Payel Dhar, B. Jose Ravindra Raj, Amayappanallur Kannan Dasarathy
et al.
ABSTRACT The rapid growth of agri‐food industries has led to an alarming increase in waste generation, posing environmental, economic, and sustainability challenges. This review explores recent advancements in the valorization of agri‐food by‐products into value‐added products through green extraction and biorefinery technologies. It emphasizes the recovery of bioactive compounds such as polyphenols, flavonoids, carotenoids, and dietary fibers from fruit, vegetable, dairy, meat, and seafood wastes, highlighting their potential applications in the food, pharmaceutical, cosmetic, and bioenergy sectors. Emerging eco‐friendly extraction techniques—including supercritical and subcritical fluid extraction, enzyme‐assisted extraction, microwave‐ and ultrasound‐assisted methods, and pulsed electric field processing—offer improved yield, purity, and energy efficiency while reducing ecological impact. Despite technological progress, large‐scale adoption remains constrained by high costs, lack of standardization, and limited industrial integration. Key research gaps include the need for techno‐economic assessments, solvent recovery strategies, and life‐cycle evaluations to ensure process scalability and sustainability. Future research should focus on developing hybrid extraction systems, AI‐driven process optimization, and pilot‐scale biorefineries supported by robust policy frameworks and industry–academia collaboration. Overall, agri‐food waste valorization presents a viable pathway toward achieving environmental sustainability and circular bioeconomy goals, enabling a transition from waste‐intensive practices to resource‐efficient and climate‐resilient production systems.
ABSTRACT: The emergence of methicillin-resistant Staphylococcus aureus (MRSA) and its robust biofilm-forming capability pose severe threats to public health, livestock production, and food safety, and underscores the urgent need for novel antibacterial and anti-biofilm agents. In this study, we identified and characterized a novel bacteriocin, PFB252, derived from Bacillus velezensis through a multistep purification process involving acid precipitation, TA-GF75 gel column chromatography, Tiderose Q HP anion-exchange chromatography (TRUKING, Changsha, China), and reversed-phase HPLC. PFB252 exhibited remarkable thermal stability, pH tolerance, and resistance to enzymatic degradation, and demonstrated potent antibacterial activity against MRSA. At subinhibitory concentrations (1/32× minimum inhibitory concentration [MIC] and 1/16× MIC), PFB252 significantly disrupted biofilm formation and impaired the metabolic viability of embedded bacteria, and it drastically reduced extracellular polysaccharide, the key component of the biofilm matrix. Transcriptional analysis further revealed that PFB252 at subinhibitory concentrations downregulated critical biofilm-associated genes. PFB252 exhibited strong antimicrobial efficacy in dairy applications and could reduce MRSA counts in milk from 103 to <10 cfu/mL within 4 d at MIC and maintain suppression in cheese below 102 cfu/g over 7 d. These properties highlight PFB252's potential as a natural biopreservative for combating MRSA in food systems and offer a promising solution for food safety applications.
Dairy farming is an energy intensive sector that relies heavily on grid electricity. With increasing renewable energy integration, sustainable energy management has become essential for reducing grid dependence and supporting the United Nations Sustainable Development Goal 7 on affordable and clean energy. However, the intermittent nature of renewables poses challenges in balancing supply and demand in real time. Intelligent load scheduling is therefore crucial to minimize operational costs while maintaining reliability. Reinforcement Learning has shown promise in improving energy efficiency and reducing costs. However, most RL-based scheduling methods assume complete knowledge of future prices or generation, which is unrealistic in dynamic environments. Moreover, standard PPO variants rely on fixed clipping or KL divergence thresholds, often leading to unstable training under variable tariffs. To address these challenges, this study proposes a Deep Reinforcement Learning framework for efficient load scheduling in dairy farms, focusing on battery storage and water heating under realistic operational constraints. The proposed Forecast Aware PPO incorporates short term forecasts of demand and renewable generation using hour of day and month based residual calibration, while the PID KL PPO variant employs a proportional integral derivative controller to regulate KL divergence for stable policy updates adaptively. Trained on real world dairy farm data, the method achieves up to 1% lower electricity cost than PPO, 4.8% than DQN, and 1.5% than SAC. For battery scheduling, PPO reduces grid imports by 13.1%, demonstrating scalability and effectiveness for sustainable energy management in modern dairy farming.
