Evaluation of a decision support system for precision feeding of gestating sows

Importance of Selected Nutrients and Additives in the Feed of Pregnant Sows for the Survival of Newborn Piglets

This systematic review analyzed the effect of selected nutrients and additives in the feed of pregnant sows on the survival of newborn piglets. We analyzed 720 peer-reviewed publications in English in PubMed® and Web of Science®, dated July 2023 to January 2024, related to the effect of dietary supplementation with fatty acids and various percentages of protein, amino acids, and/or sources of dietary fiber on the offspring of gestating sows. While several papers evaluated the effect of nutrition on gestating sows, only a few delved into the distinct feeding strategies required at each stage of gestation to meet the NRC's nutritional requirements for maternal tissue gain and postnatal neonatal survival and growth. This body of research suggests that as gestation progresses the sow's nutritional requirements increase, as the NRC established, to satisfy their own metabolic needs and those of their fetuses. Additional research is needed to determine an optimal feeding strategy.

On farm precision feeding of gestating sows based on energy and amino acids on farrowing performances and feeding behavior over 3 consecutive gestations

Gestating sows are often fed a single diet throughout their gestation cycle, leading to situations of nutrients deficiency or excess at the individual level. The purpose of this study was to characterize, over 3 consecutive cycles, the impact of a precision feeding (PF), i.e., dietary supplies adjusted at individual level in terms of quantity (energy intake) and quality (standardized ileal digestible (SID) lysine (Lys) intake), on gestating sows' productive performance, feeding behavior, environmental outputs, and health status compared with sows fed a conventional feeding (CF, i.e., fixed SID Lys intake). At the start of the trial, 2 batches of 20 Landrace × Large White gestating sows were allocated to one of the 2 feeding strategies (PF vs. CF), based on their parity (1, 2, or 3 and more), body weight, and backfat thickness (BT) 3 days after insemination. The PF strategy consisted in mixing with automatic feeders 2 iso-energetic diets (9.8 MJ/kg of net energy with 3.3 and 8.5 g SID Lys/kg, respectively) in variable proportions at individual and daily levels, whereas for the CF strategy these proportions remained constant throughout gestation (73% and 27%, respectively, resulting in an SID Lys concentration of 4.7 g/kg). Sows were followed over 3 consecutive gestations and the sows remained allocated to the same strategy throughout the study. Some sows were culled before the end of the study and were replaced by other sows who therefore performed only 1 or 2 gestations during the study. Thus, 106 gestations and lactations from 51 sows were fully studied and their data analyzed. The PF strategy allowed the sows to reach more closely the expected BT values at farrowing across cycles than the CF strategy (P < 0.001). The PF sows consumed 16% less SID Lys per gestation than the CF sows (P < 0.001), resulting in a 4% improvement in N efficiency (P < 0.001), with no impact on performance at farrowing (P > 0.10). The sows consumed their daily ration in a single visit whatever the feeding strategy (P = 0.41), but CF sows spent more time in the feeder in cycles 2 and 3 (P < 0.001). Thus, compared to the CF strategy implemented by farmers, the individual and daily nutritional supplies implemented with the PF strategy were more efficient in enabling sows to achieve body condition objectives at farrowing over the long term, also with a reduced SID Lys intake and an improved N efficiency without negative impact on farrowing performances.

Dietary supplementation with lysine (protein) in late pregnancy does not enhance mammary development in multiparous sows

This project was conducted to determine if providing standardized ileal digestible (SID) Lys at 40% above estimated requirements (NRC, 2012), with the concomitant increased protein intake, from days 90 to 110 of gestation stimulates mammary development in multiparous sows. From day 90 of gestation, Yorkshire × Landrace multiparous sows (parities 2 and 3) were fed 2.6 kg/d of either a conventional diet (CTL, control, n = 17) providing 14.8 g/d of SID Lys or a diet providing 20.8 g/d of SID Lys via additional soybean meal (HILYS, n = 16). The diets were isoenergetic. Concentrations of IGF-1, glucose, free fatty acids (FFA), urea, and amino acids (AA) were measured in jugular blood samples obtained on days 90 and 110 of gestation. Sows were necropsied on day 110 ± 1 of gestation to obtain mammary glands for compositional and histological analyses. Backfat or BW changes of sows during late gestation were unaffected by treatment (P > 0.10), as was the case for fetal BW (P > 0.10). None of the variables measured in mammary tissue were altered by supplementary Lys (P > 0.10). Circulating IGF-1, glucose, and FFA did not differ (P > 0.10) between HILYS and CTL sows on day 110 of gestation, whereas concentrations of urea were greater (P < 0.01) in HILYS versus CTL gilts. Concentrations of Ile and Thr in plasma were also greater (P < 0.05), and those of Glu were lower (P < 0.01) in HILYS than CTL sows. These results demonstrate that feeding Lys (via protein) above current NRC recommendations during late gestation does not improve mammary development of multiparous sows. Hence, the use of a two-phase feeding strategy to provide more Lys (protein) to multiparous sows during this period is not necessary.

