Search Results (127)

Food loss and waste from the European Union’s dairy supply chain, particularly in the management of fresh milk, imposes significant environmental burdens. This study demonstrates that implementing Radio Frequency Identification (RFID)-enabled digital decision-support tools can substantially reduce these impacts across the region. A cradle-to-grave life cycle assessment (LCA) was used to quantify both the additional environmental burdens from RFID (tag production, usage, and disposal) and the avoided burdens due to reduced milk losses in the farm, processing, and distribution stages. Within the EU’s fresh milk supply chain, the implementation of digital tools could result in annual net reductions of up to 80,000 tonnes of CO₂-equivalent greenhouse gas emissions, 81,083 tonnes of PM_2.5-equivalent particulate matter, 84,326 tonnes of land use–related carbon deficit, and 80,000 cubic meters of freshwater-equivalent consumption. Spatial analysis indicates that regions with historically high spoilage rates, particularly in Southern and Eastern Europe, see the greatest benefits from RFID enabled digital-decision support tools. These environmental savings are most pronounced during the peak months of milk production. Overall, the study demonstrates that despite the environmental footprint of RFID systems, their integration into the EU’S dairy supply chain enhances transparency, reduces waste, and improves resource efficiency—supporting their strategic value. Full article

The amount of protein and fat in raw milk determines its quality, value in the marketplace, and related payment to suppliers. Technicians use expensive specialized laboratory equipment to measure milk quality in specialized laboratories. The continuous quality monitoring of the milk supply in the supplier’s tanks enables the production of higher quality products, better milk supply chain optimization, and reduced milk waste. This paper presents an inexpensive AI-powered IoT sensor that continuously measures the protein and fat in the raw milk in the tanks of dairy farms, pickup trucks, and intermediate storage depots across any milk supply chain. The proposed sensor consists of an in-tank IoT device and related software components that run on any IoT platform. The in-tank IoT device quality incorporates a low-cost spectrometer and a microcontroller that can send milk supply measurements to any IoT platform via NB-IoT. The in-tank IoT device of the milk quality sensor is housed in a food-safe polypropylene container that allows its deployment in any milk tank. The IoT software component of the milk quality sensors uses a specialized machine learning (ML) algorithm to translate the spectrometry measurements into milk fat and protein measurements. The paper presents the design of an in-tank IoT sensor and the corresponding IoT software translation of the spectrometry measurements to protein and fat measurements. Moreover, it includes an experimental milk quality sensor evaluation that shows that sensor accuracy is ±0.14% for fat and ±0.07% for protein. Full article

The dairy industry faces unique challenges in demand forecasting due to the perishability of products and the variability in consumer demand. This paper explores the state of the art in demand forecasting for multi-retailers in the dairy industry, highlighting the role of technological innovations and advanced methodologies. The integration of machine learning and data analytics is transforming demand forecasting, enabling more accurate predictions and efficient supply chain management. By addressing the complexities of the dairy supply chain and adapting to changing consumer preferences, retailers can optimize inventory levels, reduce waste, and enhance product availability. This study provides insights into current trends and methodologies, offering a comprehensive overview of demand forecasting in the dairy industry. Full article

Growing concern over food safety and adulteration has thrust milk traceability technologies to the forefront of agrifood supply chains. This qualitative study explores the technological, organisational, and environmental (TOE) determinants of traceability technology adoption in Saudi Arabia’s dairy sector. In-depth semi-structured interviews with nine senior managers from small-, medium-, and large-scale dairy farms were analysed thematically in NVivo. Thematic analysis revealed that technological cost and compatibility played crucial role, while contrary to the prior literature, respondents downplayed technological complexity, arguing that training could offset it. Organisational culture and employee resistance were the primary inhibitors within dairy firms. Saudi Vision 2030, post COVID-19 consumer pressure and competitor pressure emerged as the dominant environmental factors. The findings offer insights for managers and policymakers on how to improve supply chain transparency, operational efficiency, product quality, and consumer trust while advancing several UN SDGs. Full article

