Using artificial neural networks to predict pH, ammonia, and volatile fatty acid concentrations in the rumen

Dietary fat and carbohydrate-balancing the lactation performance and methane emissions in the dairy cow industry: A meta-analysis

For the agroecosystems of the dairy cow industry, dietary carbohydrate (starch, neutral detergent fiber [NDF]) and fat could directly affect rumen methane emissions and host energy utilization. However, the relationships among diet, lactation performance, and methane emissions need to be further determined to assist dairy farms to adjust diet formulations and feeding strategies for environmental and production management. A meta-analysis was conducted in the current study to explore quantitative patterns of dietary fat and carbohydrate at different levels in balancing lactation performance and environment sustainability of dairy cows, and to establish a methane emission prediction model using the artificial neural network (ANN) model. The results showed that the regression relationship between dietary fat, carbohydrate and methane emissions could be shown by the following models: methane = 106.78 + (14.86 × DMI), R2 = 0.80; methane = 443.17 - (46.41 × starch/NDF), R2 = 0.76; and methane = 388.91 + (31.40 × fat) - (5.42 × fat2), R2 = 0.80. The regression relationships between dietary fat, carbohydrate and lactation performance could be shown by the following models: milk fat yield = 1.08 + (0.43 × starch/NDF) - [0.34 × (starch/NDF)2], R2 = 0.79; milk protein yield = 0.68 + (0.15 × fat) - (0.016 × fat2), R2 = 0.82. In the structural equation model, we found that when formulating dietary carbohydrates and fats, it was necessary to balance the relationship between methane emissions and lactation performance. Specifically, dietary starch/NDF was lower than 0.63 (extremum point) and dietary fat was between 2.89% and 4.69% (extremum point), it could ensure that the aim of methane emission reduction (methane emissions decrease with increasing dietary starch/NDF and fat) was achieved without losing lactation performance of dairy cows (lactation performance increase with increasing dietary starch/NDF and fat). Finally, we established the ANN model to predict methane emissions (training set: R2 = 0.62; validation set: R2 = 0.61).

Development of an Alternative In Vitro Rumen Fermentation Prediction Model

The aim of this study is to identify an alternative approach for simulating the in vitro fermentation and quantifying the production of rumen methane and rumen acetic acid during the rumen fermentation process with different total mixed rations. In this experiment, dietary nutrient compositions (neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM)) were selected as input parameters to establish three prediction models for rumen fermentation parameters (methane and acetic acid): an artificial neural network model, a genetic algorithm-bp model, and a support vector machine model. The research findings show that the three models had similar simulation results that aligned with the measured data trends (R2 ≥ 0.83). Additionally, the root mean square errors (RMSEs) were ≤1.85 mL/g in the rumen methane model and ≤2.248 mmol/L in the rumen acetic acid model. Finally, this study also demonstrates the models' capacity for generalization through an independent verification experiment, as they effectively predicted outcomes even when significant trial factors were manipulated. These results suggest that machine learning-based in vitro rumen models can serve as a valuable tool for quantifying rumen fermentation parameters, guiding the optimization of dietary structures for dairy cows, rapidly screening methane-reducing feed options, and enhancing feeding efficiency.

Modeling energy partition patterns of growing pigs fed diets with different net energy levels based on machine learning