Prediction of the daily nutrient requirements of gestating sows based on sensor data and machine-learning algorithms

Precision feeding is a strategy for supplying an amount and composition of feed as close that are as possible to each animal's nutrient requirements, with the aim of reducing feed costs and environmental losses. Usually, the nutrient requirements of gestating sows are provided by a nutrition model that requires input data such as sow and herd characteristics, but also an estimation of future farrowing performances. New sensors and automatons, such as automatic feeders and drinkers, have been developed on pig farms over the last decade, and have produced large amounts of data. This study evaluated machine-learning methods for predicting the daily nutrient requirements of gestating sows, based only on sensor data, according to various configurations of digital farms. The data of 73 gestating sows was recorded using sensors such as electronic feeders and drinker stations, connected weight scales, accelerometers, and cameras. Nine machine-learning algorithms were trained on various dataset scenarios according to different digital farm configurations (one or two sensors), to predict the daily metabolizable energy and standardized ileal digestible lysine requirements for each sow. The prediction results were compared to those predicted by the InraPorc model, a mechanistic model for the precision feeding of gestating sows. The scenario predictions were also evaluated with or without the housing conditions and sow characteristics at artificial insemination usually integrated into the InraPorc model. Adding housing and sow characteristics to sensor data improved the mean average percentage error by 5.58% for lysine and by 2.22% for energy. The higher correlation coefficient values for lysine (0.99) and for energy (0.95) were obtained for scenarios involving an automatic feeder system (daily duration and number of visits with or without consumption) only. The scenarios including an automatic feeder combined with another sensor gave good performance results. For the scenarios using sow and housing characteristics and automatic feeder only, the root mean square error was lower with gradient tree boosting (0.91 MJ/d for energy and 0.08 g/d for lysine) compared with those obtained using linear regression (2.75 MJ/d and 1.07 g/d). The results of this study show that the daily nutrient requirements of gestating sows can be predicted accurately using data provided by sensors and machine-learning methods. It paves the way for simpler solutions for precision feeding.

Effects of thermal conditions on gestating sows' behaviors and energy requirements

Room temperature and individual behavior may influence the energy requirements of gestating sows. These factors are not yet integrated on a daily and individual basis in the calculation of these requirements. The objective of this study was to quantify the effect of temperatures on the sows' behaviors, especially on the level of physical activity, and on the energy requirements of gestating sows. Over four consecutive weeks, the temperature of two gestation rooms was maintained at medium temperatures (16.7 °C and 18.5 °C, respectively, for room 1 and room 2) for the first and third week, at low temperatures (14.4 °C and 15.3 °C) for the second week, and at high temperatures (31.6 °C and 31.9 °C) for the fourth week. Individual behavior was manually recorded based on videos and the data used to estimate the physical activity and social interactions of 37 gestating sows separated into two groups. The videos were analyzed over two periods of 5 h ("Feeding period" from 2300 to 0400 hours, "Resting period" from 1330 to 1830 hours). The energy requirements were calculated by the InraPorc model, modified for gestating sows, on the basis of a thermo-neutral situation and an average activity of 4 h standing per day for all the sows. The sows of one group were less active in high than low temperatures (83 vs. 103 min standing or walking over 5 h, P < 0.001). Isolation for high temperatures or huddling for low temperatures could be observed when sows were lying down. The sows spent more time lying laterally with high temperatures than low temperatures (66% vs. 52% of time spent lying, respectively, P < 0.001). Both groups reacted differently to high temperatures, in one the sows changed their activity (lying more) whereas in the other they drank more water compared to medium temperatures (11 vs. 8.5 L/d, P = 0.01). In one group, with high temperatures the sows were fed above their requirements (they should have received 110 g of feed per day per sow less, P < 0.001) and with low temperatures the same group should have received 50 g/d per sow more to fulfill their requirements. For the second group of sows, the temperatures did not significantly affect the feed requirements. In conclusion, daily ambient temperature and individual physical activity seem to be relevant information to add in nutritional models to improve precision feeding.

