Machine Learning in GIS : Land Use Land Cover Image Analysis
- Description
- Curriculum
- FAQ
- Reviews
Advanced Land Use/Land Cover Mapping with Machine Learning
Are you looking to advance your geospatial analysis skills using QGIS? Want to master object-based image analysis and harness the power of Machine Learning algorithms for Land Use and Land Cover (LULC) mapping? This course is designed to take QGIS users from basic geospatial analysis to performing advanced tasks with confidence. Explore object-based image analysis with various data sources and cutting-edge Machine Learning algorithms. Dive into LULC mapping, change detection, and object-based crop type mapping using QGIS and Google Earth Engine.
Course Highlights:
-
Advanced geospatial analysis using QGIS
-
Object-based image analysis
-
Machine Learning algorithms for LULC mapping
-
Practical exercises with QGIS and Google Earth Engine
-
Installation and configuration of open-source GIS software
-
Supervised and unsupervised Machine Learning
-
Accuracy assessment for geospatial projects
Course Focus:
This advanced course is designed to equip you with practical knowledge in advanced Land Use and Land Cover (LULC) mapping and object-based image analysis. Gain confidence in using Machine Learning algorithms for geospatial tasks and leverage the capabilities of QGIS and Google Earth Engine. Whether you’re a geographer, programmer, social scientist, or geologist, this course will enhance your GIS and Remote Sensing skills.
What You’ll Learn:
-
Installing and configuring open-source GIS software (QGIS and Orfeo Toolbox)
-
Navigating the QGIS software interface, including its main components and plug-ins
-
Classifying satellite images with different Machine Learning algorithms in QGIS
-
Collecting training and validation data and performing accuracy assessments
-
Object-based image analysis and object-based crop type mapping in QGIS
-
Running supervised and unsupervised Machine Learning Algorithms in Google Earth Engine
Who Should Enroll:
This course is ideal for professionals seeking to advance their geospatial analysis skills, including geographers, programmers, social scientists, geologists, and anyone needing to use LULC maps in their field. Whether you’re planning to create land cover and land use maps, tackle geospatial challenges, or explore the cutting-edge LULC techniques, this course provides the skills and confidence you need.
INCLUDED IN THE COURSE: Gain access to all course materials, including data, Java code files, and future resources. Enroll today to take your geospatial analysis to the next level!
-
8Section OverviewText lesson
-
9Introduction to Machine LearningVideo lesson
-
10Basics of machine learning for classification analysisVideo lesson
-
11Unsupervised (K-means) image analysis in QGISVideo lesson
-
12Common algorithms of image classificationVideo lesson
-
13Land cover classification on the cloud using EO browserVideo lesson
-
14Random Forest classification in OTBVideo lesson
-
15SVM classification in OTBVideo lesson
-
16DT classification in OTBVideo lesson
-
17Accuracy AssessmentVideo lesson
-
18Section OverviewText lesson
-
19Import images and their visualization in Google Earth EngineVideo lesson
-
20Unsupervised (K-means) image analysis in Google Earth EngineVideo lesson
-
21Random Forest Supervised CLassification in Earth EngineVideo lesson
-
22Accuracy Assessment in Earth EngineVideo lesson
-
25Section OverviewText lesson
-
26Object-based image classification (OBIA) VS pixel-based image classificationVideo lesson
-
27Segmentation of high-resolution satellite imageVideo lesson
-
28Creating training data from satellite image based on the segmented layerVideo lesson
-
29Object-based image classification with the Machine Learning algorithmVideo lesson
External Links May Contain Affiliate Links read more