The objectives of this study were to evaluate the energy partition patterns of growing pigs fed diets with different net energy (NE) levels based on machine learning methods, and to develop prediction models for the NE requirement of growing pigs. Twenty-four Duroc × Landrace × Yorkshire crossbred barrows with an initial body weight of 24.90 ± 0.46 kg were randomly assigned to 3 dietary treatments, including the low NE group (2,325 kcal/kg), the medium NE group (2,475 kcal/kg), and the high NE group (2,625 kcal/kg). The total feces and urine produced from each pig during each period were collected, to calculate the NE intake, NE retained as protein (NEp), and NE retained as lipid (NEl). A total of 240 sets of data on the energy partition patterns of each pig were collected, 75% of the data in the dataset was randomly selected as the training dataset, and the remaining 25% was set as the testing dataset. Prediction models for the NE requirement of growing pigs were developed using algorithms including multiple linear regression (MR), artificial neural networks (ANN), k-nearest neighbor (KNN), and random forest (RF), and the prediction performance of these models was compared on the testing dataset. The results showed pigs in the low NE group showed a lower average daily gain, lower average daily feed intake, lower NE intake, but greater feed conversion ratio compared to pigs in the high NE group in most growth stages. In addition, pigs in the 3 treatment groups did not show a significant difference in NEp in all growth stages, while pigs in the medium and high NE groups showed greater NEl compared to pig in the low NE group in growth stages from 25 to 55 kg (P < 0.05). Among the developed prediction models for NE intake, NEp, and NEl, the ANN models demonstrated the most optimal prediction performance with the smallest root mean square error (RMSE) and the largest R2, while the RF models had the worst prediction performance with the largest RMSE and the smallest R2. In conclusion, diets with varied NE concentrations within a certain range did not affect the NEp of growing pigs, and the models developed with the ANN algorithm could accurately achieve the NE requirement prediction in growing pigs.

Rumen Fermentation Parameters Prediction Model for Dairy Cows Using a Stacking Ensemble Learning Method

Volatile fatty acids (VFAs) and methane are the main products of rumen fermentation. Quantitative studies of rumen fermentation parameters can be performed using in vitro techniques and machine learning methods. The currently proposed models suffer from poor generalization ability due to the small number of samples. In this study, a prediction model for rumen fermentation parameters (methane, acetic acid (AA), and propionic acid (PA)) of dairy cows is established using the stacking ensemble learning method and in vitro techniques. Four factors related to the nutrient level of total mixed rations (TMRs) are selected as inputs to the model: neutral detergent fiber (NDF), acid detergent fiber (ADF), crude protein (CP), and dry matter (DM). The comparison of the prediction results of the stacking model and base learners shows that the stacking ensemble learning method has better prediction results for rumen methane (coefficient of determination (R2) = 0.928, root mean square error (RMSE) = 0.968 mL/g), AA (R2 = 0.888, RMSE = 1.975 mmol/L) and PA (R2 = 0.924, RMSE = 0.74 mmol/L). And the stacking model simulates the variation of methane and VFAs in relation to the dietary fiber content. To demonstrate the robustness of the model in the case of small samples, an independent validation experiment was conducted. The stacking model successfully simulated the transition of rumen fermentation type and the change of methane content under different concentrate-to-forage (C:F) ratios of TMR. These results suggest that the rumen fermentation parameter prediction model can be used as a decision-making basis for the optimization of dairy cow diet compositions, rapid screening of methane emission reduction, feed beneficial to dairy cow health, and improvement of feed utilization.

Modeling net energy partition patterns of growing-finishing pigs using nonlinear regression and artificial neural networks

The objectives of this study were to evaluate the net energy (NE) partition patterns of growing-finishing pigs at different growing stages and to develop the corresponding prediction models using nonlinear regression (NLR) and artificial neural networks (ANN). Twenty-four pigs with an initial body weight (BW) of ~30 kg were kept in metabolic cages and fed ad libitum and were moved into six respiration chambers in turns until ~90 kg. The NE partition patterns, i.e., NE for maintenance (NEm), NE retained as protein (NEp), and NE retained as lipid (NEl), were calculated based on indirect calorimetry and nitrogen balance techniques. The energy balance data collected through the animal trial was then randomly split into a training data set containing 75% of the samples and a testing data set containing the remaining 25% of the samples. The NLR models and a series of ANN models were established on the training data set to predict the metabolizable energy intake, NE intake, NEm, NEp, and NEl of pigs. The best-fitted ANN models were selected by 5-fold cross-validation in the training data set. The prediction performance of the best-fitted NLR and ANN models were compared on the testing data set. The results showed that the average NE intakes of pigs were 17.71, 23.25, 24.56, and 28.96 MJ/d in 30 to 45 kg, 45 to 60 kg, 60 to 75 kg, and 75 to 90 kg, respectively. The NEm and NEl (MJ/d) kept increasing as BW increased from 30 kg to 90 kg, while the NEp increased to its maximum value and then kept in a certain range of 4.64 to 4.88 MJ/d. The proportion of NEm for pigs at 30 to 90 kg stayed within the range of 42.0% to 48.6%, while the proportion of NEl kept increasing. For the prediction models built based on the animal trial, ANN models exhibited better performance than NLR models for all the target outputs. In conclusion, NE partition patterns changed in different growth stages of pigs, and ANN models are more flexible and powerful than NLR models in predicting the NE partition patterns of growing-finishing pigs.

