Teach on Udemy

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

Learn More

Your cart is empty.

Keep shopping

Machine Learning in R: Image Classification in land use LULC

Name: Machine Learning in R: Image Classification in land use LULC
Rating: 4.3 (127 reviews)

Learn supervised machine learning in R 4 Remote Sensing, image classification, and land use and land cover LULC mapping

Created byKatie Alison

Last updated 11/2025

English

What you'll learn

Learn supervised machine learning for image classification using R-programming language in R-Studio
Learn theoretical background of Machine Learning
Apply machine learning based algorithms (random forest, SVM) for image classification analysis in R and R-Studio
Learn R-programming from scratch: R crash course is included that you could start R-programming for machine learning
Fully understand the basics of Land use and Land Cover (LULC) Mapping based on satellite image classification
Get an introduction and fully understand to Remote Sensing relevant for LULC mapping
Pre-process and analyze Remote Sensing images in R
Learn how to create training and validation data for image classification in QGIS
Build machine learning based image classification models for LUCL analysis and test their robustness in R
Implement Machine Learning algorithms, such as Random Forests, SVM in R
Apply accuracy assessment for Machine Learning based image classification in R
You'll have a copy of the scripts and step-by-step manuals used in the course for your reference to use in your analysis.

Course content

7 sections • 47 lectures • 5h 38m total length

Introduction6:42
What is R and RStudio?2:43
How to install R and RStudio in 20213:40
Install R and RStudio by downloading R from the comprehensive archive network and installing RStudio, choosing your operating system (Windows, Mac, or Linux) and following a simple step-by-step setup.
Lab: Install R and RStudio in 20215:33
Lab: Installing QGIS and install SCP12:39
Learn how to download and install QGIS on Windows, choose between latest releases and long-term releases, select 64-bit installers, accept the license, and launch the desktop QGIS with projects.
A note on QGIS versions and it's plug-ins8:44
Navigate the QGis website to select stable versions and install older QGis and plugin versions, including the semi-automatic classification and KSP plugins, via archived files and installing from zip.

Lab: Introduction to RStudio Interface9:37
Lab: Installing Packages and Package Management in R4:19
Variables in R and assigning Variables in R2:19
Lab: Variables in R and assigning Variables in R1:45
Overview of data types and data structures in R8:19
Explore how R uses objects and symbols to store data, covering atomic vector types (numeric, integer, character, logical, complex) and attributes. Learn to work with factors and levels.
Lab: data types and data structures in R9:57
Vectors' operations in R7:37
Data types and data structures: Factors2:32
Dataframes: overview in R3:21
Functions in R - overview4:50
Explore control structures in R, including if and else statements and vectorized forms, and learn how to print results and apply conditional logic to vectors.
For Loops in R3:56
Read Data into R5:13
Learn to input data into R by reading Excel, CSV, and text files, set the working directory, specify headers and separators, and preview and summarize data.

Data used for analysis: Landsat images5:06
Preprocessing of satellite image data5:01
Learn to reprocess optical remote sensing data through radiometric and geometric corrections, atmospheric correction, and data subsetting, using Landsat 8 level 1/2 and Sentinel-2 products converted to GeoTIFF.
Overview of processing steps in R for Landsat images2:37
Lab: Image load in R7:15
Load Landsat image data into RStudio with the raster package, define and verify the file path, then unzip the dataset into a folder named after the file.
Lab: Image Layerstacks in R8:59
Lab: Batch Processing in R: unzipp, laerstack of LAndsat images5:17
Visualize images in R7:43
Explore visualizing Landsat images in R by creating single-band and true color composites, cropping and subsetting images, and analyzing histograms of the green band to assess land cover features.

