PhD: optimization of the deployment of environmental sensors

Back to jobs listing

INRAE presentation

The French National Research Institute for Agriculture, Food, and Environment (INRAE) is a major player in research and innovation. It is a community of 12,000 people with 272 research, experimental research, and support units located in 18 regional centres throughout France. Internationally, INRAE is among the top research organisations in the agricultural and food sciences, plant and animal sciences, as well as in ecology and environmental science. It is the world’s leading research organisation specialising in agriculture, food and the environment. INRAE’s goal is to be a key player in the transitions necessary to address major global challenges. Faced with a growing world population, climate change, resource scarcity, and declining biodiversity, the Institute has a major role to play in building solutions and supporting the necessary acceleration of agricultural, food and environmental transitions.

Work environment, missions and activities

You will be welcomed to the Research Unit on Information Technologies and Systems for Agrosystems. The Unit draws on engineering sciences and information and communication technologies to conduct research on methods and tools for the engineering of agro-environmental systems. The laboratory’s research is part of the agroecological transition. 

Data collection with sensors is a major issue in many domains such as precision agriculture, environmental monitoring or smart cities. However, optimal deployment of sensors remains a challenge. Currently, this task is often realized in an empirical manner by experts, which leads to heterogeneous approaches and may cause lacks in coverage. This is noticeable when deploying environmental sensors, which is often done in remote areas and require to physically go to them to collect data.

The goal of this thesis is to develop generic methods allowing to optimize this deployment under several criteria. Those can be the type of sensors, communication constraints with a gateway connected to the network, spatial coverage requirements, grouping of different kinds of sensors in order to establish correlation, terrain accessibility, or energy consumption.

In parallel, several strategies of deployment and data collection will be explored. This includes, for example, studying several sensors’ configurations and their associated constraints, but also study approaches such as low Earth orbit satellites or using drones for collection, or even distributed data collection involving several actors (including citizens).

The developed approaches will conjugate algorithmic robustness and theoretical guarantees, but also include a strong socio-technical dimension. Indeed, beyond algorithmic aspects, it will be expected to work with end users (researchers and engineers in various fields) in order to identify their specific needs and constraints and take them into account in the conception phase. They will also be able to evaluate the results, considering their domains’ practices and requirements.

The goals of the PhD are the following:

- identify the needs and constraints of researchers for the deployment of some environmental sensors (pluviometers, river sensors…);

- define models to represent the environment (geographical area, river network, underground milieu…) and the constraints (topography, network proximity…);

- propose deployment methods relying on strong fundamental principles (geometry, combinatorics…);

- obtain formal results on the developed structures and algorithms;

- implement the methods, apply them on datasets obtained from cartographic sources;

- evaluate the results with the experts, iterate to improve the methods.

The PhD will take place within the research collective ConnecSenS (https://www.connecsens.org/), which includes researchers from several fields and will be the main venue to obtain requirements and to evaluate the methods. The PhD supervisor will be Vincent Breton (LPCA, Clermont-Ferrand), and the two advisors will be Antoine Dailly (TSCF, Clermont-Ferrand) and Valentin Gledel (LAMA, Chambéry).

Due to the diversity of situations, and even if the PhD is centered on combinatorial and semi-discrete optimization, several domains are relevant for applicants: geometry/topography, graph theory, data science...

Training and skills

Recommended training: Masters in computer science or applied mathematics

Desired knowledge: Algorithms, programing, data science, topography, geometry

Appreciated experience: Research internship, interdisciplinary experience

Skills: Scientific curiosity, interest in the diversity of specificities for different disciplines, teamwork, empirical development and evaluation as well as formal approaches

INRAE's life quality

By joining our teams, you benefit from (depending on the type of contract and its duration):

- up to 30 days of annual leave + 15 days "Reduction of Working Time" (for a full time);
- parenting support: CESU childcare, leisure services;
- skills development systems: training, career advise;
- social support: advice and listening, social assistance and loans;
- holiday and leisure services: holiday vouchers, accommodation at preferential rates;
- sports and cultural activities;
- collective catering.

The Cézeaux site is served by subway line A, and is also equipped with parking facilities and services dedicated to cycling.

How to apply

I send my CV and my motivation letter