LEARNING
Learn geospatial analysis techniques for development research. Our modules are designed to be accessible to all audiences regardless of technical background.
SUGGESTED LEARNING PATH
Follow our recommended path or jump to any module that interests you.
Start with the basics of satellite imagery and remote sensing applications.
Learn about nighttime lights data and the Google Earth Engine API.
Dive deeper into calibrated nighttime lights analysis.
Create population-weighted wealth maps and statistics.
Build ML models to identify crop types from satellite imagery.
2 of 9 modules started
Register to save your progress and get notified about new modules.
Subscribe to receive alerts when new training modules, datasets, or learning materials are added.
ALL MODULES
The Geo4Dev initiative offers a suite of learning modules aimed at training researchers and analysts to use novel geographic datasets and methods. Contact info@geo4.dev to develop a module.
This tutorial provides guidance on creating a machine learning model to identify crop types from satellite imagery and other earth observation data. For users with known crop locations, it demonstrates the steps to train a model and predict crop locations for a wider area.
Geospatial data plays a significant role in supporting impact evaluations. This module covers remotely collected data from sensors, drones, and satellites, examining forest coverage, vegetation, crops, water, air quality, buildings, and infrastructure.
This tutorial guides users through creation of population-weighted wealth maps and statistics, a product of collaboration between CEGA and Facebook Data for Good. Learn how population and wealth data are joined, aggregated, and weighted.
Drawing from Gonzalez-Navarro and Turner's work on nighttime lights and urban growth, this tutorial focuses on analysis of data from sensors calibrated to avoid saturation of urban centers for granular economic analysis.
This tutorial makes novel data from "Subways and Urban Growth" accessible to all audiences, demonstrating code to import subway data, select locations of interest, create statistics, and build maps and visualizations.
Information about vegetation coverage changes enables study across natural and social sciences. This tutorial provides an introduction to and demonstration of the MODIS Vegetation Continuous Fields (VCF) product.
Introduction to nighttime lights data and the Google Earth Engine API. Learn the fundamentals of accessing and analyzing nighttime light satellite data for research and development applications.
Create a machine learning model to predict maize yields from satellite imagery and earth observation data. Training uses variety trial data collected by CIMMYT for practical crop yield prediction.
Create a predictive modeling workflow to quantify woody cover from remote sensing datasets including Airborne LiDAR and Synthetic Aperture Radar (SAR), inspired by Wessels et al. (2023) research.