Data used for analysis: Sentinel images6:18
Training data requirements for classification and training data selection7:15
Lab: Prepare training data in R - part 17:16
Lab: Prepare training data in R - part 29:40
Prepare training data in R by converting the shapefile's class names to numeric factors (1–5), renaming raster bands, and extracting pixel values into a data frame for the classifier.
Plotting spectral signatures in R5:28

Image Classification in R with Random Forest in R14:29
Map visualization: Creating classified image based on Random Forest model in R9:15
Extrapolate the saved random forest model to the Landsat image, predict pixel classes, and visualize results to assess initial accuracy. Revisit training data if misclassifications appear to improve map quality.
Map visualization: Create a classified image based on RF model in QGIS5:31
Image Classification in R with Support Vector Machines (SVM) in R15:48
Accuracy assessment of image classification11:13
Explore accuracy assessment of image classification using confusion matrices, visual and quantitative controls, and key metrics like overall, user, and producer accuracy, with emphasis on reference data sources.
Lab: Accuracy Assessment (validation) of classification in R11:33
Independent Task: Accuracy assessment for SVM-based classification1:15
Students validate support vector machines classification using provided code, compute uzak accuracy, producer accuracy, overall accuracy, and the copper coefficient on the same validation dataset used for the random forest.
Lab: Creating a LULC map of your final image classification result in QGIS5:03
Map project0:32
BONUS2:12

Requirements

Availability computer and internet & strong interest in the topic
The course will be demonstrated on Windows PC. Mac and Linux users will have to adapt the instructions to their operating systems.

Description

Machine Learning in R: Image Classification for Land Use and Land Cover (LULC) Mapping

This course provides a practical and accessible introduction to supervised machine learning in R and R-Studio for Remote Sensing, satellite image analysis, and land use and land cover (LULC) mapping. You will learn how to build, run, and evaluate image classification models using real satellite imagery and widely used machine learning algorithms.

Why Should GIS and Remote Sensing Professionals Learn R?

R is one of the world’s leading languages for data science, statistics, and geospatial analysis. With millions of users worldwide and rapidly growing adoption across research institutions, environmental organizations, and analytical industries, R is now a core skill for professionals working with spatial data. This course shows you how to apply R to real Remote Sensing tasks, giving you a powerful and modern skill set for geospatial analysis.

Course Highlights

This course guides you through the full machine learning workflow for image classification in R. You will learn how to use supervised learning methods such as Random Forest and SVM to classify satellite imagery, evaluate model accuracy, and interpret LULC results. You will work with data from Landsat, Sentinel, and other sources, and learn how to prepare training and validation data in QGIS.

What You Will Learn

• Understand the fundamentals of machine learning for Remote Sensing
• Learn R and R-Studio from the ground up
• Apply Random Forest, SVM, and other supervised machine learning algorithms
• Perform land use and land cover (LULC) classification using satellite imagery
• Prepare training and validation datasets in QGIS
• Build and evaluate machine learning models for image classification in R
• Apply accuracy assessment and model validation techniques
• Understand essential Remote Sensing concepts for LULC mapping
• Work confidently with real geospatial datasets in R
• Apply machine learning to Landsat, Sentinel, and other imagery sources

No Prior Knowledge Required

No R, programming, or statistics background is needed. The course begins with core concepts and gradually introduces more advanced machine learning techniques. All code is explained step by step and demonstrated through practical examples.

Hands-On Practical Experience

You will receive scripts, exercises, and real datasets, allowing you to follow every step of the workflow from data preparation to final classification. You will build your own machine learning models, test them, and evaluate them using standard accuracy assessment techniques.

Who This Course Is For

This course is ideal for GIS analysts, Remote Sensing specialists, environmental scientists, geographers, programmers, students, researchers, and anyone who wants to use machine learning and R for image classification and geospatial analysis. It is suitable for complete beginners.

Join Today and Advance Your Geospatial Skills

Enroll now to learn how to use R for machine learning, Remote Sensing, and land use and land cover mapping, and take a major step toward becoming a more skilled and competitive geospatial professional.

Who this course is for:

Everyone who would like to learn Data Science Applications in the R & R Studio Environment
Geographers, Programmers, geologists, biologists, social scientists, or every other expert who deals with GIS maps in their field

Machine Learning in R: Image Classification in land use LULC

What you'll learn

Explore related topics

Course content

Introduction6 lectures • 40min

Machine Learning for image classification: theory overview3 lectures • 45min

Introduction to R-Studio and R: crash course12 lectures • 1hr 4min

Basics of Remote Sensing for LULC mapping: theory overview4 lectures • 36min

Satellite image preparation in R for Land use / land cover (LULC) analysis in R7 lectures • 42min

Training data Preparation in R for Machine Learning image classification5 lectures • 36min

Land Use/Land Cover Image Classification using Machine Learning algorithms in R10 lectures • 1hr 17min

Requirements

Description

Who this course is for: