On Thursday, December 12, George Kokkinos, President of NILEAS Producer’s Group, participated as a speaker in an exciting day workshop entitled “Strengthening the agri-food chain through social dialogue” which was organized by the Federation of Industrial Labor Unions in the Serafion Centre of the Municipality of Athens.

The workshop aimed to focus on identifying, disseminating and promoting best practices related to European Social Dialogue and labour relations in the agri-food chain.

During his speech, he had the opportunity to present the AgriDataValue Project. Targeting the new Common Agricultural Policy (CAP) implementation, AgriDataVaue will drive developments in Smart Farming, Precision Farming, Agri-Environmental monitoring and strengthen the Agricultural Digital Transformation at European Level. The project will implement a specialized digital platform for upscaling (real-time) sensor data for EU-wide monitoring of production and agri-environmental conditions. Beyond storage efficiency and semantic interoperability, the multi-technology platform will combine state-of-the-art Big Data/Artificial Intelligence frameworks and Data-Spaces’ Technologies (BDVA/IDSA/GAIA-X) with agricultural knowledge, agri-environment policies and farmers’ engagement campaigns.

NILEAS Producer’s Group is a partner of the AgriDataValue consortium and participates in the Use Case Cluster 3, which aims, in particular, to protect the health and quality of olive orchards by using fewer pesticides and to predict and mitigate the effects of frost. The project started on February 2023 and will last six years. 

Artificial Intelligence (AI) offers numerous possibilities in the agriculture sector. It can assist in decision-making, make future predictions, and provide new opportunities for deploying smart farming techniques. To create these AI models, a substantial amount of data is required. Within the AgriDataValue project, we are developing a public platform where this data can converge with AI models. Farmers will be able to access and provide their data, such as sensor or satellite data, on this platform to build AI models. These models can then be offered to farmers on the platform. We emphasize privacy and data protection in this process.

Pilot Projects Across Europe

While the platform takes shape, data are being collected from several pilot projects to train the AI models. Currently, there are 23 pilots from 9 different countries, covering various topics such as agriculture, horticulture, fruit and vineyards, and livestock.

•              Delphy, for example, will collect data on onions to improve the control of drip irrigation.

•              In Spain, they aim to address climate control in their greenhouses by automatically adjusting window openings based on optimal photosynthesis activity.

•              In Greece, they want to provide advice on spraying against the Mediterranean fruit fly based on smart traps and weather data.

Nitrogen Uptake in Leeks

In Belgium, InAgro, aims to better map the nitrogen uptake in leeks. This will help improve the fertilization recommendations and minimize leaching. InAgro uses drones and satellite images to better estimate crop growth throughout the season. Furthermore, they also collect data from their own Optifarm plot to train AI models.

Learning Network for Precision Agriculture

To implement the AI-generated advice and predictions, smart farming and precision agriculture is needed. Last year, InAgro established a learning network where farmers can share their experiences with precision agriculture. Farmers conducted trials in precision agriculture, choosing the techniques they wanted to test, while technical support was provided as needed. The following months, a second meeting will be organized by InAgro, to discuss the experiences of the first year.

1. Introduction

Remote sensing indicators play a pivotal role in identifying and assessing agricultural droughts due to their unique ability to provide comprehensive and timely information over large geographical areas (Der Sarkissian et al. 2019). These indicators, derived from satellite imagery and sensor data, offer a bird’s-eye view of vegetation health, moisture content, and temperature variations crucial for gauging agricultural conditions. They enable a deeper understanding of vegetation dynamics, allowing for the early detection of stress in crops and vegetation cover. By capturing essential parameters remote sensing indicators facilitate the monitoring of changes in vegetation vigor and response to moisture stress or temperature fluctuations. Their capacity to provide historical, current, and predictive data aids in decision-making processes, guiding agricultural planning, resource allocation, and mitigation strategies to combat the impacts of droughts on crop yield and food security (Al Sayah et al. 2021). Consequently, these indicators contribute significantly to proactive drought management and resilience-building in agricultural systems.

On the other hand, climatic models play a pivotal role in understanding and predicting the potential impacts of climate change on agriculture, hence providing valuable insights that are crucial for sustainable food production. For agriculture, these predictions are indispensable for anticipating shifts in growing seasons, identifying regions at risk of extreme weather events, and assessing changes in water availability. Farmers, policymakers, and researchers can use this information to develop adaptive strategies, optimize crop selection, and implement resilient farming practices. With their capacity to give insights from the future, corresponding decision making, and implementation of proactive and reactive measures equally is ensured.

In this context, the following study gives a brief example on the capacity of remote sensing indicators and climatic geospatial data for monitoring vegetation health and climatic conditions of heatwaves in St Emilion for the summer of 2023.

2. Methodology

2.1. Remote sensing indicators

The Vegetation Health Index (VHI) combines the Vegetation Condition Index (VCI) and the Temperature Condition Index (TCI) to evaluate both vegetation and temperature stress. VHI is a valuable tool for detecting drought (Kogan 1995) and is particularly noted for its effectiveness in assessing extensive areas (Yan et al. 2016).

The formula for computing VHI is as follows (Eq 1):

Different VHI values correspond to various drought classifications as defined by Kogan (1995): > 40 (no drought), 30–40 (mild drought), 20–30 (moderate drought), 10–20 (severe drought), and < 10 (extreme drought).

To calculate VHI, one must initially compute the VCI and TCI indices. VCI quantifies vegetation dynamics on a scale of 0–100 to reflect moisture changes (Bhuiyan, 2008) using this equation (Eq 2):

The NDVI (Normalized Difference Vegetation Index) calculation is derived from Red and NIR bands, indicating vegetation presence based on spectral reflectance (intensity of red color) (Eq 3):

NDVI ranges from − 1 to 1, higher values signifying healthy vegetation and lower values suggesting sparse vegetation (Singh et al. 2016). The extraction of NDVI was accomplished using the “Raster Calculator” tool in ArcGIS (ESRI 2016) through specific equations based on different LANDSAT platforms.

LANDSAT 4, 5, and 7: NDVI = Float ((“Band 4” – “Band 3”))/Float ((“Band 4” – “Band 3”))

LANDSAT 8: NDVI = Float ((“Band 5” – “Band 4”))/ Float ((“Band 5” + “Band 4”))

Once the NDVI rasters were obtained, VCI was calculated for various years using Eq. 2. TCI, on the other hand, represents Temperature Condition Index, capturing vegetation responses to temperature shifts. TCI complements VCI in offering more accurate drought assessments (Sholihah et al. 2016) and is computed using this formula (Eq 4):

where Tc, Tmin, and Tmax are values corresponding to Land Surface Temperatures (LST). TCI values range from 0 to 100, lower values indicating vegetation stress due to temperature or drought elevations (Bhuiyan 2008). TCI’s advantage lies in its applicability throughout any season, unlike VCI, since it relies on Land Surface Temperatures (LST) (Yan et al. 2016). LST, extracted from thermal bands of satellite platforms, particularly LANDSAT, is a crucial element for TCI computation. The thermal sensor of LANDSAT platforms measures top-of-atmosphere radiances, allowing for brightness temperature extraction using Plank’s law (Dash et al. 2002). The steps for LST extraction are outlined in Table 1 according to the LANDSAT user data guide handbook.

Table 1. Calculation of LST from LANDSAT images

Steps	Equations from Avdan and Jovanovska
1 – Conversion of Digital Number (DN) to radiance	𝑳λ=((𝐋𝐌𝐀𝐗𝛌−𝐋𝐌𝐈𝐍𝛌)(𝐐𝐂𝐀𝐋𝐌𝐀𝐗− 𝐐𝐂𝐀𝐋𝐌𝐈𝐍))∗(𝐐𝐂𝐀𝐋−𝐐𝐂𝐀𝐋𝐌𝐈𝐍)+𝐋𝐦𝐢𝐧𝛌
2- Conversion of radiance into satellite temperature	𝑻= 𝐾2𝐿𝑛(𝐾1𝐿𝛌+1) – 273.15
3- Calculation of the proportion of vegetation (Pv)	𝑷𝒗= [(𝑁𝐷𝑉𝐼−𝑁𝐷𝑉𝐼𝑚𝑖𝑛)(𝑁𝐷𝑉𝐼max− 𝑁𝐷𝑉𝐼 min )]2
4- Calculation of the surface emissivity (LSE)	LSE = 0.004 * Pv + 0.986
5- Extraction of LST	𝑳𝑺𝑻= 𝑇1+λ∗(𝑇𝑝)∗𝐿𝑛(𝐿𝑆𝐸)

With Lλ the spectral radiation at the sensor aperture in (watts/m2*ster*μm), QCAL is the quantized calibrated pixel value in DN, LMINλ is the spectral radiation which is scaled to QCALMIN (in watts /m2* ster* μm) , LMAXλ is the spectral radiance which is scaled for QCALMAX (in watts/ m2* ster* μm), QCALMIN is the quantized minimum calibrated pixel value (corresponding to LMINλ) in DN, QCALMAX is the quantized maximum calibrated pixel value (corresponding to LMAXλ ) in DN, T is the effective temperature of the satellite in Kelvin (we added -273.15 as a conversion factor from Kelvin to ˚C), K1 is the constant of band-specific thermal conversion (in watts/m2 * ster * μm), K2 is the thermal band-specific thermal conversion constant (in Kelvin), λ is the wavelength of the emitted radiation, ρ is the h * c / σ (1.438 × 10−2 m ∙ K), h is Planck’s constant (6.626 × 10−34 J ∙ s), σ is Boltzmann’s constant (1.38 × 1 0−23 J/K) and c is the speed of light (2.998 × 108 m/s).

After obtaining the LST index for the entire studied period, TCI was calculated using the “Raster Calculator” tool as specified. Finally, with VCI and TCI maps in hand, VHI computation followed.

2.2. Climatic indicator

In the case of St Emilion, frost and icing conditions are becoming major preoccupations. Understanding the evolution of these phenomena is key for anticipatory planning. Accordingly, MeteoFrance’s DRIAS database was used to obtain the “Number of Frost Days” indicator defined as: The number of days for which the daily minimum temperature of day i is less than or equal to 0. The temporal reference was selected for the reference period (1976-2005) and the year 2050.

Data was obtained in shapefile format, then rasterized to be downscaled to 1 km. By transposing the layer points, the gridded layer will be assimilated to a weather station network. Since the different points holding different climatic values can be considered as “spatial weather stations”. Through a specific kriging technique, spatiotemporal variations were calculated. As most data is transposed into GIS format, a detailed spatiotemporal evolution is obtained. Accordingly, areas of vulnerability are highlighted, hence allowing subsequent prioritized proactive and/or reactive measures. That way, evidence and priority-based budget allocation for orienting interventions can be offered. The reference period and the RCP8.5 scenario were chosen for this example. RCP8.5, the pessimistic climatic pathway was chosen to present the most plausible extreme conditions. By subtracting the predicted horizon and the reference period findings, anomalies were obtained.

3. Results and discussions

3.1. Remote sensing indicators

In this section, the findings of the remote sensing indicators will be detailed. NDVI, TCI, VCI and VHI will be discussed with respect to the obtained values and geographical gradients on the territory.

The NDVI map reveals the presence of healthy and dense vegetation with increasing values. As can be seen, most of Saint Emilion displays high to very high values, hence indicating healthy vegetation. Linear strips can be observed as these correspond to mulches that are often laid between vineyards by farmers as part of vegetative measures.

