Google Earth Engine Course

Lesson 1 • Core Geospatial Concepts for GEE

Reviews coordinate systems, projections, and raster vs. vector data as applied in GEE. Provides the spatial vocabulary needed for all subsequent chapters.

Lesson 2 • Exploring the Code Editor Interface

Tours all Code Editor panels, toolbars, and keyboard shortcuts. Students run their first script and interpret console output.

Lesson 3 • What Is Google Earth Engine

Defines GEE as a cloud-based geospatial analysis platform and contrasts it with desktop GIS. Establishes why GEE matters for large-scale environmental monitoring.

Lesson 1 • JavaScript Syntax and Data Types

Covers variables, primitive types, and operators as used in GEE scripts. Connects syntax rules directly to GEE API patterns students will encounter.

Lesson 2 • Arrays, Objects, and Dictionaries

Explains JavaScript arrays and objects as the basis for GEE feature properties and metadata. Students manipulate structured data before moving to GEE objects.

Lesson 3 • Debugging and Code Organization

Introduces print statements, error messages, and modular script structure. Students learn to isolate bugs quickly, a skill critical for complex GEE pipelines.

Lesson 1 • Loading Images and Image Collections

Covers ee.Image and ee.ImageCollection constructors and their differences. Students load satellite imagery and inspect its properties programmatically.

Lesson 2 • Filtering Image Collections

Teaches date, bounds, and property filters to reduce collections to relevant subsets. Efficient filtering is foundational to all time-series and regional analyses.

Lesson 3 • Key Satellite Datasets in GEE

Surveys Landsat, Sentinel, MODIS, and elevation datasets with their trade-offs. Students select the right dataset based on spatial, temporal, and spectral needs.

Lesson 1 • Image Visualisation and Styling

Configures visualisation parameters for true-colour, false-colour, and index maps. Effective visualisation communicates analytical results clearly to any audience.

Lesson 2 • Computing Spectral Indices

Derives NDVI, NDWI, NDBI, and EVI from raw bands using band math. Spectral indices are the most common analytical output in remote sensing workflows.

Lesson 3 • Arithmetic and Logical Operations

Covers add, subtract, multiply, divide, and bitwise operations on image bands. Students build custom expressions combining multiple spectral bands.

Lesson 4 • Band Selection and Renaming

Teaches selecting specific bands and standardising band names across sensors. Consistent naming prevents errors in multi-sensor workflows.

Lesson 1 • Importing and Exporting Vector Data

Uploads shapefiles and GeoJSON as GEE assets and exports results to Drive or Cloud Storage. Data exchange skills connect GEE to external GIS workflows.

Lesson 2 • Geometry Types and Construction

Builds points, lines, polygons, and multi-geometries using GEE geometry constructors. Geometry creation is the entry point for all region-based analyses.

Lesson 3 • Creating and Managing Features

Wraps geometries with attribute properties to form ee.Feature objects. Features bridge vector geometry and tabular data for spatial queries.

Lesson 1 • Grouped and Conditional Reductions

Performs grouped reductions by class and conditional statistics using masks. These techniques enable per-class summaries essential for land cover analysis.

Lesson 2 • Neighbourhood and Kernel Reducers

Applies focal statistics and convolution kernels for spatial smoothing and edge detection. Neighbourhood operations enhance image quality and support texture analysis.

Lesson 3 • Spatial Reduction and Region Statistics

Computes per-region statistics using reduceRegion() and reduceRegions(). These methods extract quantitative summaries for any polygon or point dataset.

Lesson 4 • Understanding Reducers in GEE

Explains the reducer concept as a function that aggregates pixel values across dimensions. Reducers underpin compositing, zonal stats, and time-series summarisation.

Lesson 1 • Trend Analysis with Linear Regression

Fits pixel-wise linear trends to time-series stacks using GEE's linearFit() reducer. Trend maps reveal long-term greening, browning, or urbanisation patterns.

Lesson 2 • Building Time-Series Image Stacks

Constructs annual and monthly image stacks from filtered collections using map() and reduce(). Stacks are the foundation for all temporal trend and change analyses.

Lesson 3 • Advanced Change Detection Algorithms

Applies LandTrendr and CCDC concepts for continuous change monitoring in GEE. These algorithms detect abrupt disturbances and gradual transitions in land cover.

Lesson 4 • Charting Time-Series Data

Uses the ui.Chart API to plot pixel and region time series interactively. Charts reveal seasonal patterns and anomalies that maps alone cannot show.

Lesson 1 • Supervised Classification Workflow

Outlines the end-to-end pipeline from training data collection to classified map output. Understanding the full workflow prevents common errors in each subsequent step.

Lesson 2 • Training and Applying Classifiers

Trains Random Forest, SVM, and CART classifiers and applies them to full images. Students compare classifier outputs and select the best performer for their dataset.

Lesson 3 • Unsupervised Classification with K-Means

Applies k-means clustering to discover spectral groups without labelled training data. Unsupervised methods are useful for exploratory analysis and training data guidance.

Lesson 4 • Collecting and Managing Training Data

Creates training polygons in the Code Editor and merges them into a labelled feature collection. Quality training data is the single largest determinant of classifier accuracy.