Valentine Judge is defending his PhD thesis "Machine Learning for Land Use Change Analysis and Modelling. An exploration of urban development on the French-German border area"


The defense will take place in Besançon at the Salon Preclin, UFR SLHS on July 16th at 3pm.

This work was directed by Jean-Philippe Antoni, Professor at the University of Borgogne, laboratory ThéMA and co-directed by Olivier Klein, Associate researcher at the LISER Institute, Luxembourg.


Defense jury

Francisco Escobar, Professor at the University of Alcala, Spain

Giovanni Fusco, Associate researcher "HDR" at CNRS, France

Guy Engelen, Emeritus researcher VITO Institute, Belgium

Bernhard Köppen, Professor at the University of Koblenz-Landau, Germany



Urban development can take different forms or features, depending on its geographical location and its socioeconomic, political and cultural context. Nevertheless, the overall action relies on one fundamental principle: building construction in order to give people housing. Therefore, the main objective of this research is to determine whether an underlying universal aspect of the urban development process can be distinguished from a specific one, being the reflect of local specificities. Specifically, this research analyzes the land use change on the French-German cross-border area. Indeed, the border context enhances the difference within this territory. Nonetheless, the internal European border importance as a separation is getting lower while European Union agreement and cooperation are getting stronger. Consequently, we tend to question a potential homogeneity of such area according the urban development analysis. To gain a better understanding of the urban development in the French-German cross-border area, a specific method using a decision tree (DT) process to generate and calibrate urban transition rules for cellular automata (CA) has been developed. In order to define CA rules, the learning algorithm is provided with data of land use, from 1990 and 2006, accessibility to the main urban area and country location. The findings demonstrate that the rule set identified rules, which are constrained at different levels: from the initial land use state needed for urbanization to the geographical location in a specific country. The analysis therefore shows rules specific to France or Germany, as well as rules free from any state location constraints, which characterize a cross-border urbanization process. The latter is more influenced by the location toward main urban areas. Proper neighborhood and internal characteristic of urbanized cells depending of the nature of the rule (French, German or Cross-border) are explicitly defined. In conclusion, this research contribution can be summarized according to the following three orientations: (1) from a theoretical point of view, which propose to identify urban processes degree of universality, (2) from a thematic outlook, describing the influence of the urban development process location on the border area, (3) from a methodological point of view, pairing DT and AC to automatically design and calibrate the urban development model used in this research work.


thèse Valentine

Last Updated: Wednesday, 27 November 2019 10:43

Olivier Bonin, researcher IFSTTAR at LVMT (Laboratoire Ville-Mobilité-Transport, Champs-sur-Marne), is defending his Accreditation to supervise research at the laboratory ThéMA.


The defense will take place on may the 27th at 2 pm, at the " Grand Salon" (18, rue Chifflet, UFR SLHS).


Olivier Bonin


Geography has since antiquity used cartography to describe the shape of the Earth and its population. Indeed, cartography is an analogical model of the world particularly suited to the description of shapes, spatial arrangements and spatial relationships, i.e. information of a qualitative nature, the meaning of which emerges when reading maps. The theoretical and quantitative turn in geography has seen the development of many formal and numerical modelling approaches in which, paradoxically, it is more difficult to integrate the question of the meaning of space in human activities. In this work, I propose a formal modelling framework aimed at clarifying the meaning of space. Through a phenomenological approach, I identify the different forms of perception of individuals and human communities, in order to propose general principles that are then mathematized by techniques from the sciences of complexity. Three models related to urban morphogenesis illustrate different facets of this general modelling framework aimed at giving meaning to space.



Defense jury

Alessandro Sarti, Director of Research at EHESS and joint to Collège de France

Gabriel Dupuy, Emeritus Professor at the University Paris I -

Jean-Philippe Antoni, Professor at the University of Bourgogne-Franche-Comté – TheMA

Geoffrey Caruso, Professor at the University of Luxembourg

Cyrille Bertelle, Professor at the University Le Havre – LITIS

Pierre Frankhauser, Emeritus Professor at the University of Franche Comté - ThéMA


Personal homepage :



Last Updated: Thursday, 09 May 2019 09:10

An article published in Nature Scientific Reports: Huge decrease of frost frequency in the Mont-Blanc Massif under climate change


Benjamin Pohl, Daniel Joly, Julien Pergaud, Jean-François Buonchristiani, Paul Soare & Alexandre Berger, Nature Scientific reports volume 9, Article number : 4919 (2019)           


This study co-signed by 5 members of the laboratory Biogéosciences (Dijon) was led in the framework of the ANR project « VIP-Mont-Blanc » about the consequences of climate change in the Mont Blanc massif. It is based on 13 models of simulated temperatures used to define the IPCC’s climate scenarios. These data have a coarse spatial resolution, i.e. grid cells of a 100 to 200 km, but have a very high temporal resolution: a daily value of minimum and maximum temperature from 1850 to 2100, amounting to 55 000 days! The algorithm developed by the Bourgogne Franche-Comté team aims at reducing this data’s spatial inaccuracy by “downscaling”. Eventually, the coupling of physical and geographical models provided very high spatio-temporal resolution climate data. At a 200 m resolution over the entire Mont Blanc massif and for 55 000 days, each of the 13 simulations were downscaled according to two scenarios, optimistic vs pessimistic.

Until the middle of the 20th century, the study shows few differences between scenarios but in the second half, strong evolutions arise. Under the pessimistic scenario, every third day will be frostless on the Mont Blanc summit in summer, with a risk of rock wall destabilization and collapse all over the range. Things will be not better in winter with very little snow in the valley.


Mont Blanc JC

                   Mont Blanc massif from the Brévent ; Credit photo : Jean-Christophe Foltête

Last Updated: Monday, 08 April 2019 13:17
Strony internetowe