Application of Machine Learning Algorithms to Describe the Characteristics of Dairy Sheep Lactation Curves.

In recent years, machine learning (ML) algorithms have emerged as powerful tools for predicting and modeling complex data. Therefore, the aim of this study was to evaluate the prediction ability of different ML algorithms and a traditional empirical model to estimate the parameters of lactation curves. A total of 1186 monthly records from 156 sheep lactations were used. The model development process involved training and testing models using ML algorithms. In addition to these algorithms, lactation curves were also fitted using the Wood model. The goodness of fit was assessed using correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), relative absolute error (RAE), and relative root mean square error (RRSE). SMOreg was the algorithm with the best estimates of the characteristics of the sheep lactation curve, with higher values of r compared to the Wood model (0.96 vs. 0.68) for the total milk yield. The results of the current study showed that ML algorithms are able to adequately predict the characteristics of the lactation curve, using a relatively small number of input data. Some ML algorithms provide an interpretable architecture, which is useful for decision-making at the farm level to maximize the use of available information.

Stoichiometric models for prediction of enteric methane production

This study aimed to empirically evaluate the adjustment quality of two stoichiometric models of methane production from diets that used different rumen fermentation modulators. We used the models proposed by Moss et al. (2000) and Blümmel et al. (1997). The data set consisted of 169 observations of in vitro methane production and volatile fatty acids (acetate, propionate, and butyrate) from dissertations, theses, and scientific articles. The model's adequacy evaluation was only possible through combination of several statistical analyzes. The models were unable to predict the enteric methane precisely and accurately. Despite this, the model proposed by Moss et al. (2000) showed a better fit based on the mean bias (% of observed, MB), MEF, RMSEP, Cb and CCC measures compared to the model proposed by Blümmel et al. (1997). However, both models presented strong evidence against the general hypothesis H0: a = 0 & b = 1. Thus, the model proposed by MOSS et al. (2000) was more efficient, whereas the model by Blümmel et al. (1997) showed a better fit for diets with high availability of H2.

Evaluation of the availability of mass of forage: morphological responses and chemical composition of Tanzania grass subjected to two pasture-management strategies / Avaliação da disponibilidade de massa da forrageira: respostas morfológicas e composição química do Tanzânia sujeito a duas estratégias de manejo de pastagem

The objective of this study was to evaluate the morphogenetic traits and chemical composition of Tanzania grass using a fixed rest period or according to light interception at 95%. The treatments consisted of evaluations of two Tanzania-grass pasture-management strategies: (1) LI95 - animals entered the paddocks when the pasture reached 95% of light interception (LI), with three days of paddock occupation; and (2) FR - the pasture was managed with a defoliation interval (DI) of 30 days, and three days of paddock occupation. The experimental area consisted of 4 ha, with 22 paddocks per treatments. Ten recently-calved cows were used per treatment in year 1, and eight cows were used per treatment in year 2. Sward height, forage mass, and morphological components and their chemical composition were evaluated. The management strategies used on the Tanzania grass pasture did not affect pasture mass or height in the pre- and post-grazing conditions, or the proportion of stems. However, the proportion of leaves was greater in the paddocks with 95% light interception. The crude protein content was higher in the paddocks with 95% light interception; the other nutrients were not affected. In conclusion, management adopting 95% light interception does not influence morphogenetic traits. Nevertheless, it promotes an increase in the crude protein content of grasses.

O objetivo deste trabalho foi avaliar as características morfogênicas e a composição química do capim-tanzânia, utilizando um período de descanso fixo ou de acordo com a interceptação luminosa a 95%. Os tratamentos consistiram de avaliações de duas estratégias de manejo de pastagem de capim Tanzânia: (1) LI95 - animais entraram nos piquetes quando o pasto atingiu 95% de interceptação luminosa (LI), com três dias de ocupação do piquete; e (2) FR - a pastagem foi manejada com um intervalo de desfolhamento (DI) de 30 dias e três dias de ocupação do piquete. A área experimental consistiu de 4 ha, com 22 piquetes por tratamento. Dez vacas recém-paridas foram utilizadas por tratamento no ano 1, e oito vacas foram utilizadas por tratamento no ano 2. A altura do pasto, a massa de forragem e os componentes morfológicos e sua composição química foram avaliados. As estratégias de manejo utilizadas na pastagem de capim-Tanzânia não afetaram a massa ou a altura do pasto nas condições pré e pós-pastejo, ou a proporção de hastes. No entanto, a proporção de folhas foi maior nos piquetes com 95% de interceptação de luz. O teor de proteína bruta foi maior nos piquetes com 95% de interceptação de luz; os outros nutrientes não foram afetados. Em conclusão, o manejo adotando 95% de interceptação de luz não influencia as características morfogenéticas. No entanto, promove um aumento no teor de proteína bruta das gramíneas