TCI ranges from 0 to 100 with low values indicating vegetation stress due to temperature/drought increases. As can be seen, most of the territory was under thermal vegetation stress particularly in the central and peripheral regions with heat pockets apparent in the Central-Western parts.

High values of VCI indicate rather a suitable condition of vegetation while lower values indicate stress. As can be seen most of the territory falls under suitable conditions except for parcels located in the North-Central region that display stress.

As can be seen from Figure 4, the vegetation health index of St Emilion showed no drought class in terms of VHI.

3.2. Climatic indicator: Evolution of heatwaves

The number of days for heatwaves is revealed in the following maps (Figures 5, 6 and 7). From Figure 5, one can see that the number of heatwaves ranged between 0 and 15 days with the Western region particularly affected. For St Emilion, the number of heatwaves is around 7 days. The highest risks are mainly concentrated in the Northern and Eastern parts of St Emilion and decreases with the progression South and West. In Figure 6, findings show that the number of frost days will significantly increase at the national scale. For St Emilion, number of frost days in 2050 under RCP8.5 are expected to significantly increase from 28 minimum and 31 days maximum (from 7 days) with the same geographical gradient.

In term of anomalies, generally, a significant increasing trend is observed in throughout the national territory. The same is applicable for St Emilion under the same geographical gradient.

4. Conclusion

In conclusion, the utilization of remote sensing in conjunction with climate indicators emerges as an indispensable approach in the assessment of agricultural drought, revolutionizing the methodology employed in comprehending, monitoring, and responding to environmental adversities. Through the application of remote sensing technologies, access to expansive geographical regions is facilitated, enabling the acquisition of real-time data crucial for informed decision-making in agriculture. This amalgamation not only allows for the early detection and precise monitoring of drought conditions but also facilitates the implementation of proactive measures to alleviate its impact on crops and livelihoods. The deployment of these technologies equips policymakers, farmers, and stakeholders with a robust framework for sustainable agricultural practices, ensuring resilience amidst the evolving patterns of climate change. As society navigates the intricate dynamics of a shifting climate, the fusion of remote sensing and climate indicators assumes a pivotal role, fostering adaptive strategies and fortifying food security for future generations.

References

Al Sayah, M.J., Abdallah, C., Khouri, M., Nedjai, R., Darwich, T., 2021. A framework for climate change assessment in Mediterranean data-sparse watersheds using remote sensing and ARIMA modeling. Theoretical and Applied Climatology. 143, 639–658. https://doi.org/10.1007/s00704-020-03442-7

Der Sarkissian, R., Zaninetti, J.M, Abdallah., C., 2019. The use of geospatial information as support for Disaster Risk Reduction; contextualization to Baalbek-Hermel Governorate/Lebanon, Applied Geography. 111, 102075. https://doi.org/10.1016/j.apgeog.2019.102075

Kogan, FN. 1995. Application of vegetation index and brightness temperature for drought detection. Adv Sp Res 15:91–100

Yan N, Bingfang W, Boken VK, Chang S, Yang L. 2016. A drought monitoring operational system for China using satellite data: design and evaluation. Geomatics Nat Hazards Risk 7:264–277

Bhuiyan C (2008) Desert vegetation during droughts: response and sensitivity. Int Arch Photogramm Remote Sens Spat Inf Sci, XXXVII

Singh RP, Singh N, Singh S, Mukherjee S. 2016 Normalized difference vegetation index (NDVI) based classification to assess the change in land use/land cover (LULC) in Lower Assam, India. Int J AdvRemote Sens GIS 5:1963–1970

ESRI (2016) Raster Calculator [WWW Document]. Spat. Anal. Tools URL  https://desktop.arcgis.com/en/arcmap/10.3/tools/spatialanalyst-toolbox/raster-calculator.htm

