An overview of the DEMETER H2020 project which aims to lead the digital transformation of Europe’s agri-food sector through the rapid adoption of advanced IoT technologies, data science and smart farming, ensuring its long-term viability and sustainability.
2. DEMETER OBJECTIVES
Objective 1:
Analyse, adopt, enhance existing (and if necessary introduce new) Information Models in the agri-food sector
easing data sharing and interoperability across multiple Internet of Things (IOT) and Farming Management
Information Systems (FMIS) and associated technologies. Use the information models to create a basis for
trusted sharing / exposure of data between farmers.
Objective 2:
Build knowledge exchange mechanisms, delivering an Interoperability Space for the agri-food domain, presenting
technologies and data from different vendors, ensuring their interoperability, and using (and enhancing) a core
set of open standards (adopted across all agri-food deployments thereby) coupled with carefully-planned
security and privacy protection mechanisms (also addressing business confidentiality).
Objective 3:
Empower the farmer, as a prosumer, to gain control in the data-food-chain by identifying and demonstrating a
series of new IoT-based, data-driven, business models for profit, collaboration and co-production for farmers and
across the value chain, leading to disruptive new value creation models.
3. DEMETER OBJECTIVES CONT.
Objective 4:
Establish a benchmarking mechanism for agriculture solutions and business, targeting end-goals in terms of
productivity and sustainability performance of farms, services, technologies, and practices based on a set of key
performance indicators that are relevant to the farming community.
Objective 5:
Reverse the relationship with suppliers, through an innovative model in which suppliers are responsible for
ensuring that a final solution is optimal to the farmer’s existing context and expressed needs.
Objective 6:
Demonstrate the impact of digital innovations across a variety of sectors and at European level.
4. DEMETER WORK PACKAGES
Work Package: 1
Project Coordination
Task 1.1 - Administrative Coordination
Task 1.2 - Technical Coordination and Integration Management
Task 1.3 - Agricultural Coordination
Task 1.4 - Management of IPR, Ethics and Legal issues
Task 1.5 - Quality Assurance and Innovation Management
5. DEMETER WORK PACKAGES
Work Package: 2
Data and Knowledge
Task 2.1: Common Data Models and semantic interoperability
Task 2.2: Data Management and Integration
Task 2.3: Targeted data fusion, analytics and knowledge extraction
Task 2.4: Data Protection, Privacy, Traceability and Governance Management
6. DEMETER WORK PACKAGES
Work Package: 3
Technology Integration
Task 3.1 DEMETER Reference Architecture
Task 3.2 Technical Interoperability and Service Provisioning
Task 3.3 Application Service Integration and Deployment Tools
Task 3.4 Connectivity and Security Framework
Task 3.5 DEMETER Hub
Task 3.6 DEMETER Agriculture Interoperability Space
7. DEMETER WORK PACKAGES
Work Package: 4
Performance Indicator Monitoring, Benchmarking and Decision Support
Task 4.1. AI-based Decision Making
Task 4.2. Benchmarking on performance of farms, services, technologies and
practices
Task 4.3. Adaptive Visualisations for Dashboards
Task 4.4. Decision Support Enablers and Advisory Support Tools
Task 4.5. Stakeholder Open Collaboration Space Implementation
8. DEMETER WORK PACKAGES
Work Package: 5
Pilot Management
Task 5.1: Stakeholder requirements, pilot design, specification and planning
Task 5.2: Pilot testbed management, pilot applications, system extensions and
deployment at pilot sites
Task 5.3: Pilot roll-out and execution management
Task 5.4: Pilot assessment, evaluation and stakeholder validation
Task 5.5: Cross-Pilot Coordination, Fertilization and Optimization
9. DEMETER WORK PACKAGES
Work Package: 6
Business Modelling, Innovation Management , Exploitation and Standardisation
Task 6.1: Exploitation, market, business strategies and activities
Task 6.2: Regulatory and policy framework, Radar, impact and
recommendations
Task 6.3: Branding, dissemination, communication strategy & planning
Task 6.4: Global outreach
Task 6.5: Standardisation Framework
10. DEMETER WORK PACKAGES
Work Package: 7
Multi-actor Ecosystem Development
Task 7.1. Governance of Multi-actor approach activities
Task 7.2. Multi-actor approach Animation
Task 7.3. Co-creation and development open calls
Task 7.4. Monitoring the effectiveness of the multi-actor approach
11. PILOT CLUSTER 1 OVERVIEW
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
Pilot Cluster: 1
Sector: Arable Crops
Focus: Water & Energy Management
Description:
The cluster will focus on an efficient integrated management of water and energy, from sources to end users to
optimise both the quality and quantity of the resources in irrigation systems applied to irrigated and arable crops. The
pilots will involve different technologies as IoT Sensors networks or satellite imagery and advanced farming platforms.
