Development and Adoption of Model-Based Practices in Precision Agriculture

Decision-making in agriculture becomes increasingly challenging as farmers seek to meet agronomic, environmental and compliance goals. There is an increasing amount of data available to help reach these goals, and decision-making can be supported by computer-based DSSs. Unfortunately, not all DSS are adopted or contribute to efficient farming. The reasons for non-adoption are not easy to find, as such failures are often not reported in the literature, hindering the process of learning from our mistakes. In this chapter we attempt to identify some of the causes of failure and propose strategies to overcome them. This involves a mix of many years of experience in model development, improving fertilizer use and more recent studies from social sciences on adoption. It is challenging for natural and social scientists to work together towards understanding the processes in creating model-based solutions in precision farming. In the past, social scientists have concentrated on the behavioural reasons for (non)adoption of model-based practices (MBPs), but it is impossible to improve the usability of even the best scientific model as it is too late after it has been developed. Natural scientists have also developed excellent research models of no use to practitioners. To avoid such mismatches, all stakeholders, particularly potential users, must be involved from the beginning and at all stages in the process. Simultaneously, natural and social scientists must work together to create models suitable for the farmer. In conclusion, co-creation is important and users need to be involved from the start. A model must be designed to take account of stakeholder needs, address relevant questions and provide appropriate answers with minimal data requirements in a user-friendly way. Models must identify and respond to the social and individual-level phenomena which lead to a number of well-documented biases that influence behaviour and attitudes.