Abstract Machine learning (ML) technology is a powerful tool in food science and engineering offering numerous advantages, from recognizing patterns and predicting outcomes to customizing and adjusting to individual needs. Its further development can enable researchers and industries to significantly enhance the efficiency of dairy processing while providing valuable insights into the field. This paper presents an overview of the role of machine learning in the dairy industry and its potential to improve the efficiency of dairy processing. We performed a systematic search for articles published between January 2003 and January 2023 related to machine learning in dairy products and highlighted the algorithms used. 48 studies are discussed to assist researchers in identifying the best methods that could be applied in their field and providing relevant ideas for future research directions. Moreover, a step-by-step guide to the machine learning process, including a classification of different machine learning algorithms, is provided. This review focuses on state-of-the-art machine learning applications in milk products and their transformation into other dairy products, but it also presents future perspectives and conclusions. The study serves as a valuable guide for individuals in the dairy industry interested in learning about or getting involved with ML.
Raw milk typically has little bacterial contamination as it leaves the udder of the animal; however, through a variety of pathways, it can become contaminated with bacteria originating from environmental sources, the cow herself, and contact with contaminated equipment. Although the types of bacteria found in raw milk are very diverse, select groups are particularly important from the perspective of finished product quality. In particular, psychrophilic and psychrotolerant bacteria that grow quickly at low temperatures (e.g., species in the genus Pseudomonas and the family Enterobacteriaceae) and produce heat-stable enzymes, and sporeforming bacteria that survive processing hurdles in spore form, are the 2 primary groups of bacteria related to effects on processed dairy products. Understanding factors leading to the presence of these important bacterial groups in raw milk is key to reducing their influence on processed dairy product quality. Here we examine the raw milk microbiological parameters used in the contemporary dairy industry for their utility in identifying raw milk supplies that will perform well in processed dairy products. We further recommend the use of a single microbiological indicator of raw milk quality, namely the total bacteria count, and call for the development of a whole-farm approach to raw milk quality that will use data-driven, risk-based tools integrated across the continuum from production to processing and shelf-life to ensure continuous improvement in dairy product quality.
Thermal and nonthermal methods are essential in ensuring the safety, quality, and extended shelf life of dairy products. Thermal processing involves the application of heat to destroy harmful microorganisms and extend the shelf life of dairy products, such as pasteurization and sterilization. Pasteurization is done to eliminate pathogens while preserving the taste and nutritional value. Whereas sterilization requires applying higher temperatures, ensuring the destruction of all microorganisms, and allowing for a long shelf life without refrigeration. Nonthermal processing, which preserves nutritional and sensory qualities without significant heat, includes techniques like high-pressure processing, ultraviolet treatment, microfiltration, pulsed electric field processing, and ultrasound processing. Both methods, with their own advantages, find their applications within the dairy industry for maintaining the safety, quality, and longevity of dairy products.
C.L. van Zyl, H.K. Eriksson, E.A.M. Bokkers
et al.