1. Water savings in irrigated crops
2. Smart energy management in irrigated & arable crops
3. Optimal Quality Rice Irrigation
4. IoT Corn Management & Decision Support Platform
12. Description:
Pilot aims to increase production saving water and improving the automation of the irrigation zones through
interoperable remote-control systems and robust management systems adapted to the conditions required by the
irrigated agriculture.
Problem:
Most of the national irrigation systems have remote control systems that are closed solutions not sharing software or
hardware elements, which limits their possibilities of modification or expansion. Neither they are interoperable as the
information they report can not be consulted by other non proprietary applications.
Solution:
Develop a Standard Model of Water Management applied to irrigation in order to standardize and model the
information that is exchanged between the water management and control systems. The implementation of
standardized and interoperable elements will facilitate the exploitation and maintenance of irrigation systems
achieving greater efficiencies in the water savings.
PILOT 1.1 WATER SAVINGS IN IRRIGATED CROPS
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
13. Description:
Pilot aims to modernize irrigation systems and design efficient networks from the energy point of view, evaluating and
selecting the optimal contracting of the electricity supply as well as implementing alternative renewable and clean
energies that reduce the price of consumption.
Problems:
The modernization of irrigation systems has been accompanied by a greater demand for energy. The figures that show
this fact, show the need to have more efficient networks from the energy point of view. It is necessary an optimal
calculation of the energetic efficiency, saving energy in electrical consumption based on the variable of the electric
power market price that changes constantly, and the distribution of water by the different pumping stations of the
hydraulic system.
Solution:
Once the consumption of kilowatts has been adjusted, the increase in profitability will be achieved by evaluating
and selecting the optimal contracting of the electricity supply as well as implementing alternative energy sources,
renewable and clean energy (photovoltaic, wind, mini-hydraulic) that reduce the price of consumption and are in
line with environmental policies of the European Union.
PILOT 1.2 SMART ENERGY MANAGEMENT IN IRRIGATED & ARABLE CROPS
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
14. Description:
The Greek pilot aims to establish a holistic approach for a sustainable management of the irrigation in rice and
maize, crops which are often included in the crop rotation systems in the rice-growing regions of EU. And since
irrigation is tightly connected to fertilisation, a prototype service for optimal spatial fertilisation in rice and maize
will be tested and optimised for variable rate applications, according to the real nutrient requirements of the crops.
Problem:
Rice and maize require considerable amounts of irrigation water. Particularly for rice, every hectare requires almost
12,000 m3 of water per cultivation period and, therefore, it is considered as a high energy demanding crop, including
the fertilization impacts. Furthermore, besides the considerable big environmental footprint, both crops have high
cultivation costs, whereas farmers are struggling to cope with the low profits.
Solution:
An in-field, real-time and automatic system using height and salinity sensors will be exploited, which will manage
rice irrigation by controlling electric water input/output valves in small scale pilots or by the provision of
information to the end-users in big scale pilots. Moreover, water- and nitrogen-stressed fields will be identified
via UAV imagery for assisting end-users’ in the decision making. Validation will be performed through field
measurements, micro-satellite high resolution imagery, as well as UAV-collected multispectral data.
PILOT 1.3 SMART IRRIGATION SERVICE IN RICE & MAIZE CULTIVATION
(GREECE)
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
15. Description:
This pilot aims to implement an IoT Corn Decision Support System Platform for farmers to improve greenhouse gas
emissions and poor water quality that drive business risks in corn production. Objective to be addressed:
• Platform integration
• Efficient collaboration and information exchange in a short local chain
• Decision support for corn farm management
Problem:
Inefficient fertilizer practices and the demand for irrigated water contribute to environmental impacts, such as
greenhouse gas emissions and poor water quality that drive business risks in corn production. Scouting and monitoring
of fields is required in order to identify any problems early. Identify stand establishment issues, nitrogen shortages,
insect buildups, disease outbreaks, weed problems and moisture stress effects
Solution:
Implementation of an IoT Corn Decision Support System Platform on more than 10 farms specialized in field crops,
members to the APPR.
