Localisation and circularity in perishable food supply chains are essential for sustainability. Poor allocation of time-sensitive food leads to waste, higher transport emissions, and unnecessary long-distance sourcing. Algorithms used in digital trading platforms and allocation systems can help address these problems by improving how local supply is matched with demand under real operational constraints. This paper examines localisation and circularity in the UK apple supply chain. Apples are an informative case because they are perishable, consumed fresh as dessert fruit, used as inputs across multiple food industries, and generate valuable by-products. We present a weighted-sum mixed-integer linear programming formulation for supply-demand allocation. The model encodes a single global objective with explicit weights on four operational criteria: price matching, quantity alignment, freshness requirements, and geographic distance. These weights make priorities explicit and adjustable, enabling transparent balancing between economic and sustainability considerations. The framework also supports the circulation of unallocated supply across allocation cycles. Using a realistic apple supply-demand dataset, we evaluate allocation outcomes under different priority settings. Results indicate that allocation outcomes are strongly shaped by both priority settings and the structure of the underlying supply network characteristics.
A wide range of raw materials are now used routinely in aquaculture feeds throughout the world, primarily to supply protein and energy in the form of lipid from edible oils. Protein meals and oils used can generally be divided into those of plant or animal origin and many have considerable potential to supply the required dietary nutrients required by aquaculture species. However, the use of any raw material introduces a suite of risks that need to be considered to enable the production of safe, sustainable and functional feeds to underpin this sector. A lack of understanding of some of those risks can result in failure of dietary specifications being met and/or negative nutritional elements being introduced (e.g. antinutritional factors). Importantly, it is this feed that when fed to food-producing animals is such an important element of food safety, and as such any undesirable aspects relating to feed production can also have a negative impact on the rest of the food chain. However, there is some disparity internationally among raw materials that are used and the perceptions surrounding the risk of their use. It is the scientific assessment of these risks that is the basis of this review.
Jhon Wilder Zartha Sossa, Adriana Maria Zuluaga Monsalve, Nolberto Gutiérrez Posada
et al.
The objective of this article is to identify and prioritize technologies, innovations and new businesses related to the dairy agro-industrial chain that are expected to emerge by 2035. To do so, the two-round Delphi method was used and questionnaires were applied to 27 national and international experts. A technology tree was built with Python codes and libraries, consisting of 174 topics. Additionally, 39 variables were generated for scenarios in the Good Livestock Practices BPG; Research, Development and Innovation R&D&I; Sustainable Livestock and Agroindustry groups, as well as four hypotheses and a bet scenario, with the future objectives of sustainable specialization of forage production and mass production and standardization in collection centers. This can be achieved through projects on technologies and innovations prioritized in the Delphi method, including ultrasound, pulsed combustion drying, dairy-derived medicinal products, bioethanol produced from whey, artificial intelligence and selection assisted by molecular markers, electromembrane filtration technologies, whey protein concentrates, life cycle assessment, blockchain, neural networks and smart assays, among others. The opportunity that actors in the Science, Technology and Innovation system have in the chain for the development of programs, plans, public policies and open innovation challenges in the prioritized technologies is highlighted.
Nutrition. Foods and food supply, Food processing and manufacture
Tsedey Azeze, Mitiku Eshetu, Tesfemariam Berhe
et al.
Abstract This study addresses the lack of comprehensive evaluations of the physico-chemical quality of raw milk and major dairy products, such as butter across supply chains and dairy production systems (DPSs) in Southern Ethiopia. Interviews with 360 dairy producers from Cash Crop Based (CCB), Enset Based (EB), Cereal Based (CB), and Diversified Crop Based (DCB) systems were conducted, along with group discussions to map the supply chains. For physicochemical analysis of milk and butter, samples were collected from CCB and EB systems, which vary in farming system and feed type. Results showed that milk supply chains ranged from short (producers directly to consumers) to longer chains (producers-collectors-cooperatives-consumers). Butter supply chains followed similar patterns, with both short and longer chains (producer-retailer-collector-wholesaler-consumer). The physico-chemical quality of raw milk significantly declined (p < 0.05) from producers to retailers (fat: 5.3% → 4.3%, SNF: 7.9% → 7.5%, TS: 13.2% → 11.8%), likely due to adulteration. Retailers’ milk had higher water content (10.8%) compared to consumers (7.3%) and producers (5.7%). Enset-based systems had higher fat and TS levels than CCB, attributed to diverse feed sources. Butter quality also dropped from producers (fat: 85%, moisture: 15%) to retailers (fat: 78%, moisture: 18%). Saturated fatty acids (SFA) were highest in retailers (67%) compared to producers (65%) and consumers (55%). Overall, milk and butter quality declined along the supply chain, with EB systems outperforming CCB. Strengthening post-production quality control and training for retailers is crucial to preserving quality and understanding its nutritional implications.