ABSTRACT: In cow-calf contact (CCC) systems breaking the maternal bond may induce stress for the cow, thereby affecting feed intake, milk yield, milk flow rate, and milk electrical conductivity. This study aimed to determine the consequences of weaning and separation strategies in CCC systems for feed intake and milking characteristics of the cow. In 2 experiments, Swedish Holstein and Swedish Red cows either had (experiment 1) whole-day CCC (CCC1, n = 12) for 8.5 ± 1.2 wk (mean ± SD) followed by 12 h of daytime CCC for 8 wk, before abrupt weaning and separation at 16.4 ± 1.2 wk, or (experiment 2) whole-day CCC for 16 ± 1.0 wk; thereafter half of the calves were weaned via nose flaps for 2 wk (NF, n = 10) before physical separation and half via nose flaps for 1 wk and fence-line contact for 1 wk (NFFL, n = 9). Cows were compared with conventionally managed cows (CONV1 or CONV2 in experiment 1 or 2) separated from their calves within 12 h postpartum. In experiment 1, the study period included the week before and after the system switch from whole-day to daytime CCC, and the week before and after separation. In experiment 2, the study period included the week before the start of weaning, during weaning, and 1 week after separation. All cows were milked in the same automatic milking unit. In experiment 1, feed intake of CCC1 cows at separation tended to be lower than CONV1 cows. In experiment 2, roughage intake of NF, NFFL, and CONV2 cows did not differ, but the concentrate intake of NF cows was lower than that of CONV2 cows. In experiment 1, the system switch did not affect milking characteristics. However, after separation, machine milk yield and milk electrical conductivity of CCC1 cows increased, remaining lower than CONV1 cows. In experiment 2, machine milk yield of NF and NFFL cows increased when calves were fitted with nose flaps, but remained lower than CONV2 cows. In the week after separation, milk yield of NFFL cows was similar to that of CONV2 cows, and the NF cows remained lower. In the week before weaning, milk flow rates of NF cows were lower than those of CONV2 cows, and the NFFL cows did not differ. Before weaning, milk electrical conductivity of NF and NFFL cows was lower than that of CONV2 cows, but not thereafter. In conclusion, machine milk yield of CCC cows remained lower either until the week of separation, for NFFL cows, or until 3 or 11 wk after weaning and separation for CCC1 and NF cows of experiments 1 and 2, respectively. Cow-calf contact reduced milk electrical conductivity, and milk and peak milk flow rates increased the week after separation of cow and calf. Not for experiment 2, but for experiment 1, cow roughage and concentrate intake decreased at separation and recovered within a week, indicating that abrupt separation exerted a greater impact on the cow than separation after nose flap weaning or fence-line contact. Future studies should compare both weaning strategies within the same experimental setup, also focusing on the consequences for calves.
ABSTRACT: There is currently a lack of research examining the association between the consumption of different dairy products and type 2 diabetes (T2D) in East Asian populations. To address this gap, the present study employs Mendelian randomization to investigate the potential effects of 3 different types of milk consumption (including whole milk, semi-skim milk, and skim milk) on the risk of developing T2D. The results indicate that both whole milk and skim milk are associated with an increased risk of T2D (whole milk: odds ratio [OR] = 1.022, 95% CI: 1.001–1.044; skim milk: OR = 1.023, 95% CI: 1.007–1.039). Mediation analysis revealed that asparagine acts as a mediator between skim milk consumption and T2D, with a mediation effect of 0.003 (95% CI: 0.000 to 0.008), accounting for 14.269% of the total effect.
L.A. Jiménez-Maroto, S. Govindasamy-Lucey, J.J. Jaeggi
et al.