APPR will introduce DEMETER results to the Romanian corn producers and to their counterparts from Europe. The
direct collaboration between the IT company SIVECO and the end-users (APPR) will increase the visibility of DEMETER
by providing access to project knowledge to stakeholders, in 2 direction, both agriculture and ICT related technologies.
PILOT 1.4 IOT CORN MANAGEMENT & DECISION SUPPORT PLATFORM
Partners:
APPR (Romania) | SIVECO (Romania)
16. PILOT CLUSTER 2 OVERVIEW
Partners:
John Deere (Germany) | LESPROJEKT (Czechia) | AVINET (Norway) | WODR (Poland) | PSNC (Poland) | m2Xpert (Germany) | Fraunhofer (Germany)
Pilot Cluster: 2
Sector: Arable Crops
Focus: Agricultural Machinery, Precision Farming
Description:
The cluster will focus on arable crops and specifically on the usage of agricultural machinery and the establishment of
precision farming. The pilots will concentrate on monitoring arable crops by using sensors and their documentation,
while decision support systems will be developed for live support of agricultural processes in a secure and trusted
way.
1. In-Service Condition Monitoring of Agricultural Machinery
2. Automated documentation of arable crop farming processes
3. (Farming)Data Brokerage Service and Decision Support System for Farm
Management
4. Benchmarking at Farm Level Decision Support System
17. Description:
This pilot aims at demonstrating the potential application of onboard after treatment (AT) sensors for in-service
monitoring, as well as testing the legal applicability of existing sensors as alternative to PEMS (Portable Emission
Measurement Systems) while considering aspects of data management, privacy and integrity.
Problem:
With Stage V, gaseous pollutant emissions have to be monitored and documented from 2019 onwards for combustion
engines with a separate device. The actual solution is really expensive and not practicable for a large scale regulation
as on board monitoring. In addition, neither appropriate sensors nor appropriate real-time analytics are available to
fulfill technical and legislative requirements.
Solution:
Using e.g., NOx-conversion, exhaust temperatures, and further not yet fully explored additional or alternative
data from the CAN-Bus, algorithmically ensuring high quality of continuous data streams, and analyzing the data
in real-time by making use of the most appropriate algorithms and technologies, will allow monitoring,
documentation, and using the analysis results for further actions. The approach will be evaluated by monitoring
real driving emissions and diesel engine conditions.
PILOT 2.1 In-Service Condition Monitoring of Agricultural Machinery
Partners:
John Deere (Germany) | m2Xpert (Germany) | Fraunhofer (Germany)
18. Description:
This pilot will develop a DSS (Decision support System) for live support of agricultural processes and the connected
supply chains based on autonomous documentation. This will include capturing high precision data, merging with
data from other farms/ machines, and deriving required documentation parameters via data analytics, and
knowledge management techniques.
Problem:
Agriculture requires an ever-increasing amount of documentation. Often the documentation is made after the activity
has taken place. This is often inaccurate. In addition, the documentation is carried out by different persons in different
processes. Here the effort is high to compile all reports.
Solution:
Automated documentation is to replace manual documentation. This is based on intelligently linked sensor data,
from machines and external sensors such as satellite data (e.g. sentinel) or data from weather stations. This
information is intelligently linked and interpreted in the respective context such as location, time, activity or crop.
PILOT 2.2 Automated documentation of arable crop farming processes
Partners:
John Deere (Germany) | m2Xpert (Germany) | Fraunhofer (Germany)
19. Description:
This pilot will establish a trustworthy and compliant data market for agricultural enterprise data that sits between
the owners and operators of agricultural data Clouds and the farmer, and that will include both a technical
platform and advisory services that will ensure easy adoption of data and technology by farmers.
Problem:
There is already existing a large number of suppliers for farming related data. It varies between data from machinery,
satellite data, meteorological data, Land parcel information systems, water bodies data, erosion data soil data, etc.
This data are offered by different systems, different data models and different API´s. For farmers it is important to
have access to the complete data, but they are not able to provide integration of this data.