The increasing emphasis on integrating sustainability into corporate operations has prompted supply chain managers to incorporate not only economic objectives but also environmental and social considerations into their network designs. This study presents a structured six-stage methodology to develop a fuzzy multi-objective optimization model for the sustainable design of a multi-level, multi-product forward supply chain network. The model incorporates two conflicting objectives: minimizing total network costs and reducing environmental impact. To quantify environmental performance, a comprehensive life cycle assessment is conducted in accordance with the ISO 14040 standard and the ReCiPe 2016 method, focusing on three impact categories: human health, resources, and ecosystems. To address uncertainty in demand and production costs, fuzzy mixed-integer linear programming is employed. The model is validated and applied to a real-world case study of a dairy small-to-medium enterprise in Ecuador. Using the epsilon-constraint method, a Pareto frontier is generated to illustrate the trade-offs between the economic and environmental objectives. This research provides a robust decision-making tool for uncertain environments and advances knowledge on the integration of life cycle assessment with supply chain optimization and network design methodologies for sustainable development. Full article

Under the context of increasing demand for transparency, efficiency, and trust in food systems, digital traceability is emerging as a key strategy for improving value creation across agri-food supply chains. This study investigates how different governance structures influence the design and effectiveness of digital traceability systems. We develop an analytical framework linking four guiding questions (why, where, how, and who) to traceability performance and apply it to five Italian supply chains (wine, olive oil, cheese, pasta, and dairy) through 28 semi-structured interviews with companies, cooperatives, and technology providers. The results show that governance models shape traceability adoption and function. In captive systems (e.g., wine), traceability ensures compliance but limits flexibility, while in modular or relational systems (e.g., pasta and cheese), it fosters product differentiation and decentralized coordination. Across cases, digital traceability improved certification processes, enhanced consumer communication (e.g., via QR codes), and supported premium positioning. However, upstream–downstream integration remains weak, especially in agricultural stages, due to technical fragmentation and limited interoperability. The diverse experience data from company interviews reveal that only 30% of firms had fully integrated systems, and fixed costs remained largely unaffected, though variable cost reductions and quality improvements were reported in the olive oil and cheese sectors. The study concludes that digital traceability is not only a technical solution but a governance innovation whose success depends on the alignment between technology, actor roles, and institutional arrangements. Future research should explore consumer-side impacts and the role of public policy in fostering inclusive and effective traceability adoption. Full article

Organic farming is becoming increasingly important in agricultural production, especially in mountain and foothill areas. In organic farms, unlike conventional ones, no mineral fertilization or chemical plant protection is used, which often limits the economic efficiency of production. It is commonly believed that conventional farming poses a threat to biodiversity due to the use of mineral fertilization, chemical plant protection, and highly productive crop varieties, and the products obtained are in many respects of lower quality than those from organic farms. The aim of this work is to compare the quality and fertility of soils and the biodiversity of grasslands in organic and conventional farms, using the example of a foothill area within the commune of Kamienna Góra located in the Western Sudetes. Thirty-three areas representing 11 farms that produce dairy cattle in a grazing system were selected for analysis. The properties of soils in organic and conventional farms and their nutrient status did not differ significantly, except for the content of available potassium, which was higher in the group of organic farms. This fact seems to be related to the type of parent rock. All soils had acidic, slightly acidic, or strongly acidic pH levels. The greatest differences between pastures in organic and conventional farms concerned the sward species composition and biodiversity indices. Grasslands in organic farms were much richer in species, which was reflected by the species richness (SR) index and the F-fidelity index. The species inventoried clearly formed two groups that are characteristic of organic and conventional grasslands. The greater biodiversity of grasslands in organic farms did not have a significant effect on the fodder value of the sward, which should be considered good, allowing producers to participate in short supply chains. However, in all farms, regardless of their type, it would be advisable to carry out gentle liming. Full article

