Jobangebot connecticum Job-1753959

Student physics, meteorology, engineering or similar (f/m/x)

Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Info zum Arbeitgeber

Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Wissenschaft & Forschung, Luft- und Raumfahrt, Energie, Verkehr, Sicherheit, Digitalisierung

Firmensprache

Deutsch, Englisch

Gründungsjahr

1907

Mitarbeiter

10.001 - 50.000

Branche

Computer Engineering, Energie, Forschung, Luft- und Raumfahrttechnik, Sicherheit, Transport und Verkehr

Kontakt

Bei Fragen zu Stellenangeboten aus unserem Jobportal DLR.de/jobs wenden Sie sich bitte an die in den Stellenanzeigen genannten Ansprechpartnerinnen und Ansprechpartner.

Homepage
DLR.de

Karriere-Website
DLR.de/jobs

Course paper/final thesis
Enter the fascinating world of the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt; DLR) and help shape the future through research and innovation! We offer an exciting and inspiring working environment driven by the expertise and curiosity of our 11,000 employees from 100 nations and our unique infrastructure. Together, we develop sustainable technologies and thus contribute to finding solutions to global challenges. Would you like to join us in addressing this major future challenge? Then this is your place!
For our Institute of Atmospheric Physics in Oberpfaffenhofen we are looking for
Student physics, meteorology, engineering or similar (f/m/x)
Investigation of thunderstorm size dependence in thunderstorm identification with CNN
What to expect:
Thunderstorms and their accompanying phenomena (e.g. lightning, heavy rain, hail) endanger human life and have a negative impact on the economic strength of various sectors. In the course of climate change, the frequency of these extreme weather events is expected to increase. This requires the availability of extremely reliable thunderstorm forecasts with very high requirements for spatiotemporal resolution. The DLR Institute of Atmospheric Physics has decades of experience in the development of customized forecasting tools for special applications (e.g. aviation).
Thunderstorms are the result of complex multi-scale dynamics and therefore cannot be directly linked to a single meteorological variable. Instead, thunderstorm forecasting based on numerical weather simulations relies on post-processing methods, in which simulation data is analyzed for signs of thunderstorm activity. Recently, the application of machine learning methods has brought significant advances in post-processing. A particularly promising approach for thunderstorm detection is the use of convolutional neural networks (CNN), which has been demonstrated in a prototype series of experiments. Initial evaluations indicate that the quality of the identification of thunderstorm activity using CNNs is size-dependent: large-scale thunderstorms are detected more reliably than small isolated cells. Your task is to understand and quantify this observation by means of systematic investigations. An integral part of the master's thesis is the development, training and tuning of a lean and robust CNN architecture for thunderstorm detection in image-like simulation data. Building on this, the classification quality of the model is then to be quantified as a function of the spatial size of the thunderstorm by means of systematic studies. This requires in particular the application of modern statistical evaluation methods on very large amounts of data. Possible improvements to the existing method are to be derived from the results and implemented in an improved prototype.
What we expect from you:
  • completed Bachelor's degree in physics, meteorology or engineering
  • good knowledge of atmospheric physics and/or statistical physics
  • good knowledge of programming, ideally in Python
  • ideally initial experience in training machine learning models on GPUs
  • high degree of independence and team spirit
What we offer:
DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified.
Further information:
Starting date: immediately
Duration of contract: 6 - 12 months
Type of employment: part-time
Remuneration: up to the German TVöD 5
Vacancy-ID: 95767
Contact:
Kianusch Vahid Yousefnia Institut für Physik der Atmosphäre
Tel.: 08153 28 3275

Info zum Arbeitgeber

Deutsches Zentrum für Luft- und Raumfahrt (DLR)

Wissenschaft & Forschung, Luft- und Raumfahrt, Energie, Verkehr, Sicherheit, Digitalisierung

Firmensprache

Deutsch, Englisch

Gründungsjahr

1907

Mitarbeiter

10.001 - 50.000

Branche

Computer Engineering, Energie, Forschung, Luft- und Raumfahrttechnik, Sicherheit, Transport und Verkehr

Kontakt

Bei Fragen zu Stellenangeboten aus unserem Jobportal DLR.de/jobs wenden Sie sich bitte an die in den Stellenanzeigen genannten Ansprechpartnerinnen und Ansprechpartner.

Homepage
DLR.de

Karriere-Website
DLR.de/jobs

Info zur Bewerbung
Jobtitel:

Student physics, meteorology, engineering or similar (f/m/x)

Jobkennzeichen:
connecticum Job-1753959
Bereiche:
Naturwissenschaften: Geographie-Geowissenschaften, Naturwissenschaften allg., Physik
Einsatzort: 82 Weßling-Oberpfaffenhofen; Bayern
Bewerbung

Jobbörse Job beanstanden