维数(图论)
网格单元
计量经济学
人工神经网络
经济
网格
人口
卫星
地理
计算机科学
大地测量学
物理
数学
人工智能
人口学
社会学
纯数学
天文
作者
Arman Khachiyan,Anthony Thomas,Huye Zhou,Gordon H. Hanson,Alex Cloninger,Tajana Rosing,Ankur Khandelwal
出处
期刊:The American economic review
[American Economic Association]
日期:2022-12-01
卷期号:4 (4): 491-506
被引量:5
标识
DOI:10.1257/aeri.20210422
摘要
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 R 2 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)
科研通智能强力驱动
Strongly Powered by AbleSci AI