Skip to main content

PhD, PostDoc, Group Leader and Guest Professor Positions in the area of Machine Learning and Data Analytics in Earth Observation (AI4EO).


we have several open PhD, PostDoc, Group Leader and Guest Professor Positions in the area of Machine Learning and Data Analytics in Earth Observation (AI4EO).
PhD, PostDoc, and Group Leader (Wissenschaftliche/r Mitarbeiter/in)
 

Zhu lab is a joint venue of the Professorship for Signal Processing in Earth Observation at the Technical University of Munich [www.sipeo.bgu.tum.de] and the Department EO Data Science of the Remote Sensing Technology Institute of the German Aerospace Center (DLR) [https://www.dlr.de/eoc/en/desktopdefault.aspx/tabid-12785/22743_read-52854/]. We develop innovative signal processing and machine learning algorithms to extract geo-information from big geospatial data, ranging from remote sensing satellite data and even social media data. As downstream applications, we provide large scale and highly accurate geo-information to address societal grand challenges, such as monitoring the global urbanization, climate research and supporting the sustainable development goals of the United Nations. Our lab offers currently several open positions for outstanding PhD Candidates, postdocs, and senior scientists at either the Technical University Munich (TUM) or the German Aerospace Center (DLR). We also have open positions for outstanding research engineers.

 

Topics of particular interest to the group include:

-        Earth Observation and Computer Vision

-        Machine Learning/Deep Learning

-        Unsupervised/weakly Supervised Learning

-        Uncertainty Analysis, Interpretation and Reasoning of Deep Neural Networks 

-        AutoML

-        Anomaly and Change Detection Methods

-        Geo-information Extraction from Social Media Data

-        Natural Language Processing

-        Large-Scale Data Mining and Knowledge Discovery in Earth Observation

-        Big Data Management

-        High-performance Computing

-        Statistical Learning, Modelling, Spatial and Temporal Analysis of Geographical Observations

-        Geo-referencing, Digitalization, Building and Maintaining Large Relational Data Bases and Geo-databases, Publishing Geo-services (i.e. Web Map Services)

 

Demonstrated hands-on experience in one or more of these areas is a requirement. Postdoc applicants should have an excellent publication record and a PhD in machine learning, computer science, statistics, remote sensing, mathematics or a related discipline. Research engineer applicants should have excellent coding skills, as well as practical skills in data science and/or deep learning, and experience with scripting and running large-scale experiments.

 

Application materials comprise:

-        CV

-        Full set of transcripts

-        Statement of purpose

-        Briefly state what drives you and what are your goals in applying to the SiPEO lab

-        Names for at least 2 reference letter writers

                             For each reference, please include name, title, and email address.

                             References should expect to be contacted for a reference letter.

 

Please submit these documents to ai@DLR.de.  Please kindly consider that due to the high requests, we will not be able to consider incomplete applications.

 

AI4EO Guest Professors
 

In the framework of the BMBF funded German International AI Future Lab AI4EO, we have also a couple of slots free for guest professors with a pay scale from W1 to W3. Should you be working on any of the three topics 1) reasoning; 2) uncertainty and 3) Ethics in AI4EO and be interested in visiting us in Munich for 18 to 36 month, please kindly in direct contact with Prof. Dr. Xiaoxiang Zhu (xiaoxiang.zhu@dlr.de)

 

About Us:

 

The Technical University of Munich (TUM):

The Technical University of Munich (TUM) is one of Europe's top universities. It is committed to excellence in research and teaching, interdisciplinary education and the active promotion of promising young scientists. The university also forges strong links with companies and scientific institutions across the world. TUM was one of the first universities in Germany to be named a University of Excellence. Moreover, TUM regularly ranks among the best European universities in international rankings.

