The beef supply chain is a complex system, involving crop farms, livestock farms, feedlots, transporters, slaughterhouses, retailers and consumers. Events occurring at farm level have huge effects on industry, consumers and other stakeholders, and vice versa. Nowadays, traceability systems collect some data from every segment of the supply chain, mainly to assure food safety to consumers. However, the potential for data sharing along the supply chain is much bigger than that. Shared value systems based on integrated data allow every segment of the supply chain to improve production efficiency and product quality. The main objective of this use case is to foster a technological framework, based on IoT, Open Data, Big Data and Blockchain, facilitating data sharing along the beef supply chain to improve decision-making and consumer trust.
Holistic approach for beef supply chain
This use case demonstrates the potential of IoT devices, Open Data, cloud platforms like FIWARE, Big Data analytics and Blockchain to create shared and added value for the beef supply chain through data sharing. Data sharing is aimed to improve decision-making in relation to resource efficiency and to enhance product traceability.
To achieve this goal, Ignacio Gomez and Carlos Callejero, the Use Case coordinators, and their team and partners relied on several testbeds to validate a holistic approach, integrating all the stakeholders of a typical beef supply chain (crop farm, cow-calf farm, feedlot, slaughterhouse or industry and consumers) to consider the variability of beef cattle production systems in Europe.
The main targets for this use case were monitoring and optimising animal production, health and welfare at farm and feedlot as well as during transportation and slaughtering. Furthermore, to increase trust among supply chain stakeholders through data sharing, which required the development of data governance models, allowing data sharing while preserving data privacy. To get there, the use case team built the Blockchain models in IBM Food Trust technology. Based on the API provided by IBM, a set of software modules were developed to keep tracking of each animal’s story. Thanks to these developments, the hardware and algorithms developed during the first half of the project were able to track meat information from farm to fork. In addition to that, the solution allows us to share information in a transparent way with all the stakeholders of the meat chain, which becomes increasingly important for consumers and food safety.
To improve the algorithms, which help to monitor animals’ conditions, the researchers focused on the improvement of a weighting algorithm in order to provide better insights about growth and health condition of calves in the feedlot. Furthermore, they also focused on improving the algorithms about grazing animals equipped with IoT collars and ear-tags. To integrate the information from all these devices, the use case team developed a web application to enable the end-user to access all gathered information through one central hub. The FIWARE-based cloud solution also takes Open Data sources such as Sentinel satellite or meteorological data into consideration. Based on that, the use case team developed a series of single purpose (specific for breeders, fatteners, crop farmers, etc.) alongside integrated multi-purpose user interfaces. Thanks to these user interfaces, farmers have information about everything that is happening in their farm and can receive alerts and notifications when an anomaly occurs among one of their animals. The combined, centralised data revealed promising results: a reduction in water usage, calf mortality, fuel consumption and time spent looking for animals in vast fields. These improvements through animal monitoring services apply for grazing as well as for feedlot scenarios. This only motivated the researchers more, so they created an enhanced version of the decision support systems (DSS) fundamental algorithms. The goal of these algorithms was to generate automated reports, alerts and advices for each farmer without them bothering about data interpretation at all. The feedlot DSS algorithms provide advice derived from the animal obtained from the IoT smart scale data. Thereby, helping farmers to identify growth issues, maximum weight and eating behaviour. The algorithms of the grazing DSS leverage the information coming from IoT collars and ear tags to generate the following recommendation for the farmers: escape events, reproductive events, health and animal welfare alerts and cow-calve cohesive behaviour monitoring.
Challenges and future perspectives
Revolutionising the beef supply chain from farm to fork bring about a plethora of obstacles and challenges which the use case team had to overcome. One of them was the redesign of the Bluetooth low-energy ear tags and their casing.
Since the plastic material initially selected for the housing of the IoT ear tags was resistant but inflexible, it caused tensions during ears movement and resulted in broken or even lost devices. Consequently, the team decided to go with a more flexible material for the casing which was able to absorb the tensions associated to ear movements. Even though the results regarding material and resistance were promising, the increase in price inhibited mass production and thus forced the use case to come up with an entirely new idea. They decided to attach the Bluetooth low-energy sensors through a box and a collar, making them collar tags rather than ear tags. This redesign struck the perfect balance between durability and animal welfare and was very welcome from farmers favouring not to pierce the cows’ ears.
The high number of test farms in 5 different countries and devices (more than 1000) has its advantages as well as disadvantages. In general, every testing site provided specific data which required an individual analysis to provide tailor-made management advice for extensive farming. During the Covid-19 pandemic farmers needed management advice more than ever before since their incomes were greatly affected by the closing of restaurants or the shut-down of other industries. Usually, sustainable, small-scale beef farms had restaurants as their major customers, but the pandemic practically eliminated this income stream and subsequently eliminating the possibility for farmers to invest into new technologies. The use case team thus decided to make a virtue of this necessity by creating an additional service: an online platform which connects the consumer directly with the producer.
In order to improve the management plan of a farm, obtaining and relying on the precision performance indicators is paramount. Since every farmer has their particular habits and ways of running daily operations - depending on farm size, suppliers, sustainability, performance - flexibility was a main objective for this use case’s innovation. Only if a technological solution adopts to the needs and requirements of the end-user, can it become successful and widely adapted. Hence, the team developed one general tool that can easily be optimised and individualised to respond perfectly to the requirements. The resulting ShareBeef solution is the perfect example. It can either monitor or track the animals whenever the end-user needs the information or give detailed information on the entire value chain and life cycle of the product, tracking every step from farm to fork.
Achievements, products & services
Certification of grass-fed beef
IoT scales for fattening calves’ growth rate
Smart collars & ear tags for location, activity and temperature
IoT multi-sensor stations for transport and slaughtering conditions
Decision support system based on machine learning algorithms
Data traceability via blockchain from farm to fork