Milk production of crossbred holstein × zebu on different pasture-management strategies / Produção de leite de vacas mestiças holandês × zebu em diferentes estratégias de manejo de pastagens

The objective of this study was to evaluate nutrient intake and digestibility, yield and components of milk from Holstein × Zebu cows on Tanzania grass pastures using a fixed-rest period or 95% light interception. The treatments consisted of evaluations of two Tanzania-grass pasture-management strategies: LI95 - when the pasture reached 95% light interception (LI), with 3 paddock-occupation days; and FR - the pasture was managed with a 30-days defoliation interval (DI) and 3 paddock-occupation days. Ten recently calved cows per treatment in year 1 and eight cows per treatment in year 2 were used, i.e. five cows per replicate in year 2 and four cows per replicate in year 2. Intake and digestibility of pasture nutrients, milk yield and milk composition were evaluated. The management strategies imposed on the Tanzania-grass pasture did not affect nutrient intake or digestibility. Milk yield and milk components were not affected by the management strategies, but milk yield per area unit was affected by the use of 95% light interception. The management strategy applying 95% light interception implies greater efficiency in the use of area, which translates to a higher milk yield per unit area, and thus it can be recommended to increase milk yield per area.

O objetivo deste estudo foi avaliar a ingestão e digestibilidade dos nutrientes, produção e os componentes do leite de vacas Holandesas × Zebu em pastagens de capim-Tanzânia em repouso fixo ou 95% de interceptação de luz. Os tratamentos consistiram de avaliações de duas estratégias de manejo de pastagem de capim Tanzânia: LI95 - quando a pastagem atingiu 95% de interceptação luminosa (LI), com três dias de ocupação do piquete; e TF - a pastagem foi manejada com intervalo de 30 dias de desfolha (ID) e três dias de ocupação do piquete. Dez vacas recém-paridas foram utilizadas por tratamento no ano 1 e oito vacas por tratamento no ano 2. Consumo e digestibilidade dos nutrientes do pasto, produção de leite e leite composição foram avaliados. As estratégias de manejo aplicadas na pastagem de capim-tanzânia não afetaram o consumo ou a digestibilidade dos nutrientes. A produção de leite e os componentes do leite não foram afetados pelas estratégias de manejo, mas a produção de leite por unidade de área foi afetada pelo uso de 95% de interceptação de luz. O manejo adotando 95% de interceptação de luz implica maior eficiência no uso da área, o que significa maior rendimento de leite por unidade de área, e assim pode ser recomendado aumentar a produção de leite por área.

Clitoria ternatea L. as a Potential High Quality Forage Legume.

Samples of Clitoria ternatea L. (Cunhã) were harvested at 35, 50, 70, and 90 d after a uniformity harvest in a field study designed as a completely randomized design with a total of 18 experimental plots. The dry matter yield of the whole plant was separated quantitatively into leaves, stems, and pods at each harvesting age. Chemical analyses and in vitro gas production kinetics were performed to assess the quality of the plant parts. Yields, chemical composition, and estimates of gas production parameters were analyzed by fitting a mixed statistical model with two types of covariance structures as follows: variance components and an unrestricted structure with heterogeneous variances. Fast and slow gas yielding pools were detected for both leaves and stems, but only a single pool was detected for pods. The homoscedasticity assumption was more likely for all variables, except for some parameters of the gas production kinetics of leaves and stems. There was no presence of typical pods at 35 and 50 d. In the leaves, the fibrous fractions were affected, whereas the non-fibrous fractions were unaffected by the harvesting age. The harvesting age affected the majority of the chemical constituents and gas kinetic parameters related to the stems. The leaves of this legume were the least affected part by the aging process.