Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?
Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur Graph Search.
Dryland irrigation is a major concern in arid and semiarid regions where agricultural output is low and water a scarce and vital resource. Irrigation efficiency and sustainability are, therefore, of paramount importance in these regions, where small farmers generally over-irrigate vegetables to avoid yield loss, resulting in excessive water consumption, unnecessary water pumping costs, and soil degradation. Improving dryland irrigation support requires field data, which is often scarce and unreliable in developing countries, being mostly collected manually with obsolete equipment. Modern automatic weather stations are costly, and local resources for station repair and maintenance are limited. The research project Info4Dourou2.0 aims to improve environmental data collection in developing countries by using low-cost wireless sensors networks (WSN). Hydrometeorological stations have been designed specifically for harsh environmental conditions and the limited local resources. They are simple to install and require little maintenance. The collected data is available in real time via a mobile phone and a web interface. These completely automatic stations have been developed by Ecole Polytechnique Fédérale de Lausanne (EPFL) and the start-up sensorscope, with the aim of being manufactured, assembled, maintained, and commercialized locally. Results of the present study show that by coupling autonomous and continuous measurements of meteorological variables with soil-water-plant-atmosphere models, we have designed a simple irrigation management system that has a strong potential to improve agricultural production: up to a 38 % yield increase has been achieved using 20 % less water compared to the unassisted way of irrigating.