ABSTRACT: High-pressure processing (HPP) and low-temperature storage (0°C) were explored as alternatives to freezing for extending the performance shelf life of low-moisture, part-skim (LMPS) mozzarella intended for export. Batches (n = 5) of reduced Na LMPS mozzarella were manufactured using camel chymosin as a lower proteolytic type of rennet. Cheeses were stored for 2 wk at 4°C, divided into control (non-HPP) and HPP (600 MPa for 3 min) groups, and stored at 3 different temperatures (4, 0, and −18°C) for 365 d. Analyses were performed at 0, 90, 150, 210, 270, and 365 d of storage. Frozen and 0°C samples (∼2.3 kg) were thawed/tempered at 4°C for 1 wk before analysis. Urea PAGE and quantification of the pH 4.6 soluble N over time were used to monitor primary proteolysis. Body and rheological properties were monitored using texture profile analysis (TPA) and dynamic low-amplitude oscillatory rheology. Changes in flavor, body, shred properties, and pizza performance were evaluated using quantitative descriptive analysis with 12 trained panelists using a 15-point scale. High-pressure processing treatment caused ∼5 log cfu/mL reduction in starter counts, partial solubilization of the insoluble Ca, and a small pH increase (from ∼5.2 to 5.3). The rate of primary proteolysis was reduced by HPP and low-temperature storage. High-pressure processing treatment reduced initial cheese hardness, but no further significant decrease was observed over storage time, whereas the hardness of non-HPP samples decreased over the 365 d of storage, apart from the frozen samples. In pizza applications, blister quantity development and loss of strand thickness were limited by storage at −18°C. Freezing LMPS mozzarella to −18°C gave the least changes in proteolysis and pizza performance over the 365 d of study, storage of cheese at 0°C slowed the loss of hardness and the deterioration of pizza performance attributes. The combination of HPP and 0°C storage of cheese resulted in little change in blistering quantity of pizza during the 365 d of study, whereas cheese stored at 0°C had blisters covering much of the pizza after this extended storage time. Combining HPP with low-temperature storage is a promising alternative approach to freezing for the extension of the functionality shelf life of LMPS mozzarella.
Mian Ibad Ali Shah, Marcos Eduardo Cruz Victorio, Maeve Duffy
et al.
The integration of renewable energy resources in rural areas, such as dairy farming communities, enables decentralized energy management through Peer-to-Peer (P2P) energy trading. This research highlights the role of P2P trading in efficient energy distribution and its synergy with advanced optimization techniques. While traditional rule-based methods perform well under stable conditions, they struggle in dynamic environments. To address this, Multi-Agent Reinforcement Learning (MARL), specifically Proximal Policy Optimization (PPO) and Deep Q-Networks (DQN), is combined with community/distributed P2P trading mechanisms. By incorporating auction-based market clearing, a price advisor agent, and load and battery management, the approach achieves significant improvements. Results show that, compared to baseline models, DQN reduces electricity costs by 14.2% in Ireland and 5.16% in Finland, while increasing electricity revenue by 7.24% and 12.73%, respectively. PPO achieves the lowest peak hour demand, reducing it by 55.5% in Ireland, while DQN reduces peak hour demand by 50.0% in Ireland and 27.02% in Finland. These improvements are attributed to both MARL algorithms and P2P energy trading, which together results in electricity cost and peak hour demand reduction, and increase electricity selling revenue. This study highlights the complementary strengths of DQN, PPO, and P2P trading in achieving efficient, adaptable, and sustainable energy management in rural communities.
Padmanabhan Jagannathan Prajesh, Kaliaperumal Ragunath, Miriam Gordon
et al.
Methane (CH4) emissions from dairy farming are a significant but under-quantified component of agricultural greenhouse gases. This study provides a satellite-based assessment of dairy-specific methane emissions across Canada using high-resolution Sentinel-5P TROPOMI data. By integrating spatial clustering of 1,701 dairy farms and processors, a quasi-experimental design with paired non-dairy reference regions, and seasonal pattern decomposition, we analyzed national and regional spatiotemporal emission trends. Results show persistently higher methane levels in dairy regions (mean difference: 16.99 ppb), with consistent fall-winter peaks. Notably, the dairy-specific methane anomaly, defined as the concentration difference between dairy and non-dairy regions declined by 62.25% from 2019 to 2024, with a sharp drop during 2022-2023 (-41.11%). Meanwhile, national methane levels rose by 3.83%, with increasing spatial heterogeneity across provinces. An inverse relationship between baseline methane levels and growth rates suggests a convergence effect. Seasonal analysis revealed universal spring minima and fall-winter maxima, offering distinct temporal signatures for source attribution. This study demonstrates the value of satellite-based monitoring for policy-relevant methane assessments and introduces a scalable framework applicable to other regions. The observed narrowing of dairy methane anomaly indicates evolving emission dynamics, potentially reflecting rising baseline methane rather than a definitive reduction in dairy source emissions. This highlights the need for integrated satellite and ground-based approaches to enhance understanding and guide mitigation efforts.
