Section: New Software and Platforms

Stochastic systems for knowledge discovery and simulation

The CarottAge and ARPEnTAge Systems

Functional Description.

The system CarottAge is based on Hidden Markov Models of second order and provides a non supervised temporal clustering algorithm for data mining [84]. CarottAge is currently used by INRA researchers interested in mining the changes in territory and landscape related to the loss of biodiversity (projects ANR BiodivAgrim and ACI Ecoger) and/or water contamination. CarottAge was also used for mining hydromorphological data and gave interesting results for that purpose.

ARPEnTAge, for “Analyse de Régularités dans les Paysages : Environnement, Territoires, Agronomie” is built on top of the CarottAge system to fully take into account the spatial dimension of input sequences. It can be used for analyzing spatio-temporal databases [85] and for space-time clustering of a landscape based on temporal land uses. Displaying tools and the generation of time-dominant shape files have also been defined. With agronomists, we are now focusing on the simulation of unknown spatial time sequences in order to explore various crop management scenarios.

CarottAge and ARPEnTAge are freely available under GPL license. A special effort is currently aimed at designing interactive visualization tools to provide the expert a user-friendly interface.