Sholihah RI, Trisasongko BH, Shiddiq D, Iman LOS, Kusdaryanto S, Manijo PDR. 2016. Identification of agricultural drought extent based on vegetation health indices of Landsat data: case of Subang and Karawang, Indonesia, in: The 2nd International Symposium on LAPAN-IPB Satellite for Food Security and Environmental Monitoring 2015, LISAT-FSEM 2015. In: Procedia Environmental Sciences, pp 14–20. https://doi.org/10.1016/j.proenv.2016.03.051  

Dash P, Göttsche FM, Olesen FS, Fischer H. 2002. Land surface temperature and emissivity estimation from passive sensor data: theory and practice-current trends. Int J Remote Sens 23:2563–2594

The AgriDataValue project presented by Synelixis at the EC-ESA JOINT EARTH SYSTEM SCIENCE INITIATIVE workshop, organized by ESA and the DG-RTD of EC. The event was held on the 22^nd -24^th of NOVEMBER 2023 in ESA-ESRIN, FRASCATI, ITALY. This initiative is expected to provide a significant scientific contribution to realize the vision of the EU Green Deal. AgriDataValue targets high-level EU impact goals, including call’s expected outcomes, de stination impacts, and the Key Strategic Orientation of “Innovative governance, environmental observations and digital solutions in support of the Green Deal”. The project is designed and structured to significantly contribute to the overall EU agricultural development and the objectives set by the Green Deal, the EU Climate Change policy and new CAP.  

Drones and multispectral cameras are a powerful combination for enabling timely and informed decisions on crop management. Scalability is a key advantage in this context, since drones can be used to fly over large fields quickly and efficiently, collecting multispectral data from a variety of angles, corresponding to images of crops in multiple spectral bands. This data can then be processed to create detailed maps of crop health and variability.

The AgriDataValue project will work on the so-called “Drones Data Toolbox” that will enable the ingestion of aerial imaging captured by multispectral cameras on drones to the emerging agri-data spaces. The project will utilize drones equipped with both visual and multi-spectral cameras to collect in-situ observations of the crop that will complement the remote sensing, satellite-based earth observations. The images that will be captured by the drones will be appropriately geo-tagged and semantically enriched to be integrated in the AgriDataValue data ecosystem and be available to feed data processing pipelines using advanced AI techniques.

A key enabling application stemming from the processing of the in-situ aerial imaging and the satellite-based data is the calculation of vegetation indices (VIs) such as the Normalized Difference Red Edge (NDRE) and the Normalized Difference Vegetation Index (NDVI). VIs are mathematical transformations of multispectral imagery that are used to quantify the presence and condition of vegetation. The indicators can be easily interpreted by the farmers to detect subtle changes in crop health, such as nutrient deficiencies, water stress, and pest infestations. In the context of AgriDataValue project, we will test the efficacy of AI-enabled VIs prediction models, adhering to data space principles for trustworthy data sharing, to estimate various crop health parameters. In addition, we will test the applicability of these Vis prediction models in real-world scenarios and the acceptance from farmers, paving the way for the uptake of drones technologies and multispectral cameras in the agricultural sector.

After almost 11 months since the project’s kick off, the partners have gathered to address project related issues in a two-day hybrid meeting. The third plenary meeting hosted by SIXENSE, in Paris, France on November 23rd and 24th of 2023. A fruitful discussion took place among the partners of the consortium. During the two-day meeting, the consortium reviewed the progress on all work packages and had the chance to address development issues. The partners presented the results achieved so far and the next steps towards the successful delivery of the AgriDataValue project.

Introduction

In modern farming, sustainability is a big concern. Traditional farming methods have sometimes caused problems like soil damage and harm to the environment. To address these issues, farmers have started using new ways of farming that are kinder to the land. Two of these methods are minimum tillage and strip-till, and they’re becoming more popular in conventional farming. They both focus on being gentle to the soil, saving resources, and making farming more sustainable. In this article, we’ll look at the differences and similarities between minimum tillage and strip-till methods. We’ll talk about how they help the environment, affect crop growth, what kind of equipment they need, and how they fit into the future of farming. Let’s dive into these new farming techniques and see how they might change the way we farm.