Precision feeding of lactating sows: implementation and evaluation of a decision support system in farm conditions

Precision feeding (PF) aims to provide the right amount of nutrients at the right time for each animal. Lactating sows generally receive the same diet, which either results in insufficient supply and body reserve mobilization, or excessive supply and high nutrient excretion. With the help of online measuring devices, computational methods, and smart feeders, we introduced the first PF decision support system (DSS) for lactating sows. Precision (PRE) and conventional (STD) feeding strategies were compared in commercial conditions. Every day each PRE sow received a tailored ration that had been computed by the DSS. This ration was obtained by blending a diet with a high AA and mineral content (13.00 g/kg SID Lys, 4.50 g/kg digestible P) and a diet low in AAs and minerals (6.50 g/kg SID Lys, 2.90 g/kg digestible P). All STD sows received a conventional diet (10.08 g/kg SID Lys, 3.78 g/kg digestible P). Before the trial, the DSS was fitted to farm performance for the prediction of piglet average daily gain (PADG) and sow daily feed intake (DFI), with data from 1,691 and 3,712 lactations, respectively. Sow and litter performance were analyzed for the effect of feeding strategy with ANOVA, with results considered statistically significant when P < 0.05. The experiment involved 239 PRE and 240 STD sows. DFI was similarly high in both treatments (PRE: 6.59, STD: 6.45 kg/d; P = 0.11). Litter growth was high (PRE: 2.96, STD: 3.06 kg/d), although it decreased slightly by about 3% in PRE compared to STD treatments (P < 0.05). Sow body weight loss was low, although it was slightly higher in PRE sows (7.7 vs. 2.1 kg, P < 0.001), which might be due to insufficient AA supply in some sows. Weaning to estrus interval (5.6 d) did not differ. In PRE sows SID Lys intake (PRE: 7.7, STD: 10.0 g/kg; P < 0.001) and digestible P intake (PRE: 3.2, STD: 3.8 g/kg; P < 0.001) declined by 23% and 14%, respectively, and feed cost decreased by 12%. For PRE sows, excretion of N and P decreased by 28% and 42%, respectively. According to these results, PF appears to be a very promising strategy for lactating sows.

ASAS-NANP symposium: mathematical modeling in animal nutrition: limitations and potential next steps for modeling and modelers in the animal sciences

The field of animal science, and especially animal nutrition, relies heavily on modeling to accomplish its day-to-day objectives. New data streams ("big data") and the exponential increase in computing power have allowed the appearance of "new" modeling methodologies, under the umbrella of artificial intelligence (AI). However, many of these modeling methodologies have been around for decades. According to Gartner, technological innovation follows five distinct phases: technology trigger, peak of inflated expectations, trough of disillusionment, slope of enlightenment, and plateau of productivity. The appearance of AI certainly elicited much hype within agriculture leading to overpromised plug-and-play solutions in a field heavily dependent on custom solutions. The threat of failure can become real when advertising a disruptive innovation as sustainable. This does not mean that we need to abandon AI models. What is most necessary is to demystify the field and place a lesser emphasis on the technology and more on business application. As AI becomes increasingly more powerful and applications start to diverge, new research fields are introduced, and opportunities arise to combine "old" and "new" modeling technologies into hybrids. However, sustainable application is still many years away, and companies and universities alike do well to remain at the forefront. This requires investment in hardware, software, and analytical talent. It also requires a strong connection to the outside world to test, that which does, and does not work in practice and a close view of when the field of agriculture is ready to take its next big steps. Other research fields, such as engineering and automotive, have shown that the application power of AI can be far reaching but only if a realistic view of models as whole is maintained. In this review, we share our view on the current and future limitations of modeling and potential next steps for modelers in the animal sciences. First, we discuss the inherent dependencies and limitations of modeling as a human process. Then, we highlight how models, fueled by AI, can play an enhanced sustainable role in the animal sciences ecosystem. Lastly, we provide recommendations for future animal scientists on how to support themselves, the farmers, and their field, considering the opportunities and challenges the technological innovation brings.

