The Project Climate Change, Health, and Artificial Intelligence (Project CCHAIN) dataset is a validated, open-sourced linked dataset measuring 20 years (2003-2022) of climate, environmental, socioeconomic, and health dimensions at the barangay (village) level across twelve Philippine cities (Dagupan, Palayan, Navotas, Mandaluyong, Muntinlupa, Legazpi, Iloilo, Mandaue, Tacloban, Zamboanga, Cagayan de Oro, Davao). The full documentation can be accessed here.

The tables are designed in a way that users can choose variables that are most relevant to their focus city and use case, and link these variables to form a single dataset by merging using standard geography codes and calendar dates. This can be done using the provided linking notebook, or offline using the user's own code.

Here are some tips on how make most use of this dataset:

• Focus on one location. Starting with a detailed analysis of one location allows for a better understanding of the local dynamics, which may differ across locations.
• Do not use all variables at once- do a literature review first to identify possible key variables. to identify possible key variables. More often than not, using all variables is not necessary and may even yield subpar results.
• Check data availability on your focus location and make sure they fit the requirements of your study.