Minimum Tillage vs. Strip-Till: A Comparison

Both minimum tillage and strip-till are practices aimed at reducing soil disturbance and promoting sustainable agriculture (Table 1):

Discussion

In the realm of modern agriculture, the pursuit of sustainability has led to the emergence of innovative farming practices, namely minimum tillage and strip-till. These methods, driven by the desire to reduce soil disruption, conserve resources, and promote environmental well-being, have demonstrated their worth in the world of conventional farming.

Minimum tillage, with its gentler approach to soil management, stands as a valuable ally in the fight against soil erosion, soil degradation, and greenhouse gas emissions. By leaving crop residues on the field and tilling the soil less deeply, minimum tillage helps preserve soil structure and health while contributing to a more sustainable agricultural future.

Strip-till, on the other hand, offers precision in soil preparation. By creating well-defined tilled strips, it not only minimizes soil disturbance but also provides a favorable environment for crops to thrive. Improved weed management and the potential for increased crop yields underscore its role in sustainable farming practices.

Within the scope of the AgriDataValue project, the incorporation of advanced technologies such as weather stations and IoT sensors marks a significant leap forward. These devices will be installed in the field to collect comprehensive data on weather patterns and soil conditions, enabling precise adjustments to farming practices. The insights gained from this real-time data can lead to more informed decision-making, optimized resource use, and further advancements in sustainable agriculture.

As we look toward the future, it becomes evident that these practices have a vital role to play in the quest for sustainable agriculture. Here are some considerations for the road ahead (Figure 1):

1. Technology and Innovation: Continuous advancements in farming technology and equipment will likely enhance the efficiency and accessibility of minimum tillage and strip-till methods. Integrating data-driven solutions and automation can further optimize these practices.

2. Education and Training: Providing farmers with the knowledge and training required to implement minimum tillage and strip-till effectively is crucial. Outreach programs and support from agricultural institutions can facilitate the adoption of these practices.

3. Tailoring to Local Conditions: Different regions and crop types may benefit differently from minimum tillage and strip-till. Future strategies should focus on tailoring these practices to local conditions and crop needs.

4. Monitoring and Research: Ongoing research and monitoring efforts should assess the long-term impacts of these methods on soil health, crop productivity, and the environment. This knowledge will help refine best practices.

5. Policy Support: Government policies and incentives that encourage sustainable farming practices, including minimum tillage and strip-till, can play a pivotal role in their widespread adoption.

Conclusion

In conclusion, minimum tillage and strip-till farming methods offer promising avenues for more sustainable and environmentally friendly agriculture. The integration of IoT sensors, such as weather stations, into these practices enhances their efficacy by providing precise, real-time data. This data-driven approach allows for the optimization of resources and informed decision-making, which can lead to improved crop yields, reduced environmental impact, and cost savings. Embracing these practices, alongside continued innovation and support, holds the potential to reshape the future of farming for the better, ensuring that we can meet the needs of today without compromising the needs of tomorrow. The AgriDataValue Project exemplifies this synergy between traditional farming techniques and modern technology, setting a benchmark for the future of sustainable agriculture.

References

1. Reicosky, D.C., and R.R. Allmaras. “Minimum Tillage Effects on Soil Carbon and Aggregate Stability in the Northern Great Plains.” Soil Science Society of America Journal, 2002.
2. Blanco-Canqui, Humberto, and Richard B. Ferguson. “Strip tillage and nitrogen rate effects on soil carbon and nitrogen in irrigated continuous corn.” Soil Science Society of America Journal, 2013.
3. Kaur, G., et al. “Environmental and economic benefits of no-tillage and strip-tillage practices: a review.” Renewable Agriculture and Food Systems, 2018.
4. Wilhelm, W.W., et al. “Corn and soybean yield response to crop rotation and tillage.” Agronomy Journal, 2004.
5. USDA Natural Resources Conservation Service. “Conservation Tillage.” (chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://www.ers.usda.gov/webdocs/publications/90201/eib-197.pdf)
6. Sustainable Agriculture Research & Education (SARE). “Strip Tillage and No-Till for Vegetables.”