Invited review: integration of technologies and systems for precision animal agriculture-a case study on precision dairy farming

Precision livestock farming (PLF) offers a strategic solution to enhance the management capacity of large animal groups, while simultaneously improving profitability, efficiency, and minimizing environmental impacts associated with livestock production systems. Additionally, PLF contributes to optimizing the ability to manage and monitor animal welfare while providing solutions to global grand challenges posed by the growing demand for animal products and ensuring global food security. By enabling a return to the "per animal" approach by harnessing technological advancements, PLF enables cost-effective, individualized care for animals through enhanced monitoring and control capabilities within complex farming systems. Meeting the nutritional requirements of a global population exponentially approaching ten billion people will likely require the density of animal proteins for decades to come. The development and application of digital technologies are critical to facilitate the responsible and sustainable intensification of livestock production over the next several decades to maximize the potential benefits of PLF. Real-time continuous monitoring of each animal is expected to enable more precise and accurate tracking and management of health and well-being. Importantly, the digitalization of agriculture is expected to provide collateral benefits of ensuring auditability in value chains while assuaging concerns associated with labor shortages. Despite notable advances in PLF technology adoption, a number of critical concerns currently limit the viability of these state-of-the-art technologies. The potential benefits of PLF for livestock management systems which are enabled by autonomous continuous monitoring and environmental control can be rapidly enhanced through an Internet of Things approach to monitoring and (where appropriate) closed-loop management. In this paper, we analyze the multilayered network of sensors, actuators, communication, networking, and analytics currently used in PLF, focusing on dairy farming as an illustrative example. We explore the current state-of-the-art, identify key shortcomings, and propose potential solutions to bridge the gap between technology and animal agriculture. Additionally, we examine the potential implications of advancements in communication, robotics, and artificial intelligence on the health, security, and welfare of animals.

Can machine learning algorithms perform better than multiple linear regression in predicting nitrogen excretion from lactating dairy cows

This study aims to compare the performance of multiple linear regression and machine learning algorithms for predicting manure nitrogen excretion in lactating dairy cows, and to develop new machine learning prediction models for MN excretion. Dataset used were collated from 43 total diet digestibility studies with 951 lactating dairy cows. Prediction models for MN were developed and evaluated using MLR technique and three machine learning algorithms, artificial neural networks, random forest regression and support vector regression. The ANN model produced a lower RMSE and a higher CCC, compared to the MLR, RFR and SVR model, in the tenfold cross validation. Meanwhile, a hybrid knowledge-based and data-driven approach was developed and implemented to selecting features in this study. Results showed that the performance of ANN models were greatly improved by the turning process of selection of features and learning algorithms. The proposed new ANN models for prediction of MN were developed using nitrogen intake as the primary predictor. Alternative models were also developed based on live weight and milk yield for use in the condition where nitrogen intake data are not available (e.g., in some commercial farms). These new models provide benchmark information for prediction and mitigation of nitrogen excretion under typical dairy production conditions managed within grassland-based dairy systems.

Estimation of milk yield based on udder measures of Pelibuey sheep using artificial neural networks

Udder measures have been used to assess milk yield of sheep through classical methods of estimation. Artificial neural networks (ANN) can deal with complex non-linear relationships between input and output variables. In the current study, ANN were applied to udder measures from Pelibuey ewes to estimate their milk yield and this was compared with linear regression. A total of 357 milk yield records with its corresponding udder measures were used. A supervised learning was used to train and teach the network using a two-layer ANN with seven hidden structures. The globally convergent algorithm based on the resilient backpropagation was used to calculate ANN. Goodness of fit was evaluated using the mean square prediction error (MSPE), root MSPE (RMSPE), correlation coefficient (r), Bayesian’s Information Criterion (BIC), Akaike’s Information Criterion (AIC) and accuracy. The 15–15 ANN architecture showed that the best predictive milk yield performance achieved an accuracy of 97.9% and the highest values of r² (0.93), and the lowest values of MSPE (0.0023), RMSPE (0.04), AIC (− 2088.81) and BIC (− 2069.56). The study revealed that ANN is a powerful tool to estimate milk yield when udder measures are used as input variables and showed better goodness of fit in comparison with classical regression methods.