This paper examines the views of software providers in the German dairy industry with regard to dairy farmers' needs for explanation of digital decision support systems. The study is based on mastitis detection in dairy cows using a hypothetical herd management system. We designed four exemplary explanation formats for mastitis assessments with different types of presentation (textual, rule-based, herd comparison, and time series). In our previous study, 14 dairy farmers in Germany had rated these formats in terms of comprehensibility and the trust they would have in a system providing each format. In this study, we repeat the survey with 13 software providers active in the German dairy industry. We ask them how well they think the formats would be received by farmers. We hypothesized that there may be discrepancies between the views of both groups that are worth investigating, partly to find reasons for the reluctance to adopt digital systems. A comparison of the feedback from both groups supports the hypothesis and calls for further investigation. The results show that software providers tend to make assumptions about farmers' preferences that are not necessarily accurate. Our study, although not representative due to the small sample size, highlights the potential benefits of a thorough user requirements analysis (farmers' needs) to improve software adaptation and user acceptance.
Celia Julliot, Gabriel M. Dallago, Amir Nejati
et al.
Detecting walking pattern abnormalities in dairy cows early on holds the potential to reduce the occurrence of clinical lameness. This study aimed to predict gait scores in non-clinically lame dairy cows by using gait attributes based on kinematic data. Markers were placed on 20 anatomical landmarks on 12 dairy cows. The cows were walked multiple times through a corridor while recorded by six cameras, representing 69 passages. Specific gait attributes were computed from the 3D coordinates of the hoof markers. Gait was visually assessed using a 5-point numerical rating system (NRS). Due to the limited number of observations with NRS lower than 2 (n = 1) and higher than 3 (n = 6), the NRS labels were combined into three groups, representing NRS <= 2, NRS = 2.5, and NRS >= 3. The dataset was split into training and testing sets (70:30 ratio), stratified by the distribution of the NRS categories. Random forest (RF), gradient boosting machine (GBM), extreme gradient boosting machine (XGBM), and support vector machine (SVM) with a radial basis kernel models were trained using k-fold repeated cross-validation with hyperparameters defined using a Bayesian optimization. Accuracy, sensitivity, specificity, F1 score, and balanced accuracy were calculated to measure model performance. The GBM model performed best, achieving an overall accuracy and F1 score of 0.65 in the testing set. The findings of this study contribute to the development of an automated monitoring system for early identification of gait abnormalities, thereby enhancing the welfare and longevity of dairy cows.
Dairy farmers should decide to keep or cull a cow based on an objective assessment of her likely performance in the herd. For this purpose, farmers need to identify more resilient cows, which can cope better with farm conditions and complete more lactations. This decision-making process is inherently complex, with significant environmental and economic implications. In this study, we develop an AI-driven model to predict cow longevity using historical multivariate time-series data recorded from birth. Leveraging advanced AI techniques, specifically Multi-Head Attention Transformers, we analysed approximately 780,000 records from 19,000 unique cows across 7 farms in Australia. The results demonstrate that our model achieves an overall determination coefficient of 83% in predicting herd life across the studied farms, highlighting its potential for practical application in dairy herd management.