Solution:
Farm data brokerage establishes a trust-based and compliant data market for agricultural enterprise data that sits
between the owners and operators of agricultural data Clouds and the farmer. This data market will consist of
both a technical platform and advisory services that will ensure easy adoption of data and technology by farmers
PILOT 2.3 (Farming) Data Brokerage Service and Decision Support
System for Farm Management
Partners:
LESPROJEKT (Czechia) | AVINET (Norway))
20. Description:
This pilot aims at developing services to support the benchmarking on the productivity and sustainability
performance of the farms, leveraging and extending existing DSS. This will involve monitoring different conditions
and parameters affecting such indicators, collecting the data and integrating it in a unified layer accessible by the
DSS.
Problem:
There are several data sets available for agriculture, but many of them are rarely used in practice. Farmers cannot
manage available information and often have big problems with their interpretation. Usually, data is coming from
many different systems and sources using different models, making it difficult to access and use it in an integrated
manner. Also many times farmers do not know what is the situation of their farms compared to the environment, and
they must devote a lot of time learning and using ICT systems instead of doing field work where is more needed.
Solution:
Provision of a simple to use benchmarking system that would allow the use of ICT and IoT technologies in
practical management and decision support, with focus on data integration. This will be done by adopting Linked
Data as a federated layer, complemented with security mechanisms, and implementing computational
benchmarking models with interfaces that reuse/extend existing decision support and farm management systems
(as an added value feature).
PILOT 2.4 Benchmarking at Farm Level Decision Support System
Partners:
WODR (Poland) | PSNC (Poland) | 10 farms
21. PILOT CLUSTER 3 OVERVIEW
Pilot Cluster: 3
Sector: Fruit & Vegetables
Focus: Health and high-quality crops
Description:
The cluster will focus on several fruit and vegetable crops in different European countries, supporting farmers in
protecting the health and quality of their production. Pilots will integrate various existing and emerging technologies:
farming digital platform, IoT sensor networks, model and Decision Support Systems, remote sensing data, advanced
data analysis tools.
1. Decision Support System to support olive growers
2. Precision Farming for Mediterranean Woody Crops
3. Pest Management Control on Fruit Fly
4. Open platform for improved crop monitoring in potato farms
Partners:
AGRICOLUS (Italy) | INESC(Portugal) | TRAGSA (Spain) | VITO (Belgium) | ENG(Italy) | DNET(Serbia) | AVR(Belgium) | INIAV ( Portugal) | UBIWHERE(Portugal) | FENADEGAS(Portugal)
22. Description:
The aim of this pilot is to develop a DSS for olive growers, advisers and food processors to address common issues
associated with olive tree growing and olive oil production, including integrated pest management, sustainable
fertilizer use and sagacious irrigation management.
Problem:
Because of uncertainties and risks associated with olive and olive-oil production – due to weather, soil, and landscape
variability, pest infestation, insect outbreaks and drought spells – the quality of decision-making is taken as primary
function for an efficient management of olive orchards and high quality olive oil production. In addition, despite DSSs
may help farmers in implementing climate-smart practices, their use among olive growers is limited due to the lack of
user-friendly interfaces and easy-to-interpret outcomes.
Solution:
The DSS will combine in-field sensors and remotely sensed data, a modelling platform and a farm management
system, merging territorial information (soil, weather, and crop traits) and IoT network, to improve the
sustainable production of olive tree orchards. The DSS will optimize water and nutrient use, and pest
management integrating knowledge of farmers, agronomists and IT experts.
PILOT 3.1 Decision Support System to support olive growers
Partners:
AGRICOLUS (Italy) | ENG(Italy) | DNET(Serbia) | INESC(Portugal) | TRAGSA (Spain) | INIAV ( Portugal) | UBIWHERE(Portugal) | FENADEGAS(Portugal)
23. Description:
The pilot aims at promoting precision farming practices and providing technology and methods to optimize the
precision and intelligence levels of Mediterranean Woody Crops (Apple Trees, Olive Groves, and small Vineyards),
considering the small farmers economical constraints.
Problem:
Mediterranean Woody Crops are being severally affected by the climate changes (water scarcity), pests and diseases.
