Machine Learning for Remote Sensing Data AnalysisModule description #40928 / Version 1
- 3 CP
- Portfolio examination
- Graded
- Winter semester
- English
This module description is not valid in the current semester (Winter semester 2026/27).
| Module / Version | #40928 / #1 |
|---|---|
| Validity | WS 2018/19 – WS 2018/19 |
| Available language(s) | English |
| Credit points | 3 |
| 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 | Not specified |
Contact
| Office | FR 6-2 |
|---|---|
| Contact person | Fuchs, Martin Hermann Paul |
| E-mail address | m.fuchs@tu-berlin.de |
| Website | http://rsim.berlin |
Learning outcomes
Participants of this seminar will acquire knowledge on advanced methodologies for the analysis of remote sensing images acquired by the last generation Earth observation satellite systems. In particular, this seminar course will provide students on the one hand an in-depth theoretical and practical knowledge on remote sensing image analysis; and on the other hand a know-how in one or more domains of applications, such as land-cover maps generation, land-cover maps updating, biophysical parameter estimation, image search and retrieval, change detection. Moreover, the students will learn about the current developments in remote sensing and related data analysis methods, and how machine learning techniques can be employed to solve Earth observation questions.
Content
Remote sensing images are a rich information source for monitoring the Earth surface, e.g., for climate change analysis, urban area studies, forestry applications, risk and damage assessment, water quality assessment, crop monitoring. Due to the recent developments in both passive multispectral and hyperspectral sensors, and synthetic aperture radar active instruments, the role of this technology is becoming more and more important for understanding the dynamics of our planet. To efficiently process/analyze the data, remote sensing has evolved into a multidisciplinary field, where machine learning algorithms play an important role nowadays. In this seminar, students will review the current state of the art in the field of machine learning applied to remote sensing image analysis in the framework of different Earth observation applications. The general topics include but are not limited to: i) feature selection and extraction; ii) supervised, unsupervised, semi-supervised classification and regression, iii) active learning, iv) structured learning, v) transfer learning and domain adaptation with applications to remote sensing image analysis.
Module components
RSiM
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Machine Learning for Remote Sensing Data Analysis | Seminar | Winter semester | [en] | 2 | ISIS |
Workload and credit points
Machine Learning for Remote Sensing Data Analysis (Seminar)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 90 hours. The module therefore comprises 3 credit points.
Description of teaching and learning methods
At the beginning of the semester there will be overview lectures that will provide some background concepts on remote sensing, different types of remote sensing images and the general remote sensing image processing/analysis chain. In addition, a set of primary literature works will be provided. Then, the students will further investigate the topics assigned to them in the seminar. A few weeks after they will give a short presentation of approx. 10 minutes (based on their initial understandings on the considered topic) that will be open to all seminar participants. In the further course of the semester the students will give a final presentation of approx. 30 minutes. In addition to the talk the students will also prepare a technical report with 10-15 pages describing their topic.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Good knowledge in Mathematics, especially linear algebra and statistics.
Basic programming knowledge.
Basic programming knowledge.
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 |
|---|---|---|---|
| Long Seminar Presentation | 45 | oral | 30 minutes |
| Short Seminar Presentation | 15 | oral | 10 minutes |
| Written Seminar Report | 40 | written | 10-15 pages |
Exam description
There are two oral portfolio deliverable assessments: a short seminar presentation (15 pts.), a long seminar presentation (45 pts.)
There is one written portfolio deliverable assessment: a written seminar report (40 pts.)
There is one written portfolio deliverable assessment: a written seminar report (40 pts.)
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 semester.
Maximum number of participants
The maximum capacity of participants is 16.
Registration procedures
Students intending to take this seminar need to follow the instructions on the RSiM website for pre-semester application.
Within the first 6 weeks after the commencement of the seminar, students will have to register for the module at QISPOS (university examination protocol tool) and, additionally, at ISIS (TU Berlin variant of 'Moodle') for teaching materials and communication.
Within the first 6 weeks after the commencement of the seminar, students will have to register for the module at QISPOS (university examination protocol tool) and, additionally, at ISIS (TU Berlin variant of 'Moodle') for teaching materials and communication.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
- G. Camps-Valls, and L. Bruzzone, Kernel methods for Remote Sensing Data Analysis, Wiley & Sons 2009
- L. Bruzzone, B. Demir, A Review of Modern Approaches to Classification of Remote Sensing Data, in Land Use and Land Cover Mapping Europe, Practices and Trends, Eds: I. Manakos, M. Braun, EARSeL Book Series, Springer Verlag, Chapter 9, 2014, pp. 127-143.
- E. Alpaydin, Introduction to Machine Learning, MIT Press, Cambridge, Massachusetts, London, England, 2004.
Assigned programs
This module is not used in any program.
Miscellaneous
Not specified