In recent years, the demand for reduced-fat dairy products (RFDPs) has increased rapidly as the health risks associated with high-fat diets have become increasingly apparent. Unfortunately, lowering the fat content in dairy products would reduce the flavor perception of fat. Fat-derived flavor compounds are the main contributor to appealing flavor among dairy products. However, the contribution of fat-derived flavor compounds remains underappreciated among the flavor improvement factors of RFDPs. Therefore, this review aims to summarize the flavor perception mechanism of fat and the profile of fat-derived flavor compounds in dairy products. Furthermore, the characteristics and influencing factors of flavor compound release are discussed. Based on the role of these flavor compounds, this review analyzed the current and potential flavor improvement strategies for RFDPs, including physical processing, lipolysis, microbial applications, and fat replacement. Overall, promoting the synthesis of milk fat characteristic flavor compounds in RFDPs and aligning the release properties of flavor compounds from the RFDPs with those of equivalent full-fat dairy products are two core strategies to improve the flavor of reduced-fat dairy products. In the future, better modulation of the behavior of flavor compounds by various methods is promising to replicate the flavor properties of fat in RFDPs and meet consumer sensory demands.
Advanced glycosylation end products (AGEs) are a series of complex compounds which generate in the advanced phase of Maillard reaction, which can pose a non-negligible risk to human health. This article systematically encompasses AGEs in milk and dairy products under different processing conditions, influencing factors, inhibition mechanism and levels among the different categories of dairy products. In particular, it describes the effects of various sterilization techniques on the Maillard reaction. Different processing techniques have a significant effect on AGEs content. In addition, it clearly articulates the determination methods of AGEs and even discusses its immunometabolism via gut microbiota. It is observed that the metabolism of AGEs can affect the composition of the gut microbiota, which further has an impact on intestinal function and the gut-brain axis. This research also provides a suggestion for AGEs mitigation strategies, which are beneficial to optimize the dairy production, especially innovative processing technology application.
Cleaning-in-place (CIP) is the most commonly used cleaning and sanitation system for processing lines, equipment, and storage facilities such as milk silos in the global dairy processing industry. CIP employs thermal treatments and nonbiodegradable chemicals (acids and alkalis), requiring appropriate neutralization before disposal, resulting in sustainability challenges. In addition, biofilms are a major source of contamination and spoilage in dairy industries, and it is believed that current chemical CIP protocols do not entirely destroy biofilms. Use of enzymes as effective agents for CIP and as a more sustainable alternative to chemicals and thermal treatments is gaining interest. Enzymes offer several advantages when used for CIP, such as reduced water usage (less rinsing), lower operating temperatures resulting in energy savings, shorter cleaning times, and lower costs for wastewater treatment. Additionally, they are typically derived from natural sources, are easy to neutralize, and do not produce hazardous waste products. However, even with such advantages, enzymes for CIP within the dairy processing industry remain focused mainly on membrane cleaning. Greater adoption of enzyme-based CIP for cheese industries is projected pending a greater knowledge relating to cost, control of the process (inactivation kinetics), reusability of enzyme solutions, and the potential for residual activity, including possible effects on the subsequent product batches. Such studies are essential for the cheese industry to move toward more energy-efficient and sustainable cleaning solutions.
Francesca Vurro, Davide De Angelis, Giacomo Squeo
et al.
Lentils are marketed as dry seeds, fresh sprouts, flours, protein isolates, and concentrates used as ingredients in many traditional and innovative food products, including dairy and meat analogs. Appreciated for their nutritional and health benefits, lentil ingredients and food products may be affected by off-flavor notes described as “beany”, “green”, and “grassy”, which can limit consumer acceptance. This narrative review delves into the volatile profiles of lentil ingredients and possible de-flavoring strategies, focusing on their effectiveness. Assuming that appropriate storage and processing are conducted, so as to prevent or limit undesired oxidative phenomena, several treatments are available: thermal (pre-cooking, roasting, and drying), non-thermal (high-pressure processing, alcohol washing, pH variation, and addition of adsorbents), and biotechnological (germination and fermentation), all of which are able to reduce the beany flavor. It appears that lentil is less studied than other legumes and more research should be conducted. Innovative technologies with great potential, such as high-pressure processing or the use of adsorbents, have been not been explored in detail or are still totally unexplored for lentil. In parallel, the development of lentil varieties with a low LOX and lipid content, as is currently in progress for soybean and pea, would significantly reduce off-flavor notes.