Besides, the majority of these farms are small, low profit, low tech and have high labor costs. These farmers need
simple, intuitive and cost effective technology to help them overcome climate changes, pests and diseases, and
become more profitable by reaching the precision agriculture “Holly Grail ” concept.
Solution:
To this end the pilot aims at supporting better knowledge about crop development, pest and diseases and soil
state, as well as, improved solutions for agricultural practices such as about pesticide and fertilization application,
by using cost effective IoT solutions and upgrading conventional machinery and technology. This will enable to
make a more efficient usage inputs such as of water, energy, macro-nutrients, and pesticides increasing the
profits of small farmers and reduce their environmental impact. Reducing the spraying losses (more than 20 %),
the irrigation water consumption approximately 10%, and the NPK overdosage in 15%.
PILOT 3.2 . Precision Farming for Mediterranean Woody Crops
Partners:
INESC TEC ( Portugal) | INIAV (Portugal) | UBIWHERE (Portugal) | FENADEGAS (Portugal) | Cooperativa de Amarante (Portugal)
24. Description:
This pilot aims at providing a set of tools to monitor and manage the Mediterranean fruit fly (Ceratitis capitata)
which is dangerous pest with a wide range of distribution and host plants. Automatic capture traps and remote
sensing technologies will be employed to predict and support in taking decision and improve citrus farms in
Valencia region.
Problem:
The citrus sector in the Valencian Community is a relevant economic activity nationally and regionally, for this reason
the Ministry of Agriculture promote a program of control of Mediterranean fruit fly since this is the main pest that
attack crops and citrus in these areas.
Solution:
Develop the Sterile Insect Technique, a biological control technique against pests that respects the environment,
fauna and human health. This technique includes the monitoring through a network of traps and remote sensors
which allow to know the tracking and the hours of maximum activity in order to define the strategy of sterile male
release.
PILOT 3.3 PEST MANAGEMENT CONTROL ON FRUIT FLY
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
25. Description:
Open platform for improved crop monitoring in potato farms: Pilot aims at integrating machinery data combined with
crop- and field-specific info into WatchITgrow to analyze the interaction of parameters (yield data fertilization and
protection data with satellite data, weather and soil info). Advice will be provided to farmers for the optimization of
field management.
Problem:
WatchITgrow uses remote sensing data (Sentinel 2, Copernicus program), combined with local meteo and soil data, to
inform farmers via a user-friendly web application on the status of their crops and on expected yield. Limited access to
ground truth data (measured yields, crop variety, exact planting date) hampers the validation of crop yield models and
specific management advice.
Solution:
AVR Connect is the recently started IOT cloud platform acting as a data hub between the machine and other
stakeholders. In this pilot data from AVR potato planters and harvesters will be added to the WatchITgrow
platform. These machine data will be combined with crop- and field-specific info such as planting date , variety,
fertilization, crop protection, crop damages ..., and with satellite data, weather and soil info i) to gain better
insights on the interaction of these parameters and their impact on the final yield and ii) to provide advice to
farmers on how to optimize their current field practices in order to increase their yields in a sustainable way.
PILOT 3.4 OPEN PLATFORM FOR IMPROVED CROP MONITORING
Partners:
VITO(Belgium) | AVR(Belgium)
26. PILOT CLUSTER 4 OVERVIEW
Pilot Cluster: 1
Sector: Livestock
Focus: Animal Health, High Quality
Description:
This cluster will focus on supporting farmers for livestock animal health and high quality in the production of animal
products with farmers’ dashboards with AI-based prediction and decision support for animal Health and animal
products. Three pilots are milk cow oriented with one focusing on AI Machine learning for predictive milk production
and dashboard including data flow for invoicing, settlement, accounting, bank and insurance.
1. Dairy Farmers Dashboard for the entire milk and meat production value chain
2. Consumer awareness: Milk quality and animal welfare tracking
3. Proactive milk quality control
4. Optimal chicken farm management
Partners:
TRAGSA(Spain) | ELGO(Greece) | ICSS (Greece) | SIVECO (Romania) | UPM(Spain) | ODINS(Spain) | UMU(Spain) | INESCTEC ( Portugal) | APPR(Romania)
27. Partners:
Agricultural DataFlow(NO) | Mimiro (NO) | SINTEF (NO | TFoU (NO)
Description:
This pilot focuses on a full dataflow dashboard with animal product accounting, settlement and payment, including
decision support around milk production based on AI Machine learning from sensor data and other data sources.
