Romain Mejean

Romain Mejean
Université Toulouse II - Jean Jaurès | UTM · Département de Géographie, Aménagement et Environnement

PhD student in Geography


How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
PhD student in Geography at University of Toulouse, GEODE Lab (UMR 5602, CNRS). My research interests are in spatial modelling and simulation. More specifically, I focus on the confrontation and coupling of modelling approaches used in land use and land cover changes modelling: process-based models (ABM) and pattern-based models (e. g. deep learning). My case study is deforestation in the Ecuadorian Amazon. I am therefore interested in agent-based models (ABM), complexity theory, epistemology of spatial modelling, remote sensing, prospective, spatial analysis and geomatics as a whole. As part of my Master's thesis, I was also interested in the social division of space, residential segregation and the modelling of residential choice (ABM).
Additional affiliations
October 2017 - present
Université Toulouse 2 Jean Jaurès · UMR 5602 - GEODE
  • PhD Student
October 2017 - present
Université Toulouse  II - Jean Jaurès
  • Doctorant contractuel chargé d'enseignement
February 2015 - May 2015
  • Student trainee
  • Implementation of data in a spatial agent-based model used to study transport self-organization in Brazzaville (Congo).
September 2012 - June 2017
Aix-Marseille Université
Field of study
  • Geography & Spatial analysis


Publications (8)
Full-text available
Spatial agent-based models (ABMs) are increasingly used to study land use and land cover changes (LUCC). This process-based approach allows formalizing the interactions between society and environment through the modelling of human decision-making processes regarding to the land use and its impact on regional land cover. Data-driven ABMs, which hav...
Conference Paper
Full-text available
Land use and land cover change (LUCC) models are increasingly being used to anticipate the future of territories, particularly through the prospective scenario method. In the case of so-called trend or Business-as-Usual (BAU) scenarios, the aim is to observe the current dynamics and to extend them into the future. However, as they are implemented a...
Conference Paper
Full-text available
This article presents the PASHAMAMA model that aims at studying the situation in the northern part of the Amazonian region of Ecuador in which the intensive oil extraction has induced a high rise of population, pollution, agricultural work and deforestation. It simulates these dynamics impacts on both environment and population by examining exposur...
Cette communication traite d’une méthode de cartographie participative, le Zonage à Dires d’Acteurs (ZADA) et de ses résultats sur le territoire de l’Amazonie équatorienne. Le ZADA consiste en la formalisation synthétique des connaissances spatiales d’acteurs locaux, sous la forme de cartes. Ces connaissances sont récoltées au cours d’entretiens ré...


Cited By


Project (1)
L’objectif de ce projet est de caractériser les vulnérabilités humaines et environnementales recensées dans la région Amazonienne de l’Equateur. Ce territoire encore largement forestier, et présentant l’une des biodiversités les plus élevées au Monde, est l’objet d’une exploitation de ses gisements pétroliers depuis 50 ans, entrainant des conséquences environnementales importantes : défrichements pour une colonisation agricole, contaminations pétrolières affectant le territoire et ses habitants.