+++ At DLR, we are always looking for bright minds – even during the current exceptional circumstances. Our current vacancies can be found here. +++

My knowledge is shaping the future.

Bookmark
Course paper / final thesis

Development of Optimized Artificial Neural Networks for the Characterization of Wake Vortex Parameters

Starting date

1 February 2022

Duration of contract

6-12 months

Remuneration

up to German TVöD 5

Type of employment

Full-time (part-time possible)

An unavoidable consequence of aircraft lift generation is the formation of wake vortices – counterrotating air whirls which travel behind aircraft and pose a hazard to follower aircraft. Especially during approach and landing a wake vortex encounter should be avoided, given the limited reaction possibilities for pilots at low altitudes. In order to avoid such encounters, landing aircraft need to follow separations to one another. On the other hand, many airports are reaching their capacity limits. In the future, aircraft separations should be dynamic i.e. increase when a hazard is detected and decrease when it is possible to do so, resulting in an increase of efficiency and safety at airports, and as a direct consequence delivering more sustainable airport operations.

It is suggested to utilize LiDAR (Light Detection and Ranging) instruments as part of real-time wake vortex detection software to determine wake vortex positions and circulation strengths. Current analytical algorithms for LiDAR scan processing are not fast enough for real-time application, given that they are only partly automated.

As a result, the Institute for Atmospheric Physics at DLR Oberpfaffenhofen has started to employ artificial intelligence in the form of Artificial Neural Networks (ANNs) for the evaluation of LiDAR measurements. A unique and large labeled data set from a measurement campaign at Vienna International Airport in 2019 is available for the training of these ANNs. First studies have been conducted to find a suitable ANN architecture and evaluate the suitability of ANNs for this task. The obtained characterization precision and processing speed with ANNs for image processing motivate to perform further research in this field, with the ultimate goal of preparing ANNs for the real-time wake vortex characterization at airports. To reach this target, the ANNs have to become more robust, accurate and traceable. In the medium-term this provides increased safety and in the long-term higher airport efficiency.

Your tasks:

  • develop, compare and optimize ANN architectures
  • utilize physical phenomena such as the vortex position for the characterization of the associated circulation strength
  • link vortex parameters of a previous image (LiDAR scan) with the evaluation of the following image
  • evaluate, assess, verify the enhanced ANNs and compare them to existing LiDAR processing algorithms
  • develop reliable methods that enable ANNs to evaluate LiDAR scans with varying numbers of vortices (for instance a vortex may already be outside of the measurement window; but also vortices from previous aircraft may still be detectable

Your qualifications:

  • Master’s program: computer science, mechanical engineering, aerospace engineering,
  • physics, mathematics, meteorology, similar degree programs
  • good knowledge of a programming language, preferably Python
  • good knowledge of the German or English language, both written and spoken
  • at best case experience with artificial neural networks and Python modules such as TensorFlow

Your benefits:

Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development. Our unique infrastructure offers you a working environment in which you have unparalleled scope to develop your creative ideas and accomplish your professional objectives. Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (f/m/x). Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.

  • Apply online now
  • You can send this job advertisement via e-mail and complete your application on a personal computer or laptop.

    We need your digital application documents (PDF). The document upload function is not supported by all mobile devices. Please complete your application on a PC/laptop.

    Complete application on PC

Technical contact

Niklas Louis Wartha
Institute of Atmospheric Physics

Phone: +49 8153 28-3906

Send message

Vacancy 62006

HR department Oberpfaffenhofen

Send message

DLR site Oberpfaffenhofen

To location

DLR Institute of Atmospheric Physics

To institute