Problem:
Providing farmers information and advice in a suitable way for farmers overview and support the whole production
value chain, including accounting and settlement data. The focus case is on milk production in Norway in general and
the Trøndelag region in particular. National scale Norway is with 8500 dairy farms, 230 000 cows, 12000 farms for
Dashboard, Data from 2000 milk robots that is in current production providing milking production data. 500 sensors
for health and fertility. 50 sensors for measuring fatness of cows and fat content for milk.
Solution:
Providing a Farmers Dashboard supported by the Agricultural Dataflow platform for accounting, settlement,
payment, bank, insurance demonstrating interoperability interfaces for different systems in the value chain.
Providing AI-based Prediction systems for milk production using sensor data from sensors on animal milk
production and health, collected and provided through the Mimiro data collection platform, where the farmer
will own his own data.
PILOT 4.1 Dairy Farmers Dashboard for the entire milk & meat
production value chain
28. Partners:
Maccarese (IT) | Latte Sano (IT) | Coldiretti (IT) | Engineering (IT) | RoTechnology (IT)
Description:
This pilot focuses on implementing an information flow optimization across different actors form the supply chain (including the
consumers), giving back the relevant information to each recipient.
Problem:
• The quality of the milk is closely linked to the welfare of the animal: if the animal eats well and in adequate amounts, rests and is
healthy, this will increase milk production and quality, and lead to increased dairy yields. Also the processing companies are
interested to the quality of milk levels, as they pay to the farmers a variable premium, based on pre-defined (on legal basis)
quality indicators of milk (these indicators are focused on the hygiene and welfare of the livestock, and encourage the farmers to
produce milk with higher quality)
• The breeding company already collects a huge amount of data linked to animal welfare monitoring coming from different sources
and devices, without connecting other actors from the supply chain in this valuable information process
• Consumers ask for transparency on the food they eat
Solution:
DEMETER will provide a solution able to give an added value to the use of data collected from the farm, providing:
• Platforms integration (optimizing the availability of scattered data in a single access point) and data management improvements
• Improvements in milk quality measurements
• Efficient collaboration and information exchange between the breeding farmer and the processing company in a short local chain
by the use of a blockchain-based tracking system able to follow all the production phases and monitor animal welfare. The
relevant information can be visible to the consumers on the product’s label.
PILOT 4.2 CONSUMER AWARENESS: MILK QUALITY AND ANIMAL
WELFARE TRACKING
29. Partners:
TEAGASC (Ireland) |. TYNDALL-UCC (Ireland) | ZOETIS (International) | INTRASOFT (Belgium)
Description:
This pilot focuses on prediction models of cow welfare and health based on analysis of streaming data from cow sensors. Appropriate
ICT tools will measure relevant parameters on a continuous, real time basis.
Problem:
Traditional farming involved management systems based on direct observation of animals and intuitive decision making by the
farmer. Larger animal numbers and reduced available time of the farmer have necessitated changes, potentially resulting in less
available time to observe and detect welfare and health issues of individual animals. At the same time, societal expectations are
increasing in terms of animal well-being and animal health. Thus, it is necessary to develop alternative mechanisms to predict welfare
and health issues.
Solution:
The use of different indicators and technological sensors will enable a large number of measured variables to be recorded, the
integration of which information will allow very strong robust prediction models to be established. Biochemical tests will also be
conducted to confirm health status. Thus the IoT will be used in establishing a farming system that will (a) predict when an animal is
not functioning properly; (b) establish a target that e.g. 95% of cows had no significant issue throughout their lactation; and (c)
satisfy claims of the well-being of animals.
PILOT 4.3 ANIMAL WELL-BEING AND EFFICIENCY
30. Partners:
DNET Labs (Serbia) | Sinkovic (Serbia) | UDG (Montenegro) | GFA (Georgia) | InData (Georgia) | ITC (Slovenia)
Description:
Pilot focuses on wellbeing of the chicken on poultry farms to ensure optimal growing conditions.
Problem:
Environmental conditions on the farms and the general wellbeing of the chicken are having a profound impact on the
effectiveness of the breeding process. Ability to not only monitor a range of environmental parameters, but also to
automatically detect stress level of the birds and react accordingly are among the top priorities of poultry farmers.
