[Defended thesis] Hugo Deléglise: Improving food security systems by linking heterogeneous data – The case of agricultural production in West Africa

Improving food security systems by linking heterogeneous data – The case of agricultural production in West Africa

My name is Hugo Deléglise. After a bachelor's degree in fundamental mathematics at the Faculty of Science in Montpellier, I obtained a master's degree in MIASHS (Mathématiques et Informatique Appliquées aux Sciences Humaines et Sociales) at the Faculty of Arts in Montpellier.
During my 2 years of master's studies, I carried out 2 internships at Ird on the subject of "Optimizing the collection, management and processing of data collected as part of an operational research project on onchocerciasis". These last years of study and this research internship have confirmed my desire to use my methodological and technical knowledge to respond to concrete development issues.

• Starting date: October 2018
• University : Universitty of Montpellier
• PhD school: I2S – Information, Structures, Systèmes
• Scientific field: IT
• Thesis management: Agnès Bégué, Mathieu Roche (Cirad, Tetis) et Maguelonne Teisseire (Inrae,Tetis)
• Funding: #DigitAg – Cirad
• #DigitAg : Cofunded PhD – Axe 5–  Challenge 8

Keywords: Food security, heterogeneous data, artificial intelligence, agriculture, West Africa

Abstract:  This thesis aims at the improvement of Food Security Monitoring systems through the use of heterogeneous data, focusing on the management of agricultural production risks. While agroclimatic data (e.g., satellite imagery, climate information, etc.) has been widely used for this task, the use of data coming from different domains (i.e., household surveys, social media, press, business analyses) has often been neglected. Remote sensing data is widely used for real time monitoring of vegetative growth, but is not sufficient to explain complex food safety-risk phenomena. The aim of this thesis is twofold: (i) to define innovative data mining techniques that will be able to exploit this heterogeneous data context. To reach this goal, three phases have been identified: (a) automatic discovery of spatial features from heterogeneous data, (b) features linking (i.e., through the definition of new similarity measures between features) and (c) data mining (i.e., through the definition of new network analysis, clustering and deep learning techniques) ; (ii) to show how remote sensing data can be enriched by linking it to data from different domains in order to make it more suitable for food safety-risk analysis tasks. During this thesis, we will focus on studies carried out in Burkina Faso, by exploiting satellite (with vegetation and climate features), economic, and textual data. The analytical framework will be based on retrospective analysis, focusing on the crop failures of 2007 and 2011 in Burkina Faso as major cases of studies. We will possibly extend our study to other areas, using data collected in Senegal. Given the interdisciplinary path at the basis of this work, the results of the analysis and the defined techniques are expected to generate significant interest in socio-economic, remote sensing, and data mining fields. During the PhD period, the student will also participate in short term missions (e.g., periods of two or three weeks) to West Africa, working with experts in the field of remote sensing and food security.

Jury compound:

Josiane Mothe, Professeur, Université de Toulouse. Rapporteure
Stan Matwin, Professeur, Dalhousie University, Canada. Rapporteur
Pierre Gançarski, Professeur, Université de Strasbourg. Examinateur
Isabelle Mougenot, Maître de conférences, Université de Montpellier. Invitée
Mathieu Roche, Chercheur HDR, CIRAD – UMR TETIS. Directeur
Maguelonne Teisseire, Directrice de Recherche, INRAE – UMR TETIS. Co-Directrice
Elodie Maître d’Hôtel, Chercheuse HDR, CIRAD – UMR MOISA. Encadrante
Roberto Interdonato, Chercheur, CIRAD – UMR TETIS. Encadrant principal
Agnès Bégué, Chercheuse HDR, CIRAD – UMR TETIS. Encadrante

Download the thesis manuscript

Contact:  hugo.deleglise [AT] cirad.fr​