In this edition, we dive into our 7th innovation area, highlighting how Digital Twins are shaping the future of smart, sustainable crop production. You'll read about our ScaleAgData approach, hear from end-users and get updates on recent activities. With the project reaching its halfway point, we're excited to share results from all RILs.
Stay informed via our website & social media & feel free to forward this newsletter or invite colleagues to register!
In this ScaleAgData Newsletter:
7th innovation area: From data assimilation to service development
Recent News items
Upcoming events
Data assimilation and Digital Twins for smart crop production
The ScaleAgData innovation area 'From data assimilation to service development' explores the use of Digital Twin concept in crop production. By leveraging real-time data and advance modeling techniques, Digital Twins can enhance agricultural decision-making, optimizing both productivity and sustainability.
Real-time insights for Smarter Farming
Accurate, up-to-date knowledge of crop status and yield prospects is essential for informed decision-making in precision agriculture. An emerging solution is the use of real-time, high-resolution crop growth models - functioning as Digital Twins of crops - to continuously maintain crop status information and simulate field development.
How Digital Twins turn raw data into actionable insights
Digital Twins developed in ScaleAgData are systems that access relevant data in real time. They have a system model that can be used for monitoring, forecasting, and decision support. A Digital Twin combines real management data, weather data, and time series of remote sensing data into one model. Data for both input and output is harmonized using a well-defined data model to achiever better interoperability. Characteristic to the output is that it can be constrained by biological and physical limits, as crop growth is forecasted using a biophysical crop model.
Development of ScaleAgData Digital Twins aims at automating model initialization and calibration, and eventually providing the modeling as a service. The crop model in a Digital Twin predicts crop growth based on factors such as temperature, soil properties, and water availability. It is beneficial to minimize manual work with the model: some required inputs, such as weather data and soil moisture levels, can be streamed from on-site sensors like weather stations and soil probes, and management data can be taken in as ISOBUS* compliant task data.
* ISOBUS is a standardized international communication protocol that allows different agricultural equipment to communicate with each other through a single common language
"Crop modeling, along with digital twins in general, is becoming an increasingly vital tool in agriculture, particularly in the management of modern farms. The development of these revolutionary tools necessitates extensive integration with various data sources, where the standardization of data plays a critical role."
Mikko Hakojärvi
Dr. Lead agronomist
Mtech Digital Solutions Oy
Fig. 1 Digital Twin Service Development: Crop model as a service.
Accuracy of the models improves when their outputs are adjusted to match real-world crop observations. Data assimilation techniques can refine model predictions by integrating satellite data such as NDVI, LAI, canopy chlorophyll content (CCC), or VITO's CropSAR fAPAR. These techniques align the Digital Twin more closely with its real-life counterpart, improving the Digital Twin's reliability for decision-making.
Currently, the development of the ScaleAgData Digital Twin is being driven by an experiment within the Yield monitoring Research and Innovation Lab (RIL), led by VITO. The main objective of this RIL is to unlock the potential of yield data from harvesters for European-wide yield monitoring. The experiment focuses on providing estimates of winter wheat yield to enhance the quality of yield maps generated by CNH wheat harvesters. Yield sensors installed on harvesters are often prone to inaccuracies, resulting in incomplete or unreliable yield maps. Additionally, errors may arise when integrating data from multiple harvesters or sensors operating in the same field. The Digital Twin model aims to address these challenges by filling in missing yield measurements, correcting outliers, and aligning yield data from different harvesters.
"A digital twin of a field can be a very useful tool accompanying our machines. It would enable us to fill gaps in our data. Even if a farmer only records part of his field, we can provide a complete dataset."
Wout Van Lierop Innovation Engineer
CNH
Over the past months, Luke has worked on calibrating the Digital Twin using data collected by CNH and UGent from winter wheat fields in Wallonia (Belgium) during the 2023 and 2024 growing seasons. The data model of the Digital Twin has also been improved during this use case. In the upcoming season, additional data will be gathered to validate the Digital Twin both within its current application area and beyond, assessing its scalability across different regions and growing conditions.
Fig. 2 LAI derived from Sentinel 2, N application based on the management task and crop yield as dry matter. Data was aggregated to 0.2 ha hexagonal grid (h3) for modelling.
How Digital Twins refine agricultural mapping
Designed as a service, the Digital Twin could eventually be integrated into agricultural service platforms and connected to operational Farm Management Information System (FMIS) software. This integration would allow farmers - including those without access to yield sensor data - to benefit from yield and nitrogen (N) uptake maps. These maps can support decision-making both in-season, for generating task maps for variable rate fertilization, and post-harvest, for evaluating field management practices. By providing these insights, the Digital Twin helps farmers optimize crop production while promoting responsible resource use.
Showcasing ScaleAgData achievements
Demonstration Events
During the first ScaleAgData demonstration event on 10 February 2025, the Yield monitoring RIL partners showcased the Digital Twin alongside other innovative products and services being developed in the RIL to a diverse group of potential users and stakeholders, including farmers, researchers, agricultural service providers, and public authority representatives. The discussions that followed generated highly positive feedback on the usefulness and usability of the proposed services, as well as valuable recommendations for further improvements. This input will help refine our roadmap for the second phase of the ScaleAgData project.
In the second phase of the project, the Digital Twin will also be tuned towards applications for other ScaleAgData RILs, such as the Water Management RIL and the Crop Management RIL.
Beyond farm-level applications, yield maps generated by the Digital Twin could also benefit insurance companies in assessing field damage or evaluating historical performance of insured fields. Additionally, researchers and seed companies may use the data to identify homogeneous fields of trials or seed multiplication. Once fully established, the Digital Twin can be easily adapted to generate yield maps for other crops as well.
The first weeks of February 2025 were all about our Demonstration Events. Five ScaleAgData RILs presented key achievements from the first half of the project during online demonstration events, engaging +75 participants in discussions on challenges and potential solutions. The RIL 'Grasslands' showcased its work in live demonstration events that were held in Spain and Italy.
At the recent GeoAI Camp PRG 2025 in Prague, partner Neuropublic presented how Machine Learning Methods are being used for crop classification in our RIL for Crop Management.
Would you like to learn about upcoming events focused on the latest innovative data technologies for managing agricultural production and monitoring agricultural environments?
VITO is the project coordinator of the ScaleAgData consortium and will also contribute significantly to the 'product and service development', the RI Lab on Yield monitoring as well as the entire communication segment of the project. As a technology provider, VITO will bring data products and innovative solutions to merge sensor data into the data products. As communication lead, VITO will be managing the ScaleAgData website, social media channels as well as these digital newsletters. Feel free to contact us via scaleagdata@vito.be.
------------------------------------- If you don't want to receive our ScaleAgData newsletter, you can unsubscribe: see the 'unsubscribe' link below.
SHARING IS CARING
Feel free to share this newsletter with colleagues or on social media!
