Project Deep Learning for Earth ObservationModule description #41012 / Version 6
- 9 CP
- Portfolio examination
- Graded
- Winter and summer semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
Current version (v7)
| Module / Version | #41012 / #6 |
|---|---|
| Validity | Winter semester 2025/26 – Summer semester 2026 |
| Available language(s) | English, German |
| Credit points | 9 |
| Person responsible for the module | Demir, Begüm |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | English |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Technische Informatik und Mikroelektronik |
| Academic chair | 34342200 FG Remote Sensing Image Analysis (RSiM) |
Contact
| Office | FR 6-2 |
|---|---|
| Contact person | Lomashvili, Ana |
| E-mail address | ana.lomashvili@tu-berlin.de |
| Website | https://rsim.berlin/ |
Learning outcomes
Participants of this project course gain practical experience in applying deep learning techniques to address Earth observation questions in a collaborative team and acquire knowledge on state-of-the-art topics in the field of deep learning for remote sensing.
Content
Recent advances in satellite technology have led to a regular, frequent, and high-resolution monitoring of Earth at the global scale, providing an unprecedented amount of Earth observation (EO) data. To efficiently process and analyze large amounts of EO data, remote sensing has evolved into a multidisciplinary field, where machine learning and computer vision algorithms play an important role nowadays. At the start of this project course, students receive project topics as well as some information material on Deep Learning for Earth Observation. After setting the project teams and topics, a project environment is decided (with the suitable tools for teamwork) with the assistance of the lecturer. Then, project planning, coordination and development start. During the weekly project meetings, each project team presents and discusses their progress as well as the next steps with the lecturer. The project is concluded with final reports as well as a final presentation. The general topics are related to the Chair’s current research activities and include, but are not limited to: i) image representation learning; ii) classification and retrieval of satellite images; iii) multimodal learning; iv) development of foundation models.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Computer Vision for Remote Sensing (CV4RS) | Project | Winter and summer semester | [en] | 6 | WS 2026/27 (1) ISIS |
Courses in the course catalog
Courses created from the teaching units of this module.
Winter semester 2026/27 (1)
Computer Vision for Remote Sensing (CV4RS) (Project) 1
Workload and credit points
Computer Vision for Remote Sensing (CV4RS) (Project)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 6 h | 90 h |
| Pre/post processing | 15 | 12 h | 180 h |
| 270 h | |||
The workload of the module adds up to 270 hours. The module therefore comprises 9 credit points.
Description of teaching and learning methods
This module contains guided and self-organized project work. Students receive a brief overview of both the fundamentals and recent advancements in Deep Learning for Earth Observation. Weekly meetings with the lecturer are held where students present and review their challenges and progress, and together with the lecturer discuss and plan the next steps. The students work in small teams on a chosen topic, and they present initial findings in an intermediate talk. Each team implements the project and presents insights, methods and results in a concluding talk. Finally, project reports are submitted.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Solid Python programming skills and expertise in common deep learning libraries such as PyTorch or TensorFlow are desired.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | English |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| (Deliverable assessment) Intermediate presentation | 10 | oral | approx. 15 minutes |
| (Deliverable assessment) Final presentation | 20 | oral | approx. 20 minutes |
| (Deliverable assessment) Scientific Report | 20 | written | 8-10 pages |
| (Deliverable assessment) Implementation | 50 | practical | approx. 120 hours |
Exam description
The overall grade for the module consists of the results of the course work ('portfolio exam'). The following are included in the final grade:
1. Intermediate presentation (10p): The students present their initial findings and results on their topic.
2. Final presentation (20p): The students present their final findings/results.
3. Scientific Report (20p): The students summarize their final findings, methods and results in a written scientific report.
4. Implementation (50p): The students work in a team on a selected topic and develop its prototypical implementation.
1. Intermediate presentation (10p): The students present their initial findings and results on their topic.
2. Final presentation (20p): The students present their final findings/results.
3. Scientific Report (20p): The students summarize their final findings, methods and results in a written scientific report.
4. Implementation (50p): The students work in a team on a selected topic and develop its prototypical implementation.
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Winter and summer semester.
Maximum number of participants
The maximum capacity of participants is 9.
Registration procedures
Admission to the lecture is limited. Please have a look at https://rsim.berlin/courses before the lecture period starts to get information on how you can register.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
- Mahmoud Hassaballah and Ali Ismail Awad. "Deep Learning in Computer Vision Principles and Applications". CRC Press, 2020. IBSN: 978-1-138-54442-0
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. "Deep Learning". MIT Press, 2016. ISBN: 978-0-262-03561-3
- Mohamed Elgendy. "Deep Learning for Vision Systems". Manning Publications, 2020. ISBN: 978-1-61729-619-2
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Computer Engineering Computer Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiet B › Kognitive Systeme / Cognitive Systems |
| SS 2026 | Wahlpflicht Studiengebiet B › Medientechnik und Mensch-Maschine-Interaktion / Digital Media und Human-Computer Interaction | |
| Computer Science (Informatik) Computer Science (Informatik) (M. Sc.) - StuPO 2015 | WS 2025/26 | Studiengebiete › Kognitive Systeme / Cognitive Systems |
| SS 2026 | Studiengebiete › Kognitive Systeme / Cognitive Systems | |
| Electrical Engineering Electrical Engineering (M. Sc.) - StuPO 2015 | WS 2025/26 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
| SS 2026 | Wahlpflicht Studiengebiete Fak. IV › Medientechnik und Mensch-Maschine-Interaktion / Digital Media and Human-Computer Interaction |
Miscellaneous
Not specified