Machine Learning for Remote Sensing Tutorial
The Machine Learning for Remote Sensing Summit in Kigali 2023, co-organized by NASA Harvest and CMU and hosted by CMU-Africa, aims to provide an extensive tutorial and workshop on the application of machine learning techniques in remote sensing data analysis, particularly in the agricultural sector. The tutorial covers various topics, such as an overview of remote sensing and machine learning methods, creating and curating labeled datasets, use cases and example methods for AI-EO in agriculture, evaluation of machine learning models, and case studies on cropland and crop type mapping.
The tutorial will take place on Thursday, May 4, 2023 at CMU Africa in Kigali. Tutorial participants will also have an opportunity on May 5 to attend the Machine Learning for Remote Sensing Workshop at the International Conference on Learning Reprsentations (ICLR), a top ML conference held in Kigali in 2023.
Important links
- Registration: https://ml4rm_harvest_cmu.eventbrite.com (registration closed)
- Pre-tutorial survey: https://forms.gle/Dh48tX8cTZgv8u8t9
Schedule
Start time | Topic | Instructor |
---|---|---|
10:00 | Buses pick up and arrive at CMU | |
11:00 | Lunch and pre-tutorial survey | |
12:30 | Introductory remarks and keynote | Moise Busogi, CMU |
13:00 | Overview of remote sensing data [slides] | Hannah Kerner |
13:20 | Overview of machine learning methods [slides] | Gabi Tseng |
13:40 | Considerations for ML and remote sensing data [slides] | Ivan Zvonkov |
14:00 | Q&A | Hannah, Gabi, Ivan |
14:20 | Coffee/tea and networking break | |
15:00 | ML + Earth observations for agriculture in Africa [slides] | Catherine Nakalembe, Hannah Kerner |
15:40 | Case study: NASA Harvest approach to cropland and crop type mapping [slides] | Ivan Zvonkov |
16:10 | Case study: ML4RS: Predictions to Actionable Insights [slides] | Gedeon Muhawenayo |
16:40 | Case study: Marine debris detection with noisy annotations using Sentinel-2 | Marc Rußwurm |
17:10 | Guide to post-tutorial resources for continuing your journey in ML+RS | Hannah, Gabi, Ivan |
17:20 | Buses leave CMU |
Instructors
- Hannah Kerner (Arizona State University)
- Catherine Nakalembe (University of Maryland)
- Gabriel Tseng (McGill / Mila - Quebec AI institute)
- Ivan Zvonkov (University of Maryland)
- Gedeon Muhawenayo (Rwanda Space Agency)
- Moise Busogi (Carnegie Mellon University Africa)
- Marc Rußwurm (EPFL)
Resources for continuing your ML+RS journey post-workshop
- An Introduction to Machine Learning: The canonical introduction to machine learning.
- Practical Deep Learning for Coders (fast.ai): A free course designed for people with some coding experience, who want to learn how to apply deep learning and machine learning to practical problems. There is also a part 2 for those with some experience.
- Google Foundational Courses: The foundational courses cover machine learning fundamentals and core concepts.
- The State of Satellites: A guide to the current state of satellite remote sensing technology, including applications and analysis.
- NASA ARSET: Applied Remote SEnsing Training (ARSET) program offers free online and in person courses for learning about remote sensing technologies, including ML for remote sensing.
- Radiant Earth Foundation’s ML for Remote Sensing Bootcamp: Course materials are freely available on Github and YouTube.
- Cloud-Based Remote Sensing with Google Earth Engine: Fundamentals and Applications: An online book for learning how to use Google Earth Engine for remote sensing data analysis.
- Automating GIS Processes: An online course for learning programming for GIS using open source tools like geopandas.