Project
Digital Future Farm (DFF)
This digital twin represents the nitrogen cycle of an arable or a dairy farm. It comprises of existing process-based and new data-driven models fed with real farm data to mimic reality. It can be used by farmers and researchers to reduce the nitrogen surplus of a farm while maintaining crop yields.
The objective is to develop a digital twin that represents an arable or dairy farm, or a mixture of these two. This digital twin, the Digital Future Farm (DFF) comprises of different components, and is connected with real farm data to mimic reality as closely as possible. By doing so, the DFF can be used by farmers and researchers to reduce the nitrogen surplus of a farm while maintaining or even increasing crop yields. To develop this DFF, the project has three major scientific objectives. The first is to locate, collect, and integrate models that will comprise the DFF, the core engine. This engine has different components, each component containing models that originate from the Science Groups with the most expertise on a certain component. The majority of these models will be existing process-based models, but also new data-driven models will be included in the core engine. The models will be integrated in the core engine, meaning that that can communicate and respond to each other. The second objective is to localise and connect data sources in- and outside WUR to provide real farm data to core engine. The third objective is to develop an interface that allows the visualisation of the current nitrogen cycle, and the expected status if actions are or are not taken. This interface will provide actionable knowledge and will allow for simulation exercises.
Publicaties
-
Keynote: Artificial intelligence for digital twins in natural and agricultural sciences
-
Digital Twins for Sustainability
-
Digital Twin helpt boer bij stikstofhuishouding
-
A digital twin of the future farm
-
Using Models and Soil/Plant Observations to Generate Fertilizer Recommendations
-
A digital twin for arable and dairy farming
In: Precision Agriculture '21 - Wageningen Academic Publishers - ISBN: 9789086863631 - p. 919-925. -
Location-specific vs location-agnostic machine learning metamodels for predicting pasture nitrogen response rate
In: Pattern Recognition. ICPR International Workshops and Challenges. - Cham: Springer - ISBN: 9783030687793 - p. 45-54. -
Precision technologies for sustainable agriculture
-
Overview of precision technologies to make agriculture more sustainable, with particular reference to The Netherlands, and possible links with the Dominican Republic.
-
Realtime monitoring, forecasting and management of crop growth