The AgriDataValue technological tools, mechanisms, and Lean Multi-Actor Approach (LMAA) will be fully tested and validated during the AgriDataValue project lifetime through several Use Cases (UC) in 23 pilots in 9 countries, representing more than 181,000ha with 25 types of crops that span from southwest to northeast Europe, outdoor and greenhouse crops, organic and non-organic production, and more than 2,000 animals of 5 types.  In addition, more than 4,200 farmers will provide insights and more than 89,000 will be directly informed.

The pilots will also be used to collect sensor data and feedback from the involved end-users, monitor and adapt the pilots over the project lifetime. The activity will continue though out the project’s lifetime (and at least 3 years after). The captured datasets will be used for the ML training and evaluation the evolving impact in each use case. In this phase mature AgriDataValue tools and solutions will be delivered evaluating the impact and collect feedback.

The Use Cases (UC) of the project have been finalized and grouped in clusters, addressing similar domains in different regions, crops, cultural, societal and farming contexts. Since the beginning of the AgriDataValue project, two new clusters have been added. The first one is ‘’Cluster number 6 – CAP Realization’’, and the second one is ‘’Cluster number 7 – Climate Monitoring’’. Below, a short description of each cluster is provided.

UC CLUSTER #1 – Arable Crops

Optimize the quality and quantity of crop production and increase environmental sustainability. Reduce the wasted irrigation water, fertilizers, pesticides, and energy. Involve different technologies and data platforms such as IoT sensors, edge cloud, drones/satellite visual/multispectral images and AI models.

UC CLUSTER #2 – Vegetables

Precision irrigation/ fertilization, harvest /diseases prediction for vegetables/arable crop increased production. Involve IoT sensors, edge cloud, radiation/clorofile/pH metering, multiple data platforms with geotagged photos alone with drones/satellite multispectral imagery.

UC CLUSTER #3 – Trees & Vineyard

Protect the health and quality of fruit trees and vineyards crop. Increase quality and quantity, avoid diseases with less pesticides, foresee and mitigate frost. Involve IoT weather/soil sensors, edge cloud, diverse geotagged photos’ datasets, drones/satellite multispectral imagery.

UC CLUSTER #4 – Livestock

Use edge cloud and real-time IoT sensor data (e.g. neck collar, feeders, emission sensors) together with GPS location data to monitor the cattle/pig health, activity, feeding and calving, proactively control milk and meat quality, reduce the greenhouse gas emissions and nitrogen deposition.

UC CLUSTER #5 – Cross Sector

Validate cross domain use cases (fruit, vineyards, livestock, milk, oil, biogas, manure, energy) and address both supply and demand sides of the supply chain, including interoperability and traceability of platforms, electricity production and waste management.

UC CLUSTER #6 – CAP Realization

Focuses on CAP realization tools/applications and aims to assess and manage risk through modern ML with the aim of reducing the use of pesticides, fertilisers and antibiotics. Promote modern crop monitoring technologies. Benchmarking eco-scheme monitoring tools to support the new CAP towards fair income, land use and environmental protection.

UC CLUSTER #7 – Climate Monitoring

Climate monitoring plays a vital role in agriculture by providing valuable information about weather patterns, climate variability, and climate change impacts on crop growth, pests, diseases, and water availability. It involves collecting data from weather stations, satellites, remote sensing technologies, and climate models.

AgriDataValue presents a comprehensive and innovative approach to revolutionize the agricultural sector by leveraging advanced technologies and data-driven solutions. Throughout the project, significant advancements will be made in several key areas, including data integration and interoperability, DSSs, precision agriculture, remote sensing, IoT, and blockchain technology.