Predicting the growth performance of growing-finishing pigs based on net energy and digestible lysine intake using multiple regression and artificial neural networks models

BACKGROUNDS

Evaluating the growth performance of pigs in real-time is laborious and expensive, thus mathematical models based on easily accessible variables are developed. Multiple regression (MR) is the most widely used tool to build prediction models in swine nutrition, while the artificial neural networks (ANN) model is reported to be more accurate than MR model in prediction performance. Therefore, the potential of ANN models in predicting the growth performance of pigs was evaluated and compared with MR models in this study.

RESULTS

Body weight (BW), net energy (NE) intake, standardized ileal digestible lysine (SID Lys) intake, and their quadratic terms were selected as input variables to predict ADG and F/G among 10 candidate variables. In the training phase, MR models showed high accuracy in both ADG and F/G prediction (R2ADG = 0.929, R2F/G = 0.886) while ANN models with 4, 6 neurons and radial basis activation function yielded the best performance in ADG and F/G prediction (R2ADG = 0.964, R2F/G = 0.932). In the testing phase, these ANN models showed better accuracy in ADG prediction (CCC: 0.976 vs. 0.861, R2: 0.951 vs. 0.584), and F/G prediction (CCC: 0.952 vs. 0.900, R2: 0.905 vs. 0.821) compared with the MR models. Meanwhile, the "over-fitting" occurred in MR models but not in ANN models. On validation data from the animal trial, ANN models exhibited superiority over MR models in both ADG and F/G prediction (P < 0.01). Moreover, the growth stages have a significant effect on the prediction accuracy of the models.

CONCLUSION

Body weight, NE intake and SID Lys intake can be used as input variables to predict the growth performance of growing-finishing pigs, with trained ANN models are more flexible and accurate than MR models. Therefore, it is promising to use ANN models in related swine nutrition studies in the future.

Progressive trends on the application of artificial neural networks in animal sciences - A review

In recent years, artificial neural networks have become the subject of intensive research in a number of scientific areas. The high performance and operational speed of neural models open up a wide spectrum of applications in various areas of life sciences. Objectives pursued by many scientists, who use neural modelling in their research, focus - among others - on intensifying real-time calculations. This study shows the possibility of using Multilayer-Perceptron (MLP) and Radial Basis Function (RBF) models of artificial neural networks for the future development of new methods for animal science. The process should be explained explicitly to make the MLP and RBF models more readily accepted by more researchers. This study describes and recommends certain models as well as uses forecasting methods, which are represented by the chosen neural network topologies, in particular MLP and RBF models for more successful operations in the field of animals sciences.

Estimating in vitro ruminal ammonia-N using multiple linear models and artificial neural networks based on the CNCPS nitrogenous fractions of cattle rations with low concentrate/roughage ratios

The objectives of this study were to investigate the relationship between the in vitro ruminal ammonia nitrogen (NH₃ -N) concentration and the Cornell Net Carbohydrate and Protein System (CNCPS) N-fractions of feeds for cattle and further compare the performance of developing multiple linear regression (MLR) and artificial neural network (ANN) models in estimating the NH₃ -N concentration in rumen fermentation. Two data sets were established, of which the training data set containing forty-five rations for cattle with concentrate/roughage ratios of 50:50, 40:60, 30:70, 20:80 and 10:90 used for developing models and the test data set containing ten other rations with the same concentrate/roughage ratios with the training data set were used for validating of models. The NH₃ -N concentrations of feed samples were measured using an in vitro incubation technique. The CNCPS N-fractions (g), for example PB₁ (rapidly degraded true protein), PB₂ (neutral detergent soluble nitrogen), PB₃ (acid detergent soluble nitrogen) of rations, were calculated based on chemical analysis. Statistical analysis indicated that the NH₃ -N concentration (mg) was significantly correlated with the CNCPS N-fractions (g) PB₁ , PB₂ and PB₃ in a multiple linear pattern: NH₃ -N = (130.70±33.80) PB₁  + (155.83±17.89) PB₂ - (85.44±37.69) PB₃  + (42.43±1.05), R²  = 0.77, p < 0.0001, n = 45. The results indicated that both MLR and ANN models were suitable for predicting in vitro NH₃ -N concentration of rations using CNCPS N-fractions PB₁ , PB₂ , and PB₃ as independent variables while the neural network model showed better performance in terms of greater r² , CCC and lower RMSPE between the observed and predicted values.