We investigate the extreme return connectedness between the food, fossil energy, and clean energy markets using the quantile connectedness approach, which combines the traditional spillover index with quantile regression. Our results show that return connectedness at the tails (57.91% for the right tail and 61.47% for the left tail) is significantly higher than at the median (23.02%). Further-more, dynamic analysis reveals that connectedness fluctuates over time, with notable increases during extreme events. Among these markets, fossil energy market consistently acts as the net receiver, while clean energy market primarily serves as the net transmitter. Additionally, we use linear and nonlinear ARDL models to examine the role of external uncertainties on return connectedness. We find that climate policy uncertainty (CPU), geopolitical risk (GPR), and the COVID-19pandemic significantly impact median connectedness, while economic policy uncertainty (EPU),GPR, and trade policy uncertainty (TPU) are crucial drivers of extreme connectedness. Our findings provide valuable insights for investors and policymakers on risk spillover effects between food and energy markets under both normal and extreme market conditions.
The need for an intelligent, real-time spoilage prediction system has become critical in modern IoT-driven food supply chains, where perishable goods are highly susceptible to environmental conditions. Existing methods often lack adaptability to dynamic conditions and fail to optimize decision making in real time. To address these challenges, we propose a hybrid reinforcement learning framework integrating Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) for enhanced spoilage prediction. This hybrid architecture captures temporal dependencies within sensor data, enabling robust and adaptive decision making. In alignment with interpretable artificial intelligence principles, a rule-based classifier environment is employed to provide transparent ground truth labeling of spoilage levels based on domain-specific thresholds. This structured design allows the agent to operate within clearly defined semantic boundaries, supporting traceable and interpretable decisions. Model behavior is monitored using interpretability-driven metrics, including spoilage accuracy, reward-to-step ratio, loss reduction rate, and exploration decay. These metrics provide both quantitative performance evaluation and insights into learning dynamics. A class-wise spoilage distribution visualization is used to analyze the agents decision profile and policy behavior. Extensive evaluations on simulated and real-time hardware data demonstrate that the LSTM and RNN based agent outperforms alternative reinforcement learning approaches in prediction accuracy and decision efficiency while maintaining interpretability. The results highlight the potential of hybrid deep reinforcement learning with integrated interpretability for scalable IoT-based food monitoring systems.
We consider a multi-retailer supply chain where each retailer can dynamically choose when to share information (e.g., local inventory levels or demand observations) with other retailers, incurring a communication cost for each sharing event. This flexible information exchange mechanism contrasts with fixed protocols such as always sharing or never sharing. We formulate a joint optimization of inventory control and communication strategies, aiming to balance the trade-off between communication overhead and operational performance (service levels, holding, and stockout costs). We adopt a common information framework and derive a centralized Partially Observable Markov Decision Process (POMDP) model for a supply chain coordinator. Solving this coordinator's POMDP via dynamic programming characterizes the structure of optimal policies, determining when retailers should communicate and how they should adjust orders based on available information. We show that, in this setting, retailers can often act optimally by sharing only limited summaries of their private data, reducing communication frequency without compromising performance. We also incorporate practical constraints on communication frequency and propose an approximate point-based POMDP solution method (PBVI/SARSOP) to address computational complexity. Numerical experiments on multi-retailer inventory scenarios demonstrate that our approach significantly improves the cost-service trade-off compared to static information sharing policies, effectively optimizing the schedule of information exchange for cooperative inventory control.
