidence from Türkiye;Policy Research Working Papers;2023-08-24

4. Accounting for spatial economic interactions at local and meso scales in integrated assessment model (IAM) frameworks: challenges and recent progress;Environmental Research Letters;2023-03-01