ANN coupled with Monte Carlo simulation for predicting the concentration of acids

The present study proposes a new approach for determining the concentration of acids. The method is based on the combination of Monte Carlo simulation and artificial neural network (ANN) technique for predicting the concentration of acids. Firstly, a Monte Carlo simulation model is validated based on the comparison of simulation data with experimental data. Then, the whole data derived from the Monte Carlo simulation using the MCNP code was used to train the ANN model. The trained ANN model was used to predict the percentage concentrations of 14 acid samples, which yields the maximum relative deviation between the predicted and the reference concentrations is less than 3.5%.

Stability assessment of extracts obtained from Arbutus unedo L. fruits in powder and solution systems using machine-learning methodologies

Arbutus unedo L. (strawberry tree) has showed considerable content in phenolic compounds, especially flavan-3-ols (catechin, gallocatechin, among others). The interest of flavan-3-ols has increased due their bioactive actions, namely antioxidant and antimicrobial activities, and by association of their consumption to diverse health benefits including the prevention of obesity, cardiovascular diseases or cancer. These compounds, mainly catechin, have been showed potential for use as natural preservative in foodstuffs; however, their degradation is increased by pH and temperature of processing and storage, which can limit their use by food industry. To model the degradation kinetics of these compounds under different conditions of storage, three kinds of machine learning models were developed: i) random forest, ii) support vector machine and iii) artificial neural network. The selected models can be used to track the kinetics of the different compounds and properties under study without the prior knowledge requirement of the reaction system.

A revised representation of ruminal pH and digestive reparameterization of the Molly cow model

Ruminal pH is a critical factor to regulate nutrient degradation and fermentation. However, it has been poorly predicted in the Molly cow model, and recent improvements in the representation of nitrogen cycling across the rumen wall altered some of the modeled responses to feed nutrients, resulting in some model bias. The objectives of this study were to further improve the representation of pH and to refit parameters related to ruminal metabolism and nutrient digestion in the model to resolve this bias, and to use the improved model to estimate nitrogen and energy fluxes with varying rumen-degradable protein (RDP; 40 vs. 60%) and ruminally degraded starch (RDSt; 50 vs. 75%). A meta data set containing 284 peer reviewed studies with 1,223 treatment means was used to derive parameter estimates for ruminal metabolism and nutrient digestions. Refitting the parameters significantly improved the accuracy and precision of the model predictions for ruminal nutrient outflow [acid detergent fiber (ADF), neutral detergent fiber (NDF), total N, microbial N, nonammonia N, and nonammonia nonmicrobial N], ammonia and blood urea concentrations, and fecal nutrient outflow (protein, ADF, and NDF). The prediction error for body weight was decreased from 19.3 to 6.2% with decreased mean bias (from 76.0 to 11.5%) and slope bias (from 17.2 to 7.7%), primarily due to improved representations of ruminal dry matter and liquid pool size. Adding ammonia concentration as a driver to the pH equation increased the precision of predicted ruminal pH and, thereby, the precision of predicted volatile fatty acid (VFA) concentrations, due to improved representation of pH regulation of VFA production rates. Although minor mean and slope bias were observed for ruminal pH and VFA concentrations, the concordance correlation coefficients indicated that much of the observed variation in these variables remains unexplained. Overall, the biological functions of nutrient degradation and digestion appear to be represented without bias. Simulated results indicated that decreasing RDP and RDSt proportions in an isonitrogenous and isocaloric diet can slightly improve N efficiency, and increasing RDSt proportions can increase energy efficiency.