Surface and ground waters are exposed to pesticides used in agronomy. To prevent water pollution by pesticides, the reliable predictions of the water outflows from fields are needed. The most frequently used models are difficult to apply due to the lack of required data about local soil properties and climate. To improve the performance and applicability of water outflow modeling we used a modeling approach based on machine learning techniques applied to data obtained from long-term experimental agronomic station La Jaillière, France. The results show overall improvement in the prediction of discharge through sub-surface drainage systems, and partial improvement in the prediction of the surface runoff. Using predictions of our models for decision support about the application time and dosage of pesticides will significantly improve the efficacy of water protection from pollution with pesticides.
F.15 Development of a new information system/databases
COBISS.SI-ID: 28041255In the area of development and use of knowledge technologies for improving education approaches, we developed a mobile application QTvity that encourages and supports real-time interaction between instructor and students during lectures. It also allows for the collection of data on students' understanding and communication, while the analysis of these data provides an additional insight into the learning process and the basis for its improvement. The application was presented at the International Conference CompSysTech 2015 in Dublin where we received an award for the best contribution.
F.15 Development of a new information system/databases
COBISS.SI-ID: 29039143A human-robot interface called WHIMBOT was developed in the context of the EU FP7 project WHIM. It enables the conversation with the humanoid robot NAO with the aim of evaluating computer-generated creative ideas. WHIMBOT was presented at the media-covered public event »Show, Tell, Imagine« at the Queen Mary University of London and at ICT 2015 in Lisbon. The WHIMBOT interface also served as the basis for the development of NAO robot applications Chatty and NAO live chat, which were presented at the TTT 2015 conference and at the 49th International Trade and Business Fair (MOS 2016). The Department of Knowledge Technologies received a special MOS recognition award from the Chamber of Craft and Small Business of Slovenia (OZS) for the innovative and compelling promotion of science and a successful collaboration with the Science and technology section of OZS. Our member dr. Vid Podpečan also received the "Prometheus of science" award of the Slovene Science Foundation for "all-round promotion of robotics, especially the NAO humanoid robot among young people".
E.01 National awards
COBISS.SI-ID: 28514087Our team won the competition of the European Space Agency ESA Mars Express Power Challenge with the development of the best solution for forecasting the use of electric energy on the space probe. In the spring 2016 ESA organised an open competition to develop a model for predicting the use of electric power on the space probe Mars Express. Even though the probe was launched already in 2003 and has used up most of its fuel, the probe is still operational. One of the greater challenges in prolonging its operations is the spent battery, which is why ESA wanted to obtain a model that would enable an accurate prediction of the necessary energy for heating the probe and, with this, indirectly, an estimate of the energy that is available for scientific measurements. We developed the winning solution which uses machine learning methods for generating the model.
E.02 International awards
COBISS.SI-ID: 30018599In collaboration with the Department of Environmental Sciences, JSI, we developed a method and a decision support system for the assessement of electric energy production technologies in Slovenia in the period 2014-2050. The approach is based on two hierarchical qualitative multi-criteria models for the evaluation of individual technologies and technology mixtures, respectively. We assessed eight individual technologies (coal fired, gas fired, biomass fired, oil fired, nuclear, hydro, wind, and photovoltaic) in the context of 64 possible long-term scenarios of electric energy production in Slovenia. The purpose of the method and the decision support system is to contribute to an informed debate on the future development of the energy sector in Slovenia and formulation of a national strategy.
F.15 Development of a new information system/databases
COBISS.SI-ID: 29867815