A recent academic milestone in Swedish agriculture could have broader implications for sectors beyond livestock farming — including industrial baking. On June 2, Lantmännen, one of northern Europe's largest agricultural cooperatives, announced that Johanna Forss has been awarded its annual From Field to Fork scholarship for her master's thesis on innovative sensor technology in ley cultivation [1].

While the research focuses on optimising forage harvest for livestock, the underlying technologies and sustainability benefits may also serve the long-term interests of the baking industry. This development is worth noting for stakeholders across the grain-based value chain, particularly as the industry grapples with evolving definitions of wheat quality and the integration of artificial intelligence in food production.

From Ley Fields to Data-Driven Decisions

Johanna Forss, a master's student at the Swedish University of Agricultural Sciences (SLU), investigated the use of the Arable Mark 3 — a commercial field spectrometer — to measure nutrient levels in ley directly in the field. Ley, primarily used for livestock forage, is Sweden's most cultivated crop by area [1].

Her study demonstrated that with sensor technology, farmers could pinpoint the optimal harvest time based on real-time data rather than estimations, thereby improving both forage quality and yield [1].

While this directly benefits livestock producers, there are indirect advantages for arable farming and, by extension, industrial baking.

The Link Between Forage Innovation and Grain Supply

At first glance, forage crop optimization may seem unrelated to the concerns of flour mills and bakery processors. However, ley plays a crucial role in crop rotation systems. It improves soil structure, fertility and biodiversity, which can enhance subsequent cereal yields — including wheat, rye, and oats — that are fundamental to baking [2].

Sustainable forage practices reduce pressure on grain markets used for animal feed. According to the European Commission, nearly 60% of EU cereals are used in animal feed [3]. Innovations that increase the efficiency of forage crops could ease competition for grains, potentially stabilizing prices and improving availability for food-grade applications.

Technology-Driven Agriculture: An Opportunity for the Baking Sector

The adoption of sensor-based technologies in agriculture aligns with broader digitalisation trends across food production. The Arable Mark 3 device used in Forss's research is part of a growing suite of agritech tools designed to capture hyperlocal field data — moisture, nutrient levels, weather conditions — with precision. These tools offer opportunities for more predictive and transparent supply chains [4].

For industrial bakers with vertically integrated supply models or close supplier relationships, there is clear incentive to support data-driven agriculture. Technologies like these could help ensure consistent grain quality and facilitate traceability — critical in meeting consumer and regulatory expectations on sustainability and transparency.

Redefining Wheat Quality Through AI and Advanced Analytics

The move toward data-driven agriculture extends beyond field sensors to sophisticated quality assessment systems. Recent research by INRAE (French National Institute for Agriculture, Food and Environment)Previously published in Baking Europe Summer 23 demonstrates how artificial intelligence and machine learning are revolutionizing wheat quality evaluation for the baking industry [5].

Traditional wheat quality assessment has long relied on standardized tests like the French baguette baking method, complemented by analytical measurements of protein content and technological properties such as water absorption capacity. However, as researchers Kamal Kansou, Luc Saulnier, and Guy Della Valle note,

"most technical decisions made in the context of the baking industry are mainly driven by tacit know-how of the operators or by empirical assessments," despite the continuous data flow from production line sensors [5].

The EVAGRAIN project, launched in 2020, addresses this gap by developing a Decision Support System that uses machine learning to assess wheat quality from routine measurements. The system analyzes data from approximately 150 wheat grains across different locations and years, combined with 20 years of French wheat production data, to predict baking performance more accurately than traditional methods [5].

From Field Sensors to Dough Rheology: A Complete Data Picture

The integration of field sensor technology like that studied by Forss with advanced wheat quality assessment creates opportunities for unprecedented supply chain optimization. While field sensors capture real-time growing conditions, AI-driven quality systems can predict how those conditions translate into flour performance.

Recent INRAE research has revealed fascinating connections between mixing power curves and dough extensional properties, using techniques like time-domain nuclear magnetic resonance (TD-NMR) to monitor water distribution during mixing. This research shows how data science can decode the complex relationships between flour characteristics, dough behavior, and final product quality [5].

Such insights are particularly valuable as the industry faces climate change pressures and evolving consumer demands. The ability to predict wheat quality from both field conditions and laboratory measurements could help bakers adapt more quickly to variable raw material quality while maintaining consistent product specifications.

A Strategic Fit for a Sustainable Future

Lantmännen's scholarship committee noted that the thesis is both

"technically insightful and practically relevant," highlighting how "digital tools can support decision-making in ley cultivation, with the potential to improve quality, sustainability, and profitability" [1].

These same principles apply to industrial baking, where the integration of sensor technology, AI-driven quality assessment, and data analytics supports environmental, social, and governance (ESG) objectives.

The INRAE research emphasises that such systems can contribute to "the required flexibility level needed to adapt to changing raw material quality and conditions" [5].

In a landscape where climate resilience and resource optimization are key, innovations spanning from field sensors to AI-powered quality prediction have value across the entire food chain. The combination of precision agriculture and intelligent quality assessment represents a significant step toward more sustainable and efficient food production systems.

Conclusion

While Johanna Forss's thesis centers on forage crop optimisation, it exemplifies a broader technological transformation that extends to wheat quality assessment and baking applications. The convergence of field sensor technology with AI-driven quality prediction systems offers industrial bakers unprecedented opportunities to optimise their supply chains and adapt to changing conditions.

For Europe's industrial bakers, supporting such advancements is not only aligned with long-term resilience goals but also represents a strategic investment in the future of sustainable, data-driven food production. As the INRAE researchers conclude, the dissemination of cereal science knowledge through advanced technologies has never been more feasible — or more necessary.

References

[1] Lantmännen. (2025). From Field to Fork Scholarship awarded to thesis on innovative sensor technology. Press release, June 2, 2025.

[2] Swedish Board of Agriculture (Jordbruksverket). (2023). Crop Production Statistics: Arable Land Use in Sweden.

[3] European Commission. (2024). EU Cereals Balance Sheet – Annual Data.

[4] Arable Labs. (2024). Arable Mark 3: Field-Scale Weather & Crop Monitoring Platform. Retrieved from: www.arable.com

[5] Baking Europe Summer 23 /Kansou, K., Saulnier, L., Della Valle, G. (2025). Mobilising Artificial Intelligence and food science to better define wheat quality. INRAE – UR12768 BIA, Nantes, France.