Sustainable Food Supply Chains through Artificial Intelligence

Drivers for sustainable food supply chains

On the one hand, developments through artificial intelligence (AI) can be understood as a “technology push”. In the supply chain, AI is currently used primarily for optimization in the areas of design, planning, scheduling and for predicting production volumes [1, 2]. In recent years, time series or big data analyses have primarily been used to detect anomalies in production data. The applications therefore primarily cover strategic areas rather than operational ones. It can also be seen that AI applications have thus far been implemented selectively and not comprehensively along the entire supply chain. In order to change this, data, trust and a cultural change are required [1]. The use of explainable AI (XAI) can present results of AI to users in a comprehensible manner and promote trust [3].

On the other hand, development potential based on “market pull” is evident. Stakeholders such as political decision-makers, suppliers, producers and consumers are increasingly interested in sustainable food supply chains. Possible measures to achieve this include environmentally friendly decisions, optimization of distribution channels and restructuring [4]. Consumer trends show that transparency is the strongest trend. It has a significant impact on logistics, as this trend influences the entire value chain. In addition, food waste awareness, which includes discarded food and losses caused by inefficient processes and processing steps within the logistics chain, is also becoming significant due to strong growth in consumer trends [5].

Holistic data networking in supply chains

In the automotive industry, the proprietary data ecosystem, Catena-X, which is based on GAIA-X, enables collaboration within an industry sector [6, 7]. This promotes a data-driven value chain that meets the challenges of the industry. Another existing solution is the Manufacturing-X initiative, which strengthens sustainability, resilience and competitiveness of the industry with an intelligently networked data network across industrial sectors [8].

Supply chain from turkey as livestock to turkey meat as a food product

Based on the initial situation described above, this concept focuses on the parameters of production processes and resource use along the value chain from turkey as livestock to turkey meat as a processed food product, in order to visualize a sustainable food supply chain through the use of AI. According to Karwowska, there is little data on food waste in the meat industry. At the same time, the meat industry is characterized by a negative impact on the environment [9]. The Meat Atlas of 2021 shows that avoidable losses within the food supply chain from livestock to food are mainly present in the process steps leading up to slaughter [10].

Visualization of sustainable food supply chains

Figure 1 visualizes a classic food supply chain, which consists of actors from different stages of the value chain working together. In the supply chain, there is a flow of materials and information [11] (characterized by the transport processes). The visualization covers the food supply chain and includes producers, the processing and production stages through to distribution via retailers to the end consumer.

A potential challenge within the first processes of the food supply chain that is not recognized predictively can result in it being passed on along the material flow. A non-centralized exchange of information can hinder the recognition of such an eventuality. Measures may not be initiated promptly enough, meaning that the problem is no longer resolved and the consumer consumes a food item which may be unsafe. This is visualized in Figure 2.

The conceptually developed sustainable supply chain is based on the networking of all players across the supply chain. In this network, it is possible to centrally store and intelligently link the production data of those involved in the process and to exchange information between the players along the food supply chain.

In addition, an exchange between all players about process flows can promote understanding of the needs, requirements and processes of others. On the one hand, the use of AI (both in the supply chain as a whole and in its individual sectors) creates opportunities to predictively identify and resolve challenges. On the other hand, the networking and exchange of data can also promote a centralized flow of information so that food which may be unsafe can be removed from the process at an early stage and the possibility of it reaching the consumer can be eliminated. Figure 3 visualizes the approach.

It is also possible to store data centrally along the food supply chain without other actors having access to it, thereby preserving the data sovereignty of the individual actors in the supply chain. This means that each link in the value chain can decide on the receipt and use of data [12]. However, standardization, compatibility and interoperability of systems and processes promote effectiveness within the supply chain [13]. The resulting benefits are illustrated in Figure 4.

The visualization demonstrates how e.g. a diseased animal that would lead to an unacceptable food quality after further processing is detected through the use of AI in agricultural production. A direct exchange of processing information ensures that this animal is not processed and is removed from the supply chain. The AI can be guided by visual characteristics by working with image classification, image segmentation and object recognition. In this way, non-compliant incidents can be detected efficiently and at an early stage. Production and consumption parameters are also relevant in order for the AI to recognize processes that are outside the ideal range in good time. This can be achieved through regression, time series analyses or the detection of anomalies.

Effects of a sustainable food supply chain

By implementing sustainable food supply chains using the example of turkey as livestock to turkey meat as a processed food product, four possible effects are derived. These effects can be summarized as the promotion of transparency, process optimization, food quality and safety as well as animal health and welfare. Figure 5 visualizes these and shows that the compatibility and interoperability of the systems and processes along the supply chain should be fulfilled in order to ensure the highest possible effectiveness [13].

Possible effects of promoting transparency can be the implementation of a central exchange of information or the reduction of workload due to the availability of continuous information. Increased data transparency allows process steps along the food supply chain to be planned and executed in an optimized manner.

An example of this is the distribution of turkeys from the finishing phase to the slaughterhouse. The transparency of the animals’ weight data enables efficient route planning within the supply chain. As a result, turkeys can be slaughtered at the ideal slaughter weight, which not only reduces costs, but also makes the finishing period more sustainable and is therefore also beneficial to animal welfare.

