Skip to content
Technische Universität Berlin Deutsch
Course catalog and module transfer system

Deep Learning for Geographical DataModule description #61434 / Version 1

← Module page Deutsche Fassung
Module / Version#61434 / #1
ValiditySince Winter semester 2020/21
Available language(s)English
Credit points6
Person responsible for the moduleKada, Martin
GradingGraded
Exam formatOral exam
Language(s) of instructionEnglish

Affiliation

FacultyFakultät VI
InstituteInstitut für Geodäsie und Geoinformationstechnik (IGG)
Academic chair36331100 FG Methodik der Geoinformationstechnik

Contact

OfficeH 12
Contact personNot specified
E-mail addressmartin.kada@tu-berlin.de
WebsiteNot specified

Learning outcomes

Students have a fundamental understanding of the principles, structure, and working of neural networks and their common architectures for solving tasks such as classification, regression, localization, recognition, segmentation, etc., in the context of geoinformation related applications. They are able to plan, implement, train, and evaluate the performance of application-specific deep neural network architectures for processing geographical 2D/3D data such as raster, vector, network, and point cloud data. The students are well acquainted with the established software libraries for Deep Learning and are able to use them self-reliantly.

Content

Introduction to artificial intelligence, artificial neural networks, linear classifier, the perceptron, fully connected neural networks, training by backpropagation, loss and activation functions, weight initialization and regularization, optimizers, hyperparameter tuning, multi-task learning, convolutional neural networks (CNN), common network architectures and custom models, Deep Learning on 3D data and aerial laser scanning point clouds, time series geographical data, recurrent neural networks (RNN), attention mechanism, generative learning with Autoencoders and generative adversarial networks (GAN), Deep Learning libraries (e.g. TensorFlow, PyTorch).

Module components

Compulsory area

The following courses are mandatory for this module:

CoursesTypeNumberFrequencyLanguageHours per weekCourse catalog
Deep Learning for Geographical DataExercise Winter semester[en]2 ISIS
Deep Learning for Geographical DataLecture Winter semester[en]2 ISIS

Courses in the course catalog

Courses created from the teaching units of this module.

Winter semester 2026/27 (2)

Deep Learning for Geographical Data (Exercise) 1

All groups of this course in the catalog

Deep Learning for Geographical Data (Lecture) 1

All groups of this course in the catalog

Workload and credit points

Deep Learning for Geographical Data (Exercise)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

Deep Learning for Geographical Data (Lecture)

Workload descriptionMultiplierHoursTotal
Attendance152 h30 h
Pre/post processing154 h60 h
90 h

The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.

Description of teaching and learning methods

Lectures (45%), exercises (45%), and independent reading (10%).

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

Profound knowledge of geographical data and linear algebra, basic understanding in machine learning, and solid background and experience in object-oriented programming with Python.

Mandatory requirements for the module examination registration:

This module has no examination requirements.

Completion of the module

GradingGraded
Exam formatOral exam
LanguageEnglish
Duration/Extent30 Minutes

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

This module is not limited to a number of students.

Registration procedures

No information.

Recommended reading, lecture notes

Lecture notes

unavailable

Electronic lecture notes

available

Recommended literature

No recommended literature given

Assigned programs

This module version is used in the following programs:

Program / program versionSemester(s)Curriculum component
Ecology and Environmental Planning
Ecology and Environmental Planning (M. Sc.) - StuPO 2016
SS 2025Wahlpflichtbereich
WS 2025/26Wahlpflichtbereich
SS 2026Wahlpflichtbereich
WS 2026/27Wahlpflichtbereich
Ecology and Environmental Planning
Ecology and Environmental Planning (B. Sc.) - StuPO 2019 (20.02.2019)
SS 2025Wahlpflichtbereich Profilierung Ökologie und Umweltplanung › Profilierung Umweltplanung
WS 2025/26Wahlpflichtbereich Profilierung Ökologie und Umweltplanung › Profilierung Umweltplanung
SS 2026Wahlpflichtbereich Profilierung Ökologie und Umweltplanung › Profilierung Umweltplanung
WS 2026/27Wahlpflichtbereich Profilierung Ökologie und Umweltplanung › Profilierung Umweltplanung
Environmental Planning
Environmental Planning (M. Sc.) - StuPO 2017 (13.12.2017)
SS 2025Wahlpflichtbereich 2: Ergänzungsbereich
WS 2025/26Wahlpflichtbereich 2: Ergänzungsbereich
SS 2026Wahlpflichtbereich 2: Ergänzungsbereich
WS 2026/27Wahlpflichtbereich 2: Ergänzungsbereich
Geodesy and Geoinformation Science
StuPO 2007 (21.03.2007)
SS 20252.1 Major subject Geoinformation Technology › Major subject Geoinformation Technology
WS 2025/262.4 Major subject Computer Vision and Remote Sensing › Minor subject Geoinformation Technology
SS 20262.4 Major subject Computer Vision and Remote Sensing › Minor subject Geoinformation Technology
WS 2026/272.4 Major subject Computer Vision and Remote Sensing › Minor subject Geoinformation Technology

Miscellaneous

Not specified