Earth Engine Track

The current Google Earth Engine implementation track.

Getting Started with GEE

Register a Google Earth Engine account and set up access through the JavaScript code editor or the Python API with geemap.

JavaScript vs Python

Comparing the Earth Engine JavaScript code editor and the Python API to choose the right interface for your workflow.

Data Structures and Methods

Core Earth Engine data types including Image, ImageCollection, Geometry, Feature, FeatureCollection, Reducer, and Join.

Detailed Data Structures and Methods

A deeper look at Earth Engine raster images, bands, metadata, and image collections organized as temporal stacks.

Machine Learning in Earth Engine

Built-in Earth Engine machine learning for pixel classification and regression with algorithms like Random Forest and SVM.

Server vs. Client

The distinction between client-side and server-side operations in Earth Engine and why it matters for efficient processing.

Python Environment

Setting up a Python environment for Earth Engine work, weighing Google Colab against local package and environment managers like Anaconda.

Digital Images

How digital images work as pixel matrices, and how geospatial raster imagery extends them with bands and spatial reference.

Resolution

The spatial, temporal, and radiometric resolution of satellite platforms and how to choose the right data for an analysis.

Visualizing Images

Searching imagery in Earth Engine and building true and false color composites, with the difference between radiance and reflectance.

Indices

Building and visualizing spectral indices like NDVI from Landsat 8 bands to separate land cover by reflectance.

Transformations

Linear transforms of image bands, including the Tasseled Cap rotation, to create weighted composites for analysis.

Classification

Supervised and unsupervised land cover classification in Earth Engine using Random Forest, CART, and ee.Clusterer.

Time Series Modeling

Foundations of time series analysis on remotely sensed data, covering decomposition, autocorrelation, and modeling change over decades.

Nighttime Lights Appendix

Using nighttime lights imagery as a proxy for economic development, as a companion to the World Bank Open Nighttime Lights tutorial.