Solution:
Pilot will deploy and validate open platforms designed for integrated poultry farm management with focus on
preserving the wellbeing of the chicken. A range of different IoT devices will be connected, live measurements
collected and processed on the edge and in the cloud. Using several data analytics and AI based algorithms, advices
and suggestions on how to improve farm operation will be given to the farmers via web, mobile and chatbot clients.
The pilot will cover the supply part of the farming business.
It will serve as the basis for execution of pilots in the context of Cluster 5, where demand side will be addressed
through further integration and interoperation of various systems. Pilot activities will be done across 4 countries,
ensuring diverse inputs and potentially wide impact.
PILOT 4.4 OPTIMAL CHICKEN FARM MANAGEMENT
31. PILOT CLUSTER 5 OVERVIEW
Pilot Cluster: 5
Sector: Cross-sectorial
Focus: Full supply chain, interoperability, robotics
Description:
The goal of this cluster is to run pilots across several sectors (fruit, vineyards, cattle, poultry) and to address both
supply and demand sides of the supply chain. Such approach will enable us to validate interoperability of platforms
and solutions used in different sectors as well as to validate interoperability of platforms used for management of on-
farm and post-farm (supply chain) activities. The complete lifecycle of a product will be covered by inclusion of
representatives of the recycling industry through the open call.
1. Disease prediction and supply chain transparency for orchards/vineyards
2. Farm of things in extensive cattle holdings
3. Pollination optimisation in apiculture
4. Transparent supply chain in poultry industry
Partners:
DNET Labs (Serbia) | Srem (Serbia) | UDG (Montenegro) | Plantaze (Montenegro) | Sinkovic (Serbia) | GFA (Georgia) | InData (Georgia) | ITC (Slovenia) |
FEDE (Spain) | WODR (Poland) | UPM (Spain) | Napieerata (Poland) | Maciej (Poland)
32. Description:
This pilot will address both on-farm and post-farm activities, from technical and business perspectives. Data
analytics modules will reason over acquired sensor data and suitable advices given to farmers. Product passports
will be created for wine production and supply chain stakeholders (retailers, consumers) engaged.
Problem:
The ability to reliably identify appearance of diseases and their prevention is among the major challenges of vineyards’
and orchards’ owners. Further, with the increased focus of consumers on the origin of the food and its production
process as well as the ability to transparently provide information about it are becoming important aspects for a
market success, but difficult to achieve without adequate tools.
Solution:
Pilot will deploy and validate open platforms designed for integrated management of orchards and vineyards as well as
for creation of a transparent and trusted supply chain. While doing so, a range of different IoT devices will be
connected, live measurements collected and processed on the edge and in the cloud. Using data analytics, advices and
suggestions on how to improve farm operations (disease prevention, irrigation optimization) will be given to the
farmers via web, mobile and chatbot clients. Product passport concept will be used to capture field activities of
importance from the consumer and supply chain perspectives. The pilot will be done across 4 countries, ensuring
diverse inputs and potentially wide impact.
PILOT 5.1 DISEASE PREDICTION AND SUPPLY CHAIN TRANSPARENCY FOR
ORCHARDS/VINEYARDS
Partners:
DNET(RS) | SREM(RS) | UDG(MNE) | Plantaze (MNE) | Sinkovic(RS) | INDATA(GE) | GFA(GE) | ITC(SLO) | FEDE(ES) | WODR(PL) | UPM(ES) | Napierata(PL) | Maciej(PL)
33. Description:
A new generation of farmers request technology as a competitiveness advantage and a matter to develop better
products at effective best practices. Pilot aims to modernize the rural environment and livestock sector specifically
improving the production management with new technologies as Data Automation, Voice Recognition and Animal
Electronic Identification based on RFID.
Problem:
The current RFID devices identifies each animal with an unique code which cannot be modified or deleted. This
unique and individual code which provides a safety advantage, unfortunately is the only information that can be
stored with the existing animal RFID identifiers. The farm workers finds difficulties in managing animals with their
hands and at the same time taking handy notes to register the animal data.
Moreover, the products quality from extensive cattle can be improved with a proper management of crops and silage.
