On June 12th, a special session took place at the ModelIt 2019 conference. The session started with a keynote presentation by Dr. Jorge Hernandez, coordinator of RUC-APS
From the genetic design of the seed, till their planting and harvest processes, considering the Farmers desired productivity as well as the expected end-customer service level, RUC-APS aims to provide a knowledge advancing in agriculture based-decision making through the development of a high impact research in terms of integrating real-life based agriculture requirements, land management alternatives for a variety of scales, unexpected weather and environmental conditions.
Agrifood value chain modelling as a tool to face uncertainties
The agriculture value chain concept it is certainly not new. But, since new unpredictable environments (weather, economy, technology, etc.) has emerged, it has become more difficult to manage it, but also difficult to compare to similar cases from the past, since most of them does not exists. In addition to this, there is a lack on global agriculture value awareness and Knowledge Management, thus a lack on participative and collaborative ICT developments, which implies that there are no validated framework to manage risks in agribusiness, since managing high uncertainty and unexpected events is even more challenging. Therefore, the genetic design of the seed, till their planting and harvest processes at the end of the agriculture value chain, this is research use and implement a a variety of modelling languages to provide customised answers to each of the challenges and requirements in the agrifood value chain. Thus, and throughout the H2020 RUC-APS project, the variety of modelling approaches is used to integrate real-life based agriculture requirements, land management alternatives for a variety of scales, unexpected weather and environmental conditions as well as innovation for the development of agriculture production systems and their impact over the end users under participatory ICT developments. Key outcomes are measured in terms of usability and impact of these models in real-life agriculture domains.