Section: Application Domains

Agriculture and environment

  • Dairy farming. The use and analysis of data acquired in dairy farming is a challenge both for data science and for animal science. Its goal is to improve farming conditions (health, welfare and environment) as well as farmers’ income. Nowadays, animals are monitored by multiple sensors giving a wealth of heterogeneous data (ex: temperature, weight, milk composition…). Current techniques used by animal scientists focus mostly on mono-sensor approaches. The dynamic combination of several sensors could provide new services and information useful for dairy farming. A PhD thesis will begin soon to study such combinations of sensors and to investigate data mining methods, especially pattern mining algorithms. The challenge is to design new algorithms taking into account the data heterogeneity, coming both from their nature and the different time scales involved, and to produce patterns that are actually useful for dairy farming. This thesis will be an original and important contribution to the new challenge of the IoT (Internet of Things) and will interest domain actors to find new added value to a global data analysis. The PhD thesis will take place in an interdisciplinary setting bringing together computer scientists from Inria and animal scientists from INRA, both located in Rennes.

    Similar problems are investigated with the veterinary department of the University of Calgary in the context of cattle monitoring from multiple sensors placed on calves for the early detection of diseases.

  • Optimizing the nutrition of individual sow. Another direction for further research is to combine data flow with prediction models in order to learn nutrition strategies. We are currently starting a project with INRAon the nutritional requirements and the optimal diet to be supplied to individual lactating sow. The research issue will be to develop decision algorithms for the determination of the optimal ration (amount and composition) to be fed to a given sow, on a given day, considering all the information available (real-time observation data flow and historical data). Issues concern the design of an incremental learning algorithm that will compute the animal profile and how to determine the best feeding plan. Efficiency issues of developed algorithms will also be considered since the proposed software should work in real-time on the automated feeder.

  • Ecosystem modeling and management. Ongoing research on ecosystem management includes modelling of ecosystems and anthroprogenic pressures, with a special concern on the representation of socio-economical factors that impact human decisions. A main research issue is how to to represent these factors and how to integrate their impact on the ecosystem simulation model. This work is an ongoing cooperation with ecologists from the Marine Spatial Ecology of Queensland University, Australia and from Agrocampus Ouest.