ASAS-NANP SYMPOSIUM: MATHEMATICAL MODELING IN ANIMAL NUTRITION: Opportunities and Challenges of Confined and Extensive Precision Livestock Production

Modern animal scientists, industry, and managers have never faced a more complex world. Precision livestock technologies have altered management in confined operations to meet production, environmental, and consumer goals. Applications of precision technologies have been limited in extensive systems such as rangelands due to lack of infrastructure, electrical power, communication, and durability. However, advancements in technology have helped to overcome many of these challenges. Investment in precision technologies is growing within the livestock sector, requiring the need to assess opportunities and challenges associated with implementation to enhance livestock production systems. In this review, precision livestock farming and digital livestock farming are explained in the context of a logical and iterative five-step process to successfully integrate precision livestock measurement and management tools, emphasizing the need for precision system models (PSMs). This five-step process acts as a guide to realize anticipated benefits from precision technologies and avoid unintended consequences. Consequently, the synthesis of precision livestock and modeling examples and key case studies help highlight past challenges and current opportunities within confined and extensive systems. Successfully developing PSM requires appropriate model(s) selection that aligns with desired management goals and precision technology capabilities. Therefore, it is imperative to consider the entire system to ensure that precision technology integration achieves desired goals while remaining economically and managerially sustainable. Achieving long-term success using precision technology requires the next generation of animal scientists to obtain additional skills to keep up with the rapid pace of technology innovation. Building workforce capacity and synergistic relationships between research, industry, and managers will be critical. As the process of precision technology adoption continues in more challenging and harsh, extensive systems, it is likely that confined operations will benefit from required advances in precision technology and PSMs, ultimately strengthening the benefits from precision technology to achieve short- and long-term goals.

Dietary supplementation with lysine (protein) stimulates mammary development in late pregnant gilts

The goal of this project was to determine if standardized ileal digestible (SID) lysine provided at 40% above estimated requirements, with the concomitant increase in protein intake, from days 90 to 110 of gestation would stimulate mammary development in gilts. From day 90 of gestation, Yorkshire × Landrace gilts were fed 2.65 kg of either a conventional diet (CTL, control, n = 19) providing 18.6 g/d of SID Lys or a diet providing 26.0 g/d of SID Lys via additional soybean meal (HILYS, n = 19). Both diets were isoenergetic. Jugular blood samples obtained on days 90 and 110 of gestation were used to measure concentrations of insulin-like growth factor-1 (IGF-1), metabolites, and amino acids (AA). Gilts were necropsied on day 110 ± 1 of gestation to obtain mammary glands for compositional analyses, immunohistochemistry, and analysis of mRNA abundance for AA transporters and markers of cell proliferation and differentiation. The HILYS gilts gained more body weight (P < 0.01) during the experimental period compared with CTL gilts, and had greater fetal weights (1.29 vs. 1.21 ± 0.03 kg, P < 0.05). There was no difference in circulating IGF-1, glucose, or albumin (P > 0.10) between HILYS and CTL gilts on day 110 of gestation, whereas concentrations of urea and free fatty acids were greater (P < 0.01), and those of Trp and Ala were lower (P < 0.05), in HILYS than CTL gilts. The provision of lysine at 40% above estimated requirements increased total mammary parenchymal mass by 44%, as well as total parenchymal fat, protein, DNA, and RNA (P < 0.01). The mRNA abundance of ACACA was greater (P < 0.05) in HILYS than CTL gilts, while only the AA transporter SLC6A14 tended (P < 0.10) to be greater. Results demonstrate that providing dietary Lys above current National Research Council recommendations in late gestation increases mammary development in gilts. Results also indicate that Lys may have been limiting for protein retention. These data suggest that the use of a two-phase feeding strategy during gestation, whereby dietary Lys is increased from day 90, could benefit potential sow milk yield in the subsequent lactation.

