Post-doctoral fellow in machine learning for distributed acoustic sensing over optical fiber networks - 24 months contract

Who we are ?

Télécom Paris, part of the IMT (Institut Mines-Télécom) and a founding member of the Institut Polytechnique de Paris, is one of France's top 5 general engineering schools.

The mainspring of Télécom Paris is to train, imagine and undertake to design digital models, technologies and solutions for a society and economy that respect people and their environment.

We are looking for a Post-doctoral Fellow in machine learning for distributed acoustic sensing over optical fiber networks. You will join the COMELEC Department in GTO team. The Optical Telecommunications Group (GTO) is home to the research programs of six faculty members and a state-of-the-art laboratory on optical fiber transmission. We conduct advanced research in high-rate fiber-optic transmission, optical network architectures, advanced lasers for communications, integrated photonics, and distributed optical fiber sensors.

SCIENTIFIC CONTEXT

The concept of a smart city is based on the collection and exploitation of data extracted by numerous sensors providing information on vehicle traffic, the detection of human presence and numerous events affecting infrastructures (water and gas networks, buildings, bridges and tunnels, etc.). The current approach to collecting this information is to deploy a multitude of discrete, dedicated sensors or to deploy distributed, dedicated fiber optic detection cables. This deployment has a high logistical cost (installation, energy supply, maintenance). However, fiber-optic telecommunication networks already crisscross our cities: using this available infrastructure to capture, locate and identify vibration events is a very attractive approach. Much of the research into sensing over telecom infrastructure has replicated Distributed Acoustic Sensing (DAS) solutions, originally used on dedicated sensing cables. These solutions have yielded promising results in road/rail traffic monitoring and in measuring dynamics at the scale of an urban or regional area: near-surface characterization, detection of high levels of use of certain sites in times of crisis (as in the current COVID19 crisis) and other seismic events.

In the fields of DAS and geophysics, researchers regularly point out that DAS measurements on deployed fiber optic infrastructures are able to provide a coverage and a bandwidth that is not met with conventional discrete sensors such as seismometers. Despite this positive observation, DAS still lacks the sensitivity of conventional discrete sensors. The integration of powerful sensing techniques into the optical network will pave the way for improved real-time network monitoring and the provision of valuable data for a multitude of applications.

In an optical network, technical obstacles arise from the heterogeneity of topologies and fiber environments. In this project, we propose to take advantage of machine learning techniques to help in achieving event detection from DAS data measured over the deployed optical fiber telecom infrastructure. Characterising and locating these vibrations as accurately as possible, followed by identifying them using machine learning algorithms, opens the way to network monitoring and to the provision of valuable data for a multitude of applications (road/rail traffic supervision, security, monitoring of urban dynamics to detect hazards, particularly in times of crisis, etc.).

We plan to provide proofs-of-concept of machine learning solutions for DAS systems by dividing the study in two parts:

1.       Compression of captured DAS data and study of most appropriate representations for the extraction of the main features from the data (wavelet representation, multi-resolution representation, triangulation, application of audio processing tools, etc.)

2.       Processing and identification of multiple vibration events that may happen simultaneously or that may have an impact over large portions of the deployed fiber cables.

Your main tasks will be to :

• To carry out research missions in the field of photonics

• To ensure supervision and tutoring missions

• To contribute to the reputation of the School, the Institut Mines-Télécom and the Institut Polytechnique de Paris

The ideal candidate will have a PhD or equivalent in Electrical Engineering or Computer Science. You have knowledge in digital signal processing (DSP) algorithms and in machine learning algorithms. Knowledge of optical fiber sensors or optical transmission systems and networks  is desirable. Skills in DSP programming (through MATLAB or Python) are appreciated.

You are recognized for your ability to work in a team and for your interpersonal skills.

You are fluent in english.

Why join us?
You'll be working in a fast-growing, pleasant, green and accessible environment (especially for people with disabilities) just 20 km from Paris (RER B and C suburban train lines, close to major roads, shared shuttle departing from Porte d'Orléans). You will benefit from :

• 49 days annual leave (CA + RTT)

• flexible working hours (depending on department activity)

• telecommuting 1 to 3 days/week possible

• 75% public transport pass reimbursement

• Proximity to numerous sports facilities, concierge service, underground parking, in-house catering, etc.

• Staff association at school and ministry level

• Good to know: our social security contributions are lower than in the private sector

Other information :
Application deadline: October 31, 2025
Job type : 24 months fixed-term contract
Job description ici

Scientific contact person: Élie AWWAD  (elie.awwad@telecom-paris.fr)

Administrative contact person: Hamidou YAYA KONE (hamidou.kone@telecom-paris.fr)

Our recruitment is based on skills, without distinction of origin, age, gender identity, or sexual orientation, and all our positions are open to individuals with disabilities.