182-Machine Learning based solutions for M2M satellite communications

182-Machine Learning based solutions for M2M satellite communications

  • Contract :Ph.D.
  • Duration :36 months
  • Working time :Full-time
  • Experience :Entry Level
  • Education level :Master’s Degree, MA/MS/MSc

Your mission at CNES :

In this thesis, we explore novel coding and modulation schemes based on Machine Learning solutions, in order to alleviate the limitations of classical digital communication techniques when applied to M2M satellite communications.

The focus will be on the design of robust deep neural channel encoders and decoders which can adapt better to the overall channel characteristics and to short blocklength packets, as compared to classical linear codes. Next, we will explore the joint design of coding and modulation schemes based on auto-encoders in order to explore more intricate designs than separate schemes. The design and analysis of these solutions will rely on the adaptation of deep learning solutions to communication systems, while exploiting tools from coding theory, information theory and digital communication chains design.

The host laboratory is TéSA (

For more information, contact  from ISAE/DEOS

Candidate profile searched:

Graduate of an engineering school (specialty Telecommunications or Data Science), Master in Telecommunications, Master in Data Science, Master in Signal Processing

We suggest you to contact first the PhD supervisor about the topics and the co-financial partner (found by the lab !). Then, prepare a resumé, a recent transcript and a reference letter from you M2 supervisor/ engineering school director and you will be ready to apply online !

CNES will inform about the status of your application in mid-June.

More details on CNES website :

  • Our address

    10 Avenue Edouard Belin, 31400 Toulouse, France
    Would you like to calculate the access time? Click here