Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Google Earth Engine for Machine Learning & Change Detection

Name: Google Earth Engine for Machine Learning & Change Detection
Rating: 4.2 (507 reviews)

Become an expert in spatial analysis & Remote Sensing machine learning for land use and land cover mapping in GEE

Created byKatie Alison, Georg Müller

Last updated 6/2026

English

What you'll learn

Students will gain access to and a thorough knowledge of the Google Earth Engine platform
Implement machine learning algorithms on geospatial (satellite images) data in Earth Engine for LULC mapping
Get introduced and advance JavaScript skills on Google Earth Engine platform
Fully understand the main types of Machine Learning (supervised and unsupervised learning)
Learn how to apply supervised and unsupervised Machine Learning algorithms in Google Earth Engine
Learn how to obtain satellite data, apply image preprocessing, create training and validation data in Google Earth Engine
Implement calculation of change detection (pre and post-event detection) based on spectral indices
You'll have a copy of the codes used in the course for your reference

Course content

8 sections • 40 lectures • 6h 8m total length

Introduction2:56
Introduction: Machine Learning9:27

Why to work with Google Earth Engine?7:27
Using cloud platform for spectral indices & land cover analysis: EO browser19:15
Explore how the ESA EO Browser enables cloud-based visualization and on-the-fly computation of spectral indices from Sentinel and Landsat data for land cover and vegetation monitoring.
Lab: Sign up for Google Earth Engine3:37
The updated procedure for signing in to Google Earth Engine in 2026 is provided in the Resources section of this video.
Interface of Google Earth Engine: Code Editor & Explorer8:56
Overview of datasets in GEE5:30

Lab: Introduction to Javascript14:06
Lab: Declaring variables in Javascript in GEE5:17
Lab: Mapping and Reducing Collection - Landsat Example13:34
Lab: Working with image collections and image visualization21:54
Lab: Image Calculations - Create a composite and calculate NDVI5:42
Learn to create a satellite image composite and calculate the normalized difference vegetation index (ndvi) in Google Earth Engine using bands, function operations, and expression-based workflows.
Lab: Short introduction to functions - Maximum NDVI Example10:37
Lab: Image mosaicking, clipping, and reprojection8:21
Lab: Export image data from Google Earth Engine4:13
Practice your skills - the task1:23
Practice your skills in Google Earth Engine by applying JavaScript basics—change the area and time period, use Landsat images, and create and run your own image visualizations.

Section_Overview1:39
Introduction to Machine Learning in GIS and Remote Sensing9:27
Understanding Remote Sensing for LULC mapping6:59
Explore the basics of remote sensing for land use and land cover mapping, using spectral signatures and Landsat time-series to perform visual and automated change detection.
Introduction to LULC classification based on satellite images10:30
Supervised and unsupervised image classification9:31
Stages of LULC supervised classification12:18
Define mutually exclusive and exhaustive land use and land cover classes for supervised LULC classification. Collect representative training data, build spectral statistics, classify pixels, and assess accuracy to produce maps.
Lab: Machine Learning Classification in Google Earth Engine (Explorer)18:57

Common machine Learning algorithms for supervised learning19:18
Lab: Random Forest Classification in Earth Engine17:34
Learn to perform supervised land-cover classification in Google Earth Engine using sentinel imagery and a random forest classifier, including training data creation, class merging, and model deployment.
Lab: Supervised Machine Learning with CART12:18
Lab: Accuracy Assessment in GEE5:53
Accuracy Assessment of LULC maps11:13

On change detection: Theory7:35
Explore change detection in remote sensing by comparing multi-temporal classifications and images, using image differencing, post-classification comparison, and time-series trend analysis to reveal land degradation and crop dynamics.
Mapping Burnt Severity witn Nornalised Burnt Ration (NBR) Index: Theory3:13
Lab: Change Detection in GEE16:01
Learn to perform simple change detection in Google Earth Engine using Landsat 8 data, computing a normalized burn ratio to map post-fire burn severity in Chile 2016.
Advanced Analysis: Time Series Anomalies of Precipitation Data7:58
Advanced Analysis: Adding Legend Chart to precipitation anomalies map6:54
Your Final Project1:12
BONUS - QGIS preview - Map making in QGIS0:32

Requirements

A working computer with internet connection
An interest in working with geospatial data

Description

Land Use and Land Cover (LULC) Mapping and Change Detection with Machine Learning in Google Earth Engine

This course provides a complete, practical introduction to machine learning and change detection using Google Earth Engine (GEE). Designed for learners with basic GIS and Remote Sensing knowledge, this course will equip you with the skills to map land use and land cover, detect changes over time, and work confidently with satellite imagery for environmental analysis.

Course Highlights

• Extensive coverage of supervised and unsupervised machine learning algorithms
• Hands-on LULC classification and change detection workflows
• Real projects using Landsat, Sentinel, and other satellite datasets
• Step-by-step image preprocessing, spectral indices, and classification design
• Downloadable datasets and JavaScript code files
• Access to future updates and resources

Course Focus

The course emphasizes practical, project-based learning. You will build complete workflows in Google Earth Engine, from data acquisition and preprocessing to machine learning classification and change detection. By the end of the course, you will be able to apply state-of-the-art geospatial methods to your own professional or research projects.

Why Choose This Course

Unlike many theoretical courses, every lecture here focuses on actionable skills. You will develop real, applied expertise in Google Earth Engine, machine learning for Remote Sensing, and change detection analysis. These skills are highly in demand in GIS, environmental science, climate studies, land management, and academic research.

What You Will Learn

• How to sign in and navigate the Google Earth Engine interface
• Cloud-based data preprocessing and spectral indices calculation
• Introduction to JavaScript for geospatial analysis
• Fundamentals of machine learning for GIS and Remote Sensing
• Supervised and unsupervised image classification using GEE
• Training and validation data creation and accuracy assessment
• LULC change detection methods for multi-date satellite imagery
• How to build and complete your own geospatial project on GEE

Ideal For

This course is suited for geographers, GIS analysts, Remote Sensing professionals, environmental scientists, programmers, social scientists, geologists, and anyone who needs to produce LULC maps or perform change detection for their work or research.

Hands-On Practical Experience

You will complete multiple practical exercises using real satellite data. Step-by-step instructions, datasets, and code files are included so you can follow along and build your own cloud-based geospatial workflows.

Included in the Course

• All datasets used in lectures
• JavaScript code files for GEE
• Access to future resources and updates

Enroll Today

Start mastering land use and land cover mapping, Remote Sensing machine learning, and change detection in Google Earth Engine. Enroll now to unlock powerful skills for environmental monitoring and geospatial analysis.

Who this course is for:

Geographers, Programmers, geologists, biologists, social scientists, or every other expert who deals with GIS maps in their field

Google Earth Engine for Machine Learning & Change Detection

What you'll learn

Explore related topics

Course content

Introduction2 lectures • 12min

Getting started with Google Earth Engine & EO browser5 lectures • 45min

Basics of Jave Scrips for Google Earth Engine and first steps in image analysis9 lectures • 1hr 25min

Theory: on Machine Learning and Image CLassification7 lectures • 1hr 9min

Import Images and Image Collections in Google Earth Engine3 lectures • 27min

Unsupervised (K-means) image analysis in Google Earth Engine2 lectures • 20min

Supervised image analysis in Google Earth Engine5 lectures • 1hr 6min

Introduction to change detection and image time series in Google Earth Engine7 lectures • 43min

Requirements

Description

Who this course is for: