04-800-AB Machine Learning for Earth Observation
Location: Africa
Units: 12
Semester Offered: Spring
Course description
Satellite data needs special skills to process, visualize, and analyze. In this course, students will be introduced to different GIS data models. The course will introduce some of the advanced techniques for collecting, processing, and analyzing remote sensing data. It will also discuss some of the techniques in geospatial data fusion and introduce the concept of transfer learning in geospatial data analytics.
Students will apply ML techniques and other geospatial data analytics tools in practical and relevant applications such as assessing land use and land cover, change detection, crop disease detection, etc.
Learning objectives
In this class, students will learn:
- Different GIS data models and their advantages and disadvantages
- Techniques for efficiently encoding, manipulating, and querying geospatial data
- How to design, use, and implement algorithms dealing with geospatial data
- How to use ML techniques to generate insight from satellite data in practical applications
Outcomes
At the end of this course, students will be able to apply ML techniques to generate insight from geospatial data in a wide range of applications.
Content details
The coverage of this course includes:
- Introduction to GIS and satellite data
- Geometric algorithms for spatiotemporal data processing and analysis
- Scalable algorithms and representations for big geospatial data
- Geospatial data fusion
- Introduction transfer learning
- Feature Extraction Techniques
- Land Use/Cover Mapping
- Change Detection