In this paper, we analyse the impact of international migration on the food consumption and dietary diversity of left-behind households. Using the Kerala migration survey 2011, we study whether households with emigrants (on account of international migration) have higher consumption expenditure and improved dietary diversity than their non-migrating counterparts. We use ordinary least square and instrumental variable approach to answer this question. The key findings are that: a) emigrant households have higher overall consumption expenditure as well as higher expenditure on food; b) we find that international migration leads to increase in the dietary diversity of left behind households. Further, we explore the effect on food sub-group expenditure for both rural and urban households. We find that emigrant households spend more on protein (milk, pulses and egg, fish and meat), at the same time there is higher spending on non-healthy food habits (processed and ready to eat food items) among them.
Instant food delivery has become one of the most popular web services worldwide due to its convenience in daily life. A fundamental challenge is accurately predicting courier routes to optimize task dispatch and improve delivery efficiency. This enhances satisfaction for couriers and users and increases platform profitability. The current heuristic prediction method uses only limited human-selected task features and ignores couriers preferences, causing suboptimal results. Additionally, existing learning-based methods do not fully capture the diverse factors influencing courier decisions or the complex relationships among them. To address this, we propose a Multi-Relational Graph-based Route Prediction (MRGRP) method that models fine-grained correlations among tasks affecting courier decisions for accurate prediction. We encode spatial and temporal proximity, along with pickup-delivery relationships, into a multi-relational graph and design a GraphFormer architecture to capture these complex connections. We also introduce a route decoder that leverages courier information and dynamic distance and time contexts for prediction, using existing route solutions as references to improve outcomes. Experiments show our model achieves state-of-the-art route prediction on offline data from cities of various sizes. Deployed on the Meituan Turing platform, it surpasses the current heuristic algorithm, reaching a high route prediction accuracy of 0.819, essential for courier and user satisfaction in instant food delivery.
This paper presents the first nationwide deployment of human activity recognition (HAR) technology in the on-demand food delivery industry. We successfully adapted the state-of-the-art LIMU-BERT foundation model to the delivery platform. Spanning three phases over two years, the deployment progresses from a feasibility study in Yangzhou City to nationwide adoption involving 500,000 couriers across 367 cities in China. The adoption enables a series of downstream applications, and large-scale tests demonstrate its significant operational and economic benefits, showcasing the transformative potential of HAR technology in real-world applications. Additionally, we share lessons learned from this deployment and open-source our LIMU-BERT pretrained with millions of hours of sensor data.
Bread as a staple food has been predominantly prepared from refined wheat flour. The world’s demand for food is rising with increased bread consumption in developing countries where climate conditions are unsuitable for wheat cultivation. This reliance on wheat increases the vulnerability to wheat supply shocks caused by force majeure or man-made events, in addition to negative environmental and health consequences. In this review, we discuss the contribution to the sustainability of food systems by partially replacing wheat flour with various types of plant ingredients in bread making, also known as composite bread. The sustainable sources of non-wheat flours, their example use in bread making and potential health and nutritional benefits are summarized. Non-wheat flours pose techno-functional challenges due to significantly different properties of their proteins compared to wheat gluten, and they often contain off-favor compounds that altogether limit the consumer acceptability of final bread products. Therefore, we detail recent advances in processing strategies to improve the sensory and nutritional profiles of composite bread. A special focus is laid on fermentation, for its accessibility and versatility to apply to different ingredients and scenarios. Finally, we outline research needs that require the synergism between sustainability science, human nutrition, microbiomics and food science.
Julie E. Campbell, Jessie-Lee D. McIsaac, Margaret Young
et al.
Child care environments offer an ideal setting for feeding interventions. CELEBRATE Feeding is an approach implemented in child care environments in two Maritime Provinces in Canada to support responsive feeding (RF) to foster children’s self-efficacy, self-regulation, and healthy relationships with food. This study aimed to describe RF in child care using established and enhanced scoring frameworks.
Alsadig Yahya, Abdeen Elkhedir, Mamoun A. Homaida
et al.