The effects of precisely meeting estimated daily energy and lysine requirements for gestating sows over three consecutive pregnancies on sow reproductive and lactation performance

The objective of the current study was to determine the effects of precisely meeting estimated daily energy and Lys requirements for gestating sows over three consecutive pregnancies on sow reproductive and lactation performance. A total of 105 sows (initial reproductive cycle 1.4 ± 0.5) were randomly assigned to a precision (PF; n = 50) or control (CON; n = 55) feeding program between days 2 and 9 of gestation and housed in group-pens equipped with electronic sow feeders capable of blending two diets. The PF sows received unique daily blends of two isocaloric diets (2518 kcal/kg NE; 0.80% and 0.20% standardized ileal digestible [SID] Lys, respectively), whereas CON sows received a static blend throughout gestation to achieve 0.56% SID Lys. After weaning, sows were re-bred and entered the same feeding program as in the previous pregnancy for two subsequent pregnancy cycles (PF: n = 36; CON: n = 37; average reproductive cycle: 2.4 ± 0.5; PF: n = 25; CON: n = 24; average reproductive cycle: 3.5 ± 0.5). Sows on the PF program received 97%, 105%, and 118% (average over three pregnancy cycles) of dietary energy and 67%, 79%, and 106% of SID Lys intakes compared to CON between days 5 and 37, 38 and 72, and 73 and 108 of gestation, respectively. Estimated N (26.1%) retention did not differ between gestation feeding programs in any pregnancy, but excess N excretion was less (1617 vs. 1750 ± 54 g/sow; P < 0.01) for PF vs. CON sows. Regardless of pregnancy cycle, sows that received the PF program had greater ADG between days 38 and 72 (614 vs. 518 ± 63 g/d; P < 0.05) and between days 73 and 108 (719 vs. 618 ± 94 g/d; P = 0.063) of gestation, and greater loin depth gain between days 63 and 110 of gestation (0.7 vs. −1.1 ± 1.6 mm; P < 0.05), but BW (235.1 kg) and backfat (17.8 mm) and loin (70.5 mm) depths on day 110 of gestation did not differ. The number of piglets born alive, stillborn, and mummified, and litter birth weight (16.5 kg) did not differ in any pregnancy cycle, nor did piglet ADG during lactation (250 g/d) and piglet BW (6.7 kg) at weaning. Sows that received the PF program during gestation had lower ADFI during lactation (5.7 vs. 6.2 ± 0.2 kg; P < 0.01). Therefore, using feeding programs that precisely match estimated daily energy and Lys requirements for gestating sows provides the opportunity to reduce N losses to the environment and reduce lactation feed usage, without negatively affecting sow reproductive and lactation performance.

A Novel Estimation of Unobserved Pig Growth Traits for the Purposes of Precision Feeding Methods

Recent technological advances make it possible to deliver feeding strategies that can be tailored to the needs of individual pigs in order to optimise the allocation of nutrient resources and contribute toward reducing excess nutrient excretion. However, these efforts are currently hampered by the challenges associated with: (1) estimation of unobserved traits from the available data on bodyweight and feed consumption; and (2) characterisation of the distributions and correlations of these unobserved traits to generate accurate estimates of individual level variation among pigs. Here, alternative quantitative approaches to these challenges, based on the principles of inverse modelling and separately inferring individual level distributions within a Bayesian context were developed and incorporated in a proposed precision feeding modelling framework. The objectives were to: (i) determine the average and distribution of individual traits characterising growth potential and body composition in an empirical population of growing-finishing barrows and gilts; (ii) simulate the growth and excretion of nitrogen and phosphorus of the average pig offered either a commercial two-phase feeding plan, or a precision feeding plan with daily adjustments; and (iii) simulate the growth and excretion of nitrogen and phosphorus across the pig population under two scenarios: a two-phase feeding plan formulated to meet the nutrient requirements of the average pig or a precision feeding plan with daily adjustments for each and every animal in the population. The distributions of mature bodyweight and ratio of lipid to protein weights at maturity had median (IQR) values of 203 (47.8) kg and 2.23 (0.814) kg/kg, respectively; these estimates were obtained without any prior assumptions concerning correlations between the traits. Overall, it was found that a proposed precision feeding strategy could result in considerable reductions in excretion of nitrogen and phosphorus (average pig: 8.07 and 9.17% reduction, respectively; heterogenous pig population: 22.5 and 22.9% reduction, respectively) during the growing-finishing period from 35 to 120 kg bodyweight. This precision feeding modelling framework is anticipated to be a starting point toward more accurate estimation of individual level nutrient requirements, with the general aim of improving the economic and environmental sustainability of future pig production systems.