Explore our demo notebooks to understand various use cases of Population Dynamics embeddings.

Notebook	Description
Custom boundary aggregation Colab	Demonstrates how to aggregate S2 cell embeddings into custom polygonal boundaries using Earth Engine population data to create population-weighted machine learning features.
Economic forecasting Colab	Demonstrates how to integrate S2 cell embeddings with Data Commons economic data to train machine learning models for county-level time-series forecasting.
Nowcasting Colab*	Uses past and partial present-day data for a county-level target variable to predict outcomes for remaining counties.
Superresolution and imputation Colab*	Helps train a model at the county level on a target variable to predict at the ZIP code level. Also demonstrates imputation (training on 20% of ZIP codes and predicting for the remaining 80%).
Nighttime lights prediction with Earth Engine Colab*	Illustrates how Earth Engine data, such as nighttime lights, can also be predicted from the embeddings, enhancing geospatial understanding for environmental and socioeconomic forecasting.
Prediction using global embeddings*	Illustrates the usage of global embeddings by setting up a multi-country model to predict for a new country.

* This notebook uses ZIP code embeddings and needs to be updated to S2 cells.