 

German Aerospace Center (DLR):

As a member of the Helmholtz Association of German Research Centers, the German Aerospace (DLR) employs more than 8000 people at 20 locations. The department "EO Data Science" at the Remote Sensing Technology Institute (IMF-DAS), located at the DLR in Oberpfaffenhofen is developing novel signal processing and AI algorithms to improve information retrieval from remote sensing data, in particular those from current and the next generation of Earth observation missions and deliver crucial geo-information to address social grant challenges, such as urbanization and climate change.

 

Resources and opportunities for collaboration:

·       Both at TUM and DLR, we are equipped with state-of-the-art computational resources such as DGX servers. In addition, we are closely collaborating with the Leibniz Supercomputing Centre (LRZ), which provides us with access to one of the most powerful supercomputing environments in Europe.

 

·       Helmholtz AI: The Helmholtz AI [link] platform aims to enhance the research within the Helmholtz Association with applied AI methods. For that each research area of Helmholtz operates HAICU units to work on short, medium and long term AI projects. IMF-DAS operates the local Helmholtz AI unit "MASTr: HAICU Munich @ Aeronautics, Space and Transport". It consists of a Young Investigator Group (YIG) in Earth observation and an AI Consulting Team, providing the expertise from Earth Observation, robotics, computer vision and an HPC/HPDA support unit. Currently we are looking for an enthusiastic Head of the YIG in the field of Large-Scale Data Mining in Earth Observation, and two PhD students.

 

·       Future AI Lab on Artificial Intelligence in Earth Observation: For the BMBF-funded Future Lab on Artificial Intelligence in Earth Observation (AI4EO), we are looking for one science manager and two PostDocs to form the backbone team of the lab starting from May 1, 2020. The Future Lab will bring together 12 highly renowned senior scientists and dozens of junior scientists from across the globe to carry out cutting-edge AI4EO research that will help to bring AI4EO to the next level. The research topics include but are not limited to reasoning, uncertainty and ethics in AI4EO.

 

 

Best regards,

Xiaoxiang Zhu

 

——————————————————

Prof. Dr.-Ing. habil. Xiaoxiang Zhu

Direcor of the German International Future AI Lab „AI4EO"

Technical University of Munich (TUM) & German Aerospace Center (DLR)

Department of Aerospace and Geodesy| Willy-Messerschmitt-Str. 1 | 82024 Taufkirchen/Ottobrunn | Germany
Website: www.ai4eo.de (up soon)

Head of Department "EO Data Science"

German Aerospace Center (DLR)

Earth Observation Center | Remote Sensing Technology Institute | Department of EO Data Science | Oberpfaffenhofen | 82234 Wessling | Germany

Telephone +49 81-5328-3531 | Telefax +49 81-5328-1420 | xiaoxiang.zhu@dlr.de

 

Professor for Signal Processing in Earth Observation

Technical University of Munich (TUM)
Signal Processing in Earth Observation| Arcisstrasse 21 | 80333 Munich | Germany

Telephone +49 89-289-22659 | Telefax +49 89-289-23202 | xiaoxiang.zhu@tum.de

 

Please visit my DLR-TUM joint research group here http://www.sipeo.bgu.tum.de/


🌍
🌏
🌎
🌐
😀
👍🏾
#Globe
#Earth
#Map
#Decision Making
#Cartography
#Cartographer
#Geography
#Geographer
#GIS
#Remote_Sensing
#RemoteSensing, #GeospatialEducation, #GeoEducation, #government, #LocalGovernment, #BigData, #geospatial, #GeoOps #ChangeDetection, #LocationIntelligence, #LocationTechnology, #SmartCities, #SmartCity, #Geomatics, #Geoinformatics, #Geology, #surveying
#StaySafe, #StayHome, #StayHealthy
#Scholarship, #Scholarships, #Onlinecourse, #Onlineducation

....