Overall, the AgriDataValue project signifies a transformative shift in the agricultural sector, where data-driven approaches, advanced technologies, and collaborative frameworks converge to address the challenges and unlock the opportunities in modern agriculture. By integrating diverse datasets, developing advanced decision support systems, promoting precision agriculture and remote sensing, and exploring blockchain technology, the project paves the way for a more sustainable, efficient, and resilient agricultural ecosystem. The outcomes of the project have the potential to drive innovation, optimize resource utilization, mitigate risks, and ultimately contribute to global food security and environmental stewardship.

At ILVO the enteric emissions from dairy cows are being monitored to gather data that will be used to develop AI models within the AgriDataValue project. Currently, enteric emissions are already being monitored at the ILVO dairy farm using GreenFeeds (C-Lock Inc., USA). In these devices cows are being fed small amounts of concentrate while at the same time the concentration of methane and carbon dioxide in their breath and eructation are being measured. Cow measurements are combined into daily emission values expressed as grams CH4 per day which provide a good idea of enteric emissions from cows. As these emissions are influenced by many other factors, general cow data such as milk production, lactation stage etc. will also be made available for further analysis.

Apart from these individual measurements, SynField sensors will be used to gather more emission data from the barn environment in the future. Using the AgriDataValue platform, these data will be made available for the development of AI models to create more added value.

As one of the pilots in the AgriDataValue project, ILVO intends to further increase the range and quality of emission data and make them available to third parties in the project in order to work towards a reduction of greenhouse gasses in the dairy sector.

In large scale agricultural research projects such as AgriDataValue, where vast amounts of sensitive data are generated and analyzed, having a reliable and secure storage solution is required. MinIO, an open-source object storage server, emerges as a significant tool in this scenario, offering a scalable, high-performance, and secure storage platform tailored to the unique needs of agricultural innovations.

The use case partners involved in AgridataValue generate large datasets, ranging from satellite imagery to real-time IoT sensor data. MinIO’s scalable architecture allows effortless expansion, ensuring that the storage infrastructure can grow seamlessly with the increasing volume of agricultural data. Whether it is analytics for crops management or climate monitoring, MinIO’s scalability makes it a suitable choice for handling diverse data types and massive datasets.

Data security is always necessary when dealing with sensitive agricultural information. MinIO offers robust encryption mechanisms, both in transit and at rest. This means data is encrypted during transmission, safeguarding it against interception, and remains encrypted when stored, ensuring unauthorized access is impossible. This level of security instills confidence among farmers and project stakeholders, enhancing the overall trust in the technology.

Data integrity must be ensured in our project, where decisions are often data driven. MinIO’s advanced features, such as checksumming and bitrot protection, guarantee that the stored data remains intact and uncorrupted. With MinIO, AgriDataValue can rely on the accuracy and reliability of the data, enabling precise analysis and informed decision-making.

Collaboration among stakeholders is a cornerstone of successful European projects. MinIO’s support for various APIs and compatibility with standard protocols ensures seamless integration with other technologies and tools. Whether it is sharing data insights with researchers or policymakers, MinIO enables secure and controlled data collaboration, enhancing the project’s collaborative potential.

Agricultural innovation heavily relies on advanced technologies like AI and machine learning. MinIO’s compatibility with AI frameworks and analytical tools simplifies the integration process. The stored data can be seamlessly accessed and processed by AI models, enabling the project to derive meaningful insights and optimize agricultural practices effectively.

MinIO, with its scalability, security features, data integrity assurance, and seamless integration capabilities, stands as a robust solution for securing the vast and diverse datasets generated by modern agricultural projects. By choosing MinIO as the storage backbone, the AgriDataValue project not only ensures the confidentiality and integrity of agricultural data but also lays a solid foundation for future innovations. With MinIO tools in place, our project can focus on what truly matters: leveraging data-driven insights to revolutionize farming practices and secure a sustainable future for agriculture.