The predictive identification of potential challenges and the reduction of rejects along the supply chain can be used as arguments for promoting food quality. Improving animal health and increasing animal welfare primarily boosts agricultural production and downstream processes. The early detection of possible diseases, for example, serves as a measurable parameter for this effect.

This article was created as part of the KINLI project, which is funded by the German Federal Ministry of Food and Agriculture (BMEL) under the reference number 28DK124C20.

You might also be interested in

MAKI—A Digital Assistant for Practice-Based Learning Why every factory is a learning factory Olaf Resch

With the help of digital assistants, academic teaching is possible in any factory. In order to achieve the best learning effects, however, the interests of all stakeholders must be taken into account. The factory wishes to deploy its employees quickly and productively, the learners desire a positive learning experience, and the educators want to illustrate abstract concepts in a meaningful and practical way. The only way to combine all of these perspectives is via a well-thought-out educational concept and highly functioning technology.

Industry 4.0 Science | Volume 42 | 2026 | Edition 2 | Pages 70-77

Serious Gaming and the Energy Transition Collaborative knowledge generation and interactive understanding of complex interrelationships Janine Gondolf , Gert Mehlmann, Jörn Hartung, Bernd Schweinshaut, Anne Bauer

Conveying the complexity and multifaceted nature of the energy transition to a broad audience is a challenge. This article demonstrates how interactive serious games on a multitouch table can help make connections tangible and comprehensible. The games and the table were used in various conversational contexts. These are presented here in three case vignettes based on participant observation of the different applications, as well as situated and shared reflection. The vignettes demonstrate how interaction can trigger epistemic processes, enable shifts in perspective, and foster collective thinking, all of which are necessary for shaping the future of society as a whole.

Industry 4.0 Science | Volume 42 | 2026 | Edition 2 | Pages 62-69

Industrial Transformation via a Machining Learning Factory A learning module to foster competencies for a sustainability-driven transformation Oskay Ozen , Victoria Breidling , Stefan Seyfried , Matthias Weigold

Sustainability-enhancing transformation processes are necessary in all sectors if we are to remain within planetary boundaries. This also applies to the industrial sector as a significant emitter of greenhouse gases. Employees need new competencies to master this complex task of industrial transformation. These range from CO2 equivalents accounting to the development and evaluation of transformation scenarios, including technical measures. The learning module developed here addresses these competency requirements and uses the example of the ETA factory to show how a competency-oriented learning module for industrial transformation can be structured. It essentially comprises four phases: data collection and CO2 equivalents accounting, cause analysis, development of measures and evaluation of measures.

Industry 4.0 Science | Volume 42 | Edition 2 | Pages 38-47 | DOI 10.30844/I4SE.26.2.38

Data Quality and Domain Expertise for Resilient AI Deployment Integrating anomaly and label error detection in industry Pavlos Rath-Manakidis, Henry Huick, Erdi Ünal, Björn Krämer , Laurenz Wiskott

AI implementation transforms work and worker-technology relationships in industrial quality control. This paper explores how approaches to data quality and model transparency support ethical AI deployment, fostering worker agency, trust, and sustainable work design in automatic surface inspection systems (ASIS). Recurring problems like data inefficiency, variable model confidence, and limited AI expertise point to key challenges of human-centered AI: user trust, agency and responsible data management. A solution co-developed with an ASIS supplier demonstrates that the challenges extend beyond the purely technical, underscoring the value of AI design that augments human capabilities. Technical solutions such as anomaly, label error, and domain drift detection are proposed to enhance data quality and model reliability. The insights emphasize the following generalizable strategies for resilient AI integration: understanding user-reported problems through a human-AI interaction lens, ...

Industry 4.0 Science | Volume 42 | Edition 1 | Pages 128-135 | DOI 10.30844/I4SE.26.1.120

Digital Competence Lab (DCL) for Speech Therapy Designing a learning platform to advance digital skills Anika Thurmann , Antonia Weirich , Kerstin Bilda, Fiona Dörr , Lars Tönges

The digital transformation of healthcare results in lasting changes in speech therapy. Smart technologies and artificial intelligence (AI) are creating new opportunities to ensure therapy quality, address care bottlenecks, and actively involve patients in exercise processes. At the same time, these developments are expanding the role of speech therapists, who increasingly use digital systems as supportive tools in addition to their core therapeutic tasks. Based on a feasibility study of the AI-supported application ISi-Speech-Sprechen in a real-world setting of complex Parkinson's therapy (PKT), this article outlines the key challenges associated with implementing smart technologies.

Industry 4.0 Science | Volume 42 | 2026 | Edition 1 | Pages 110-118 | DOI 10.30844/I4SE.26.1.102

AI Skills for Responsible Use Realistic learning environments, critical thinking, and role design in teams Valentin Langholf , Niklas Obermann , Uta Wilkens , Marco Kuhnke, Michael Prüfer

Artificial intelligence (AI) is changing the world of work. But how can work teams learn to use AI support in a way that delivers speed advantages and ensures consistently high quality? One possible approach is to test it in a workplace-like simulation. Trying it out under realistic conditions shows the role that critical thinking plays.

Industry 4.0 Science | Volume 42 | Edition 1 | Pages 100-107 | DOI 10.30844/I4SE.26.1.92