Note that while many Global Policy Lab (GPL) repositories are hosted under our organization account, there are also many repositories that are hosted under individual accounts. For this reason, code for specific projects is hyperlinked below. For questions, contact Luke Sherman via [email protected].

We divide our code into two sections: (1) Code-based tools and packages for general and (2) Replication code for research projects. The former is designed to be continuously improved and updated, while the latter is not.

Code-based tools and packages are designed for general use in the research community. We encourage researchers using our code-based tools and packages to make contributions via pull request. For questions, contact Luke Sherman via [email protected].

• Cider - Python package for poverty prediction and targeting with mobile phone metadata. Code available. Documentation available. See also Aiken et al, 2022.

• SFD - R code for for computing the spatial first differences (SFD) estimator. SFD is a research design that exploits the spatial structure of the data to address unobservable heterogeneity in cross section. Code available. See also Druckenmiller and Hsiang, 2018.

Research project code must persist for replication purposes. It will not typically be updated following the publication of the corresponding research paper.

• Young and Hsiang (2024). Mortality caused by tropical cyclones in the United States. Nature. Code available. Data Available.

• Sherman et al (2023). Global High Resolution Estimates of the Human Development Index using Satellite Imagery and Machine Learning. NBER Working Paper. Code available. Data available.

• Chi et al (2022). Micro-estimates of wealth for all low- and middle-income countries. PNAS. Code available. Website. Data availabe.
• Krasovich et al (2022). Harmonized nitrogen and phosphorus concentrations in the Mississippi/Atchafalaya River Basin from 1980 to 2018. Scientific Data. Code available.
• Aiken et al (2022). Machine learning and phone data can improve targeting of humanitarian aid. Nature. Code available.
• Smythe and Blumentsock (2022). Geographic microtargeting of social assistance with high-resolution poverty maps PNAS. Code available.

• Ilin et al (2021). Public mobility data enables COVID-19 forecasting and management at local and global scales. Scientific Reports. Code and data available by request.
• Rolf et al (2021). A generalizable and accessible approach to machine learning with global satellite imagery. Nature Communications. Code available. Website.
• Huang et al (2021). Using Satellite Imagery and Deep Learning to Evaluate the Impact of Anti-Poverty Programs. NBER Working Paper. Code available.

• Hsiang et al (2020). The effect of large-scale anti-contagion policies on the COVID-19 pandemic. Nature. Code available. Website.

• Englander et al (2019). Property rights and the protection of global marine resources Nature Sustainability. Code available.

• Druckenmiller and Hsiang (2018). Accounting for Unobservable Heterogeneity in Cross Section Using Spatial First Differences. NBER Working Paper. Code available.

Older projects will be listed soon