Solution:
The introduction in the market of advanced animal identification devices under ISO 14223, 1-3. can allow
managing more information by different actors in the full supply chain (farmers, veterinarians, markets, fairs,
abattoirs), each of them with a different access level to the data stored in the devices. Animal traceability
information (birth holding, fattening country…) will make the final consumer confident regarding the control
during the animal lifetime. In order to optimize the daily task of farm workers and reduce the errors during the
data capture, the Voice recognition technology will let them to take data and record them with complete safety.
And Artificial Intelligence and Data Analytics can helpfully assist farmers in accurately managing crops and silage.
Partners:
DNET(RS) | SREM(RS) | UDG(MNE) | Plantaze (MNE) | Sinkovic(RS) | INDATA(GE) | GFA(GE) | ITC(SLO) | FEDE(ES) | WODR(PL) | UPM(ES) | Napierata(PL) | Maciej(PL)
CODAN(ES) | TECNALIA(ES) | TRAGSA(ES) | CENTRIA (FI) | PROBOT(FI)
PILOT 5.2 FARM OF THINGS IN EXTENSIVE CATTLE HOLDINGS
34. Description:
This pilot will address apiary management and provide the technology and methods to optimize the pollination by
honey bees. Data analytics modules will reason over acquired sensor data and suitable advices will be given to farmers
and beekeepers. The pilot will involve at least one beekeeper and three farms for the testing and validation, and will
be trialed and validated on arable crops, particularly oilseed-rape and buckwheat.
Problem:
Among the many potential responses to pollinator decline, better pesticide control, integrated pest management, and
improved pollinator control and management are particularly important activities. Honeybees and other bee species
are among the most economically valuable pollinators of crop monocultures worldwide, and they play a key role in
improving the production profitability of many crops. In Poland, the number of bee colonies in 2009 was sufficient for
pollination to a minimum degree of ~44% of the area of the main cultivated plants, flowering at a similar time and
needs for pollination increase.
Solution:
Integration of farmers’ Decision Support Systems (DSS), farm management and apiary management systems,
enabling a better communication of farmers and beekeepers to protect bees and to optimise pollination of crops
with the aim of improving their yields. In particular, the pilot will connect the DSS created by the regional
agriculture advisory center, with farm and apiary management systems to manage beekeeping information and
farming activities like planned fertilizations, and to provide new advisory services.
PILOT 5.3 POLLINATION OPTIMISATION IN APICULTURE
Partners:
DNET(RS) | SREM(RS) | UDG(MNE) | Plantaze (MNE) | Sinkovic(RS) | INDATA(GE) | GFA(GE) | ITC(SLO) | FEDE(ES) | WODR(PL) | UPM(ES) | Napierata(PL) | Maciej(PL)
35. Description:
This pilot will address the post farm activities of a poultry farm. It will validate both performance regarding
technical features as well as feasibility of business models. Product passports will be created for poultry products
and supply chain stakeholders (retailers, consumers).
Problem:
Supply chain in the poultry business is well developed with multiple stakeholders fulfilling different roles and adding
value. However, despite this, the flow of information between different actors is fragmented, thus hampering the
ability to exchange information and create an integrated view of the complete supply chain, from providing feed to
retail and finally consumers. The last step, engaging consumers and providing them a transparent and trustworthy
insights into the food production process, has become one of the most significant challenges having in mind the
changing consumer attitude towards understanding where they food is coming from and how it was produced.
Solution:
The pilot will cover the supply part of the poultry farming business and farm activities leading to releasing products to
the next actor in the supply chain. Information about the wellbeing of the chicken, the origin of the food used,
resource usage, etc. will be collected and recorded in a distributed fashion to enable transparent and trustworthy
information sharing. The platform will implement and validate APIs and interfaces based on standards (GS-1 Digital
link) and market drivers to ensure easy interaction and interoperation of different supply chain stakeholders. Pilot
activities will be done across 3 countries, ensuring diverse inputs and potentially wide impact.
PILOT 5.4 TRANSPARENT SUPPLY CHAIN IN POULTRY INDUSTRY
Partners:
DNET(RS) | SREM(RS) | UDG(MNE) | Plantaze (MNE) | Sinkovic(RS) | INDATA(GE) | GFA(GE) | ITC(SLO) | FEDE(ES) | WODR(PL) | UPM(ES) | Napierata(PL) | Maciej(PL)