Advanced Remote Sensing

About this course:

The main objective of this course is to introduce more advanced topics in remote sensing in the realm of cloud computing. To promote collaboration in research and interoperability of different programming languages and data sources, we will be using the Google Earth Engine Python API running on Google Colab (GEE Javascript API will only be used for reference purposes). The course will have six units: 0) Introduction, 1) Advanced GEE operations, 2) Modeling in GEE, 3) Machine Learning in GEE (raster), 4) Machine Learning in KERAS (point clouds) and 5) Open topics. Unit 0 is an overview of advanced remote sensing applications. Unit 1 introduces more advanced concepts not covered in intro class. Unit 2 introduces linear models in remote sensing as a foundation to help promote the understanding of more complicated machine learning models. Unit 3 introduces the fundamentals of machine learning in remote sensing as implemented in GEE (Random Forest models for image classification). Unit 4 introduces more advanced machine learning models that are not available in GEE (PointNet models for point cloud classification). Unit 5 is reserved to discuss various topics that may interest you (please reach out to me as early as possible so that I can pick a common interest of the class to discuss). All units will also include lab sessions with code examples to help start the transition from working in various different platforms using different programming languages to working in one unified cloud-based coding environment. The ultimate goal is for you to be comfortable integrating different remote sensing and geospatial analysis workflows and datasets from different sources into one unified cloud-based coding environment to enhance efficiency and to promote collaboration. SUGGESTED PREREQUISITES It is advisable that you complete the following (or equivalent): GEOG XL 182A: Introduction to Remote Sensing