Potatoes are an important food crop worldwide and are rich in essential nutrients. However, cooking can reduce their nutritional value and alter their texture. This study aimed to investigate the impact of pretreating potato slices with lemon juice. The slices were immersed in 5% lemon juice solution for 3 h, rinsed with distilled water for another 3 h, then cooked at 100°C for 20 min. Findings revealed that lemon juice pretreatment (LJP) notably improved the texture, mouthfeel, and overall acceptability of the cooked potato slices of different sizes (CPS-Ds). Additionally, LJP significantly increased vitamin C and total phenolic contents, slightly decreased pH levels, and preserved the desired color of CPS-Ds. Consumer sensory evaluations also indicated a positive response to LJP samples, suggesting its potential application in the food industry. The study confirmed that LJP is an effective, sustainable, consumer-friendly, and cost-efficient technique for improving the quality of cooked potato slices.
Nutrition. Foods and food supply, Food processing and manufacture
This research investigates the performance of various machine learning algorithms (CNN, LSTM, VADER, and RoBERTa) for sentiment analysis of Twitter data related to imported food items in Trinidad and Tobago. The study addresses three primary research questions: the comparative accuracy and efficiency of the algorithms, the optimal configurations for each model, and the potential applications of the optimized models in a live system for monitoring public sentiment and its impact on the import bill. The dataset comprises tweets from 2018 to 2024, divided into imbalanced, balanced, and temporal subsets to assess the impact of data balancing and the COVID-19 pandemic on sentiment trends. Ten experiments were conducted to evaluate the models under various configurations. Results indicated that VADER outperformed the other models in both multi-class and binary sentiment classifications. The study highlights significant changes in sentiment trends pre- and post-COVID-19, with implications for import policies.
Nowadays, it is urgent to produce in larger quantities and more sustainably to reduce the gap between food supply and demand. In a circular bioeconomy vision, insects receive great attention as a sustainable alternative to satisfy food and nutritional needs. Among all insects, Tenebrio molitor (TM) is the first insect approved by the European Food Safety Authority as a novel food in specific conditions and uses, testifying its growing relevance and potential. This review holistically presents the possible role of TM in the sustainable and circular solution to the growing needs for food and nutrients. We analyze all high value-added products obtained from TM (powders and extracts, oils and fatty acids, proteins and peptides, and chitin and chitosan), their recovery processes (evaluating the best ones in technical and environmental terms), their nutritional and economical values, and their biological effects. Safety aspects are also mentioned. TM potential is undoubted, but some aspects still need to be discussed, including the health effects of substances and microorganisms in its body, the optimal production conditions (that affect product quality and safety), and TM capacity to convert by-products into new products. Environmental, economic, social, and market feasibility studies are also required to analyze the new value chains. Finally, to unlock the enormous potential of edible insects as a source of nutritious and sustainable food, it will be necessary to overcome the cultural, psychological, and regulatory barriers still present in Western countries.
Robert T. da Paixão, Edenio Detmann, Marcos I. Marcondes
et al.
The objective of this paper is to evaluate the effects of creep feeding supplementation during the preweaning phase on the growth performance and metabolic characteristics of Nellore heifers. Forty-two female Nellore calves (age = 100 ± 25 d; initial body weight (BW) = 113.4 ± 16.6 kg) were randomly assigned to the following treatments: control, where calves received mineral mix supplementation (<i>n</i> = 21); supplemented in creep feeding, where calves received 6 g/kg BW of a concentrate supplement (<i>n</i> = 21) during a period of 140 d. In the postweaning phase, all heifers received 6 g/kg BW of a concentrate supplement during a period of 210 d. Supplemented heifers had a greater average daily gain (ADG) than control heifers during the preweaning phase and, consequently, were heavier at weaning and at the end of the growing phase (<i>p</i> < 0.05). However, preweaning supplementation did not influence (<i>p</i> > 0.05) the body measurements or BW at the end of the growing period. Greater (<i>p</i> < 0.05) rib fat was observed in supplemented heifers. Concentrations of metabolites were not affected by preweaning supplementation (<i>p</i> > 0.05). Thus, supplementing heifers in the preweaning phase improved growth performance of weaning and body adiposity.