Large potential reduction in economic damages under UN mitigation targets
Nature, 557, 549–553 
Marshall Burke, W. Matthew Davis, Noah S. Diffenbaugh (2018)

fig1.jpg

We present an empirical framework for evaluating the economic benefits of the 2015 Paris Agreement’s temperature targets of 1.5°C and 2.0°. Our findings decompose the enormous uncertainty in such forecasting exercises and stress the inequity in impacts: it is a stark result that poorer countries that have historically contributed least to carbon emissions will likely be impacted most.


Combining satellite imagery and machine learning to predict poverty
Science, 353 (6301), 790-794.
Neal Jean, Marshall Burke, Michael Xie, W. Matthew Davis, Stefano Ermon, David Lobell (2016)

F1.large.jpg

We apply methods in computer vision to train a convolutional neural network to identify features in daytime satellite imagery informative of socioeconomic conditions. We perform a ridge-regression exercise combining the CNN with georeferenced data from household surveys in Uganda, Tanzania, Nigeria, Malawi, and Rwanda to generate fine-scale “poverty maps,” which estimate the distribution of consumption expenditure and asset wealth. We emphasize the entire pipeline uses only freely accessible data and software, enabling straightforward replication and potential scalability.


In progress:

  • Dispersion of temperature exposure and economic growth: evidence from panel data with implications for climate change and global inequality
    (thesis supervised by Prof. Elizabeth Baldwin and Prof. Sir David Hendry)

  • Welfare implications of remote sensing-assisted methods of targeting aid
    (with Stanford SustainLab)