The rapid growth of world population and increase in living standards have led to an increase in the demand for high-quality, safe food. The Food and Agriculture Organization of the United Nations (FAO) estimates that by 2050 the demand for food will increase by 60%, and production of animal protein will increase by 1.7% a year, with meat production to increase by nearly 70%, dairy products by 55%, and aquaculture by as much as 90%. Microbial contamination of food is a significant problem for the accessibility of safe food which does not pose a threat to the life and health of consumers. Campylobacter, Salmonella, and Yersinia are responsible for thousands of food-borne infections in humans. Currently, numerous programs are being developed to combat pathogenic bacteria in the food supply chain, especially at the primary production stage. These approaches include physical, chemical, biological, and other strategies and methods used to inhibit the bacterial growth of bacteria or completely eliminate the pathogens from the food chain. Therefore, an extremely important goal is to provide safe food and control its quality by eliminating pathogenic and spoilage microorganisms. However, the use of chemicals in food preservation has negative effects for both the consumption values of food and the natural environment. Therefore, it seems absolutely necessary to implement measures utilizing the most environmentally friendly and effective techniques for controlling microbial contamination in food. There is a great need to develop ecological methods in food production which guarantee adequate safety. One of these methods is the use of bacteriophages (bacterial viruses) naturally occurring in the environment. Given the above, the aim of this study was to present the most natural, ecological, and alternative methods of food preservation with regard to the most common foodborne zoonotic bacteria. We also present methods for reducing the occurrence of microbial contamination in food, thus to produce maximally safe food for consumers. Full article

Automated Planning and Scheduling (APS) is an area of artificial intelligence dedicated to generating efficient plans to achieve goals by optimizing objectives. This case study is based on a middle-mile segment of the dairy supply chain. This article focuses on applying and analyzing APS compared to the following classical optimization methods: mathematical modeling based on Mixed-Integer Programming (MILP) and the Genetic Algorithm (GA). The language supported for APS modeling is Planning Domain Definition Language (PDDL), and the temporal solver used is the OPTIC planner. Optimization methods are guided by a mathematical model developed specifically for the research scope, considering production, inventory, and transportation conditions and constraints. Dairy products are highly perishable; therefore, the main optimization objective is to minimize Tmax, i.e., the total time to meet demand, ensuring that the products are available at the distribution center with a viable shelf life for commercialization. The APS application showed limitations compared to the other optimization approaches, with the Exact Method proving the most efficient. Finally, all algorithms, models, and results are available on GitHub, aiming to foster further research and enhance operational efficiency in the dairy sector through optimization. Full article

The agri-food sector is undergoing profound transformations driven by ecological and digital transitions, as well as evolving consumer and nutritional choices. These shifts pose significant challenges but also open new opportunities for businesses to enhance sustainability and competitiveness through circular economy principles. In response, Spoke 9 of the National Agritech Center (PNRR) has launched a survey to analyze agri-food companies and sustainability practices and promote circular strategies. A large-scale survey conducted in early 2024 gathered data from 3002 agri-food companies, covering 20 Italian regions and six major supply chains (wine, olive oil, dairy, milk, fruit and vegetables, and beekeeping). The study is the first attempt in Italy to get metrics on these topics from agri-food companies, and it provides a comprehensive assessment of circular economy practices in the sector. The key objectives of the work are as follows: (1) developing integrated sustainability indicators; (2) sector-specific circular metrics; (3) identifying best practices and gaps; (4) supporting policy and decision-making; and (5) benchmarking and monitoring. Full article

Key Performance Indicators (KPIs) are rates, percentages, or averages that convey information depending on their application field. In the Food Supply Chain (FSC), a comprehensive study is lacking. This paper fills the gap through a systematic literature review of 125 documents on FSC performance measurement. Bibliometric analysis shows a growing publication trend, with common keywords being KPIs, supply chain management, performance, and sustainability. Content analysis identifies nine FSC product types, with agricultural, dairy, and meat products being the most common categories. Similarly, three FSC areas (supply, production, distribution) are outlined, with production receiving the greatest attention. Finally, KPIs are classified into economic, environmental, and social sustainability categories, to highlight their relationships with the triple bottom line. A framework including the most common KPIs for each stage of the FSC is also proposed, together with the specific KPIs for the different product types. Full article

