2019-01902 - PhD Position F/M Numerical rule mining for the prediction of the dynamics of crop diseases
Le descriptif de l’offre ci-dessous est en Anglais

Type de contrat : CDD de la fonction publique

Niveau de diplôme exigé : Bac + 5 ou équivalent

Fonction : Doctorant

A propos du centre ou de la direction fonctionnelle

Inria, the French national research institute for the digital sciences, promotes scientific excellence and technology transfer to maximise its impact.
It employs 2,400 people. Its 200 agile project teams, generally with academic partners, involve more than 3,000 scientists in meeting the challenges of computer science and mathematics, often at the interface of other disciplines.
Inria works with many companies and has assisted in the creation of over 160 startups.
It strives to meet the challenges of the digital transformation of science, society and the economy.

Contexte et atouts du poste

Applications are welcome for a PhD position starting in January 2020 (or as soon as possible thereafter) with a duration of 3 years, to undertake research in the area of machine learning and data science applied to agricultural data. The project aims to develop novel methods to assist agricultural scientists with the analysis of the dynamics of crop diseases. 

Being an interdisciplinary project, the PhD will take place at the IRISA (http://www.irisa.fr/) and INRA research centers (http://www.inra.fr/), both located in France. The PhD thesis is financed by the #DigitAg (https://www.hdigitag.fr/fr/) convergence lab, and the PhD student will be enrolled in the graduate school of the University of Rennes I.


The extremely long and diverse list of existing phytosanitary problems on crops has motivated agricultural research & development efforts to develop decision support tools (DST) for effective crop protection. One of the goals of such tools is to limit the use of phytosanitary products in crops. Given the plethora of existing data on the dynamics of diseases, such a goal requires us to exploit data science techniques in order to accelerate our understanding on the behaviour of diseases as well as to automate the processes for decision support.

This thesis aims at assisting crop protection experts by automating the discovery of working hypotheses on plant disease behaviour. For this purpose we will resort to machine learning techniques based on the mass of data collected in epidemiological surveillance networks. This quest for hypotheses amounts to mining "hybrid rules" on data. Such rules  predict a numerical variable (e.g., the incidence of downy mildew disease) by taking into account the interactions between categorical variables (e.g. the phenological stage of the plant) and statistical models on numerical variables. This original approach seems a promising way of reconciling predictive modeling and "local" configuration in line with the great diversity of agronomic situations to be considered. 

Mission confiée

To apply for the position, the candidate must send an email to the list of contacts below. The email should include:

  • A CV
  • A copy of the candidate's latest diploma
  • A copy of the transcripts of the candidate's last year of studies
  • At least two recommendation letters
  • A statement letter explaining the candidate's motivations to apply for the position

Contact people

  • David Makowski (INRA, David.Makowski@inra.fr)
  • François Brun (ACTA, francois.brun@acta.asso.fr)
  • Alexandre Termier (University of Rennes I, alexandre.termier@irisa.fr)
  • Luis Galárraga (Inria, luis.galarraga@inria.fr)

Principales activités

As a PhD student you will primarily devote yourself to your research. This will include the development of algorithms to mine hybrid regression rules from the observations of the incidences of diseases in different types of crops. This task will require continuous exchanges with experts in the field of crop diseases and pests, as they will be able to validate the accuracy of the output rules. Such rules will help improve the effectiveness of plant health monitoring systems by making better use of the observed data collected in this context.


We are searching for candidates with a master in computer science or bioinformatics with competences in data science and machine learning, and a good disposition towards interdisciplinary work. This latter requirement is important as the candidate will need to acquire a significant amount of expertise in the field of crop diseases. The candidate should be proficient in written and spoken English (at least B2 level according to the CEFR system).


  • Subsidized meals
  • Partial reimbursement of public transport costs


PhD student : monthly gross salary amounting to 1982 euros for the first and second years and 2085 euros for the third year