Deep Learning for Remote Sensing

2023-10-22

Course Description:

This course introduces deep learning techniques for remote sensing. The course will cover the fundamentals of deep learning, including artificial neural networks, convolutional neural networks, and recurrent neural networks. The course will also cover the application of deep learning to remote sensing problems, such as land cover classification, object detection, and change detection.

Course Objectives:

Upon completion of this course, students will be able to:

○ Understand the fundamentals of deep learning

○ Apply deep learning to remote sensing problems

○ Evaluate the performance of deep learning models

○ Use deep learning to solve real-world problems

Prerequisites:

○ Introduction to Remote Sensing

○ Introduction to Programming

○ Introduction to Statistics

Textbooks:

○ Goodfellow, Ian, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016.

○ Amini, Bahram, and Saeed Amini. Deep Learning for Remote Sensing. CRC Press, 2020.

Course Outline:

○ Module 1: Introduction to deep learning

○ Module 2: Artificial neural networks

○ Module 3: Convolutional neural networks

○ Module 4: Recurrent neural networks

○ Module 5: Land cover classification

○ Module 6: Object detection

○ Module 7: Change detection

○ Module 8: Case studies

Course Delivery Method:

○ Lectures: Interactive lectures delivered by experienced remote sensing professionals and experts through presentations, videos, and demonstrations.

○ Homework Assignments: There will be three homework assignments throughout the course. The homework assignments will be graded on correctness and completeness.

○ Project: The project will involve applying machine learning to a remote sensing problem. Students will work in groups of two or three to complete the project. The project will be graded on creativity, originality, and technical quality.

○ Q&A Sessions: Regular question and answer sessions to clarify doubts and address participants' queries related to the course content and practical exercises.

Course Duration:

4 weeks (can be adjusted as per requirements)

Note:

The course content and duration can be customized according to the specific requirements and level of expertise of the target audience.