Archeological evidence shows that dairy farming dates to the early Neolithic era in Europe, the Middle East, Asia, and Africa. Over time, it has evolved from domestication to intensive dairy farms with large, high-tech processing units. Dairy farming has contributed to economic growth, food production, employment, and processing industries. Nonetheless, it has been identified as a major contributor to climate change. This study explores the literature on dairy farming and sustainable development goals (SDGs) to identify current scholarly developments since the formulation and adoption of the SDGs in 2015 and themes for future research. This paper argues that sustainability shortfalls in dairy farming are primarily driven by human processes associated with commercialization and industrialization rather than the animals themselves, although biological emissions remain an inherent factor. Data were analyzed using R package, Excel, NVIVO, and VoS Viewer. A review of the literature showed that dairy farming and its contribution to sustainability has gained more scientific interest since 2015. Moreover, livestock management, feed production and management, stakeholder management, logistics and supply chain management, and waste management are the sources of environmental adversities associated with dairy farming. Notably, these are human processes developed from the commercialization of dairy farming and involve multiple stakeholders across the supply chain. While solutions are embedded within these processes, innovation emerges as a key driver of sustainability and a source of opportunities to strengthen sustainability in the dairy farming sector and achieve SDGs. Sustainability strategies, such as sustainable intensification, multifunctional agriculture, and agro-ecology should be implemented to improve sustainability in the dairy sector. Full article

This study explores the application of Fourier transform infrared (FTIR) spectroscopy combined with chemometric and machine learning techniques for authenticating sheep’s milk and distinguishing it from cow’s milk. The demand for accurate authentication methods is driven by the high production costs of sheep’s milk and the prevalent issue of adulteration with cow’s milk, which can have economic, health, and ethical implications. Our research utilizes exploratory analysis, regression, and classification tasks on spectral data to identify characteristic spectral signatures and physicochemical parameters for sheep’s milk. Key methods included the application of decision trees, random forests, and k-nearest neighbors (KNN), with the random forest model showing the highest predictive accuracy (R² of 0.9801). Principal Component Analysis (PCA) and analysis of variance (ANOVA) revealed significant spectral and compositional differences, particularly in fat content and wavelengths responsible for amide I and II bands (1454 nm and 1550 nm) correlated with the conformational characteristics of the proteins, with sheep’s milk exhibiting higher values than cow’s milk. These findings indicate the potential of FTIR spectroscopy as a reliable tool for milk authentication. Currently, digitalization within the milk production chain is limited, particularly in the case of regional dairy products. The introduction of integrated photonics, machine learning, and, in the future, telemetry systems would enable dairy farmers to optimize their operations and ensure the origin and quality of the milk supplied to milk producers. Full article

In a scientific context, the main focus of sustainable supply chain management is on the creation and optimization of product and information flows; however, the management of financial flows receives insufficient attention. All effectively developed supply chain activities may collapse as a result of inadequate management of sustainable supply chain financial processes. In order to successfully develop systematically functioning processes of the international supply chain, it is necessary to analyze how to apply financing instruments in a targeted and effective manner. Adequate financing of the sustainable supply chain is the effect of great prospects and competitive advantage not only on a national scale but also in international markets. The aim of this research was to assess the importance of financing instruments used in international sustainable supply chain finance. Correlation-regression analysis was chosen for the research, which was designed to assess the factors of financial instruments of the dairy industry sustainable supply chain using the example of a company. The results showed that the key factor in the supply chain processes of the dairy products production company was the turnover ratio of buyers’ debts; therefore, in order for the company to improve the indicators of the sustainable supply chain, it should allocate more financing specifically to the turnover ratio of buyers’ debts. Full article

The dairy supply chain encompasses all stages involved in the production, processing, distribution, and delivery of dairy products from farms to end consumers. Artificial intelligence (AI) refers to the use of advanced technologies to optimize processes and make informed decisions. Using the PRISMA methodology, this research analyzes AI technologies applied in the dairy supply chain, their impact on process optimization, the factors facilitating or hindering their adoption, and their potential to enhance sustainability and operational efficiency. The findings show that artificial intelligence (AI) is transforming dairy supply chain management through technologies such as artificial neural networks, deep learning, IoT sensors, and blockchain. These tools enable real-time planning and decision-making optimization, improve product quality and safety, and ensure traceability. The use of machine learning algorithms, such as Tabu Search, ACO, and SARIMA, is highlighted for predicting production, managing inventories, and optimizing logistics. Additionally, AI fosters sustainability by reducing environmental impact through more responsible farming practices and process automation, such as robotic milking. However, its adoption faces barriers such as high costs, lack of infrastructure, and technical training, particularly in small businesses. Despite these challenges, AI drives operational efficiency, strengthens food safety, and supports the transition toward a more sustainable and resilient supply chain. It is important to note that the study has limitations in analyzing long-term impacts, stakeholder resistance, and the lack of comparative studies on the effectiveness of different AI approaches. Full article