Vineesh V
Assistant Professor of Geography,
Directorate of Education,
Government of Kerala.
https://g.page/vineeshvc

Comments

Popular posts from this blog

Photogrammetry – Types of Photographs

In photogrammetry, aerial photographs are categorized based on camera orientation , coverage , and spectral sensitivity . Below is a breakdown of the major types: 1️⃣ Based on Camera Axis Orientation Type Description Key Feature Vertical Photo Taken with the camera axis pointing directly downward (within 3° of vertical). Used for maps and measurements Oblique Photo Taken with the camera axis tilted away from vertical. Covers more area but with distortions Low Oblique: Horizon not visible High Oblique: Horizon visible 2️⃣ Based on Number of Photos Taken Type Description Single Photo One image taken of an area Stereoscopic Pair Two overlapping photos for 3D viewing and depth analysis Strip or Mosaic Series of overlapping photos covering a long area, useful in mapping large regions 3️⃣ Based on Spectral Sensitivity Type Description Application Panchromatic Captures images in black and white General mapping Infrared (IR) Sensitive to infrared radiation Veget...

Photogrammetry – Geometry of a Vertical Photograph

Photogrammetry is the science of making measurements from photographs, especially for mapping and surveying. When the camera axis is perpendicular (vertical) to the ground, the photo is called a vertical photograph , and its geometry is central to accurate mapping.  Elements of Vertical Photo Geometry In a vertical aerial photograph , the geometry is governed by the central projection principle. Here's how it works: 1. Principal Point (P) The point on the photo where the optical axis of the camera intersects the photo plane. It's the geometric center of the photo. 2. Nadir Point (N) The point on the ground directly below the camera at the time of exposure. Ideally, in a perfect vertical photo, the nadir and principal point coincide. 3. Photo Center (C) Usually coincides with the principal point in a vertical photo. 4. Ground Coordinates (X, Y, Z) Real-world (map) coordinates of objects photographed. 5. Flying Height (H) He...

Raster Data Structure

Raster Data Raster data is like a digital photo made up of small squares called cells or pixels . Each cell shows something about that spot — like how high it is (elevation), how hot it is (temperature), or what kind of land it is (forest, water, etc.). Think of it like a graph paper where each box is colored to show what's there. Key Points What's in the cell? Each cell stores information — for example, "water" or "forest." Where is the cell? The cell's location comes from its place in the grid (like row 3, column 5). We don't need to store its exact coordinates. How Do We Decide a Cell's Value? Sometimes, one cell covers more than one thing (like part forest and part water). To choose one value , we can: Center Point: Use whatever feature is in the middle. Most Area: Use the feature that takes up the most space in the cell. Most Important: Use the most important feature (like a road or well), even if it...

Photogrammetry

Photogrammetry is the science of taking measurements from photographs —especially to create maps, models, or 3D images of objects, land, or buildings. Imagine you take two pictures of a mountain from slightly different angles. Photogrammetry uses those photos to figure out the shape, size, and position of the mountain—just like our eyes do when we see in 3D! Concepts and Terminologies 1. Photograph A picture captured by a camera , either from the ground (terrestrial) or from above (aerial or drone). 2. Stereo Pair Two overlapping photos taken from different angles. When seen together, they help create a 3D effect —just like how two human eyes work. 3. Overlap To get a 3D model, photos must overlap each other: Forward overlap : Between two photos in a flight line (usually 60–70%) Side overlap : Between adjacent flight lines (usually 30–40%) 4. Scale The ratio of the photo size to real-world size. Example: A 1:10,000 scale photo means 1 cm on the photo...

Logical Data Model in GIS

In GIS, a logical data model defines how data is structured and interrelated—independent of how it is physically stored or implemented. It serves as a blueprint for designing databases, focusing on the organization of entities, their attributes, and relationships, without tying them to a specific database technology. Key Features Abstraction : The logical model operates at an abstract level, emphasizing the conceptual structure of data rather than the technical details of storage or implementation. Entity-Attribute Relationships : It identifies key entities (objects or concepts) and their attributes (properties), as well as the logical relationships between them. Business Rules : Business logic is embedded in the model to enforce rules, constraints, and conditions that ensure data consistency and accuracy. Technology Independence : The logical model is platform-agnostic—it is not tied to any specific database system or storage format. Visual Representat...