Display language

#40928 / #2

Seit SS 2019
(Deaktivierung beantragt zum SoSe 2023)


Machine Learning for Remote Sensing Data Analysis


Demir, Begüm




Fakultät IV

Institut für Technische Informatik und Mikroelektronik

No information

No information


EN 5

Fuchs, Martin Hermann Paul


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.


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


All Courses are mandatory.

Course NameTypeNumberCycleLanguageSWSVZ
Machine Learning for Remote Sensing Data AnalysisSEMWiSeEnglish2

Workload and Credit Points

Machine Learning for Remote Sensing Data Analysis (SEM):

Workload descriptionMultiplierHoursTotal
90.0h(~3 LP)
Pre/post processing15.04.0h60.0h
The Workload of the module sums up to 90.0 Hours. Therefore the module contains 3 Credits.

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.

Mandatory requirements for the module test application:

No information

Module completion



Type of exam

Portfolio examination

Type of portfolio examination

100 Punkte insgesamt



Test elements

Long Seminar Presentation45oral30 minutes
Short Seminar Presentation15oral10 minutes
Written Seminar Report40written10-15 pages

Grading scale

Test description (Module completion)

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.)

Duration of the Module

The following number of semesters is estimated for taking and completing the module:
1 Semester.

This module may be commenced in the following semesters:

Maximum Number of Participants

The maximum capacity of students 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.

Recommended reading, Lecture notes

Lecture notes

Availability:  unavailable


Electronical lecture notes

Availability:  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 Degree Programs

This module is used in the following Degree Programs (new System):

Studiengang / StuPOStuPOsVerwendungenErste VerwendungLetzte Verwendung
Computer Engineering (M. Sc.)154SS 2019SoSe 2023
Computer Science (Informatik) (M. Sc.)143SS 2019SoSe 2023
Elektrotechnik (M. Sc.)127SS 2019SoSe 2023
ICT Innovation (M. Sc.)39SS 2019SoSe 2023
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)19SS 2019SoSe 2023
Wirtschaftsingenieurwesen (M. Sc.)120SS 2019SoSe 2023

Students of other degrees can participate in this module without capacity testing.


No information