Demet Çanga Boğa

Hayvancılık işletmelerinde toplam üretim maliyetlerinin büyük bölümünü oluşturan yem giderleri, işletme kârlılığı ve rekabet gücü üzerinde belirleyici bir rol oynamaktadır. Bu bölümde, geleneksel yem hammaddelerindeki fiyat artışları ve arz güvenliği sorunları karşısında öne çıkan alternatif yem kaynakları (tarımsal ve agro-endüstriyel yan ürünler, endüstriyel yan ürünler, böcek unları, mikroalgler, tek hücre proteinleri) ile fonksiyonel yem katkı maddeleri (probiyotikler, prebiyotikler, organik asitler, enzimler, fitobiyotikler) güncel bilimsel literatür ışığında bütüncül bir yaklaşımla ele alınmıştır. Bu yemlerin yem maliyetleri, hayvan performansı, ürün kalitesi, rekabet gücü ve ekonomik sürdürülebilirlik üzerindeki etkileri; brüt/net kâr, fayda-maliyet oranı ve başa baş noktası gibi ekonomik göstergeler temel alınarak örnek bir karşılaştırmalı analizle desteklenmiştir. Ayrıca alternatif yemlerin karbon ayak izinin azaltılması ve döngüsel ekonomiye katkısı çerçevesinde çevresel sürdürülebilirlik boyutu değerlendirilmiş, SWOT analizi ile güçlü/zayıf yönler ve fırsat/tehditler sistematik olarak ortaya konmuştur. Hassas hayvancılık, yapay zekâ destekli rasyon formülasyonu ve yeni nesil protein kaynaklarının gelecekteki rolüne dair öngörülerle bölüm tamamlanmaktadır.

This study investigated the factors influencing milk yield in dairy cattle, the determination of optimal combinations, and the predictive performance of machine learning (ML) models. A total of 830 records collected in 2024 from a private dairy farm in Niğde, Turkey, were analyzed using breed, physiological status code, lactation number, age and days in milk as predictors. Statistical analyses confirmed that both breed and status code significantly affected milk yield (p < 0.05). Regression analysis indicated a positive effect of lactation number (β = 17.65, p < 0.001) and a negative effect of age (β = –0.80, p < 0.001). The highest yield (40.07 L/day) was recorded in Holstein Friesian cows with Cyclic status in the 3rd lactation. Six ML algorithms were compared using 5‑fold cross‑validation under two modelling scenarios designed to address multicollinearity between age and lactation number. Among the tested algorithms, Random Forest (R² ≈ 0.88, RMSE ≈ 5.2 L) and Gradient Boosting (R² ≈ 0.88, RMSE ≈ 5.2 L) provided markedly better predictive accuracy than linear regression models. SHAP (SHapley Additive exPlanations) analysis enhanced model interpretability and identified days in milk, physiological status and lactation number as the most influential predictors, followed by age and breed. These findings highlight the importance of integrating physiological and genetic factors in herd management and demonstrate the potential of ensemble ML techniques as reliable decision-support tools for optimizing milk yield in dairy farming.

In this study, Random Forest, Gradient Boosting Machines (GBM), and Support Vector Machines (SVM), Multi-Class Logistic Regression (MCLR) models were comparatively evaluated for the prediction of milk yield in water buffaloes. The study’s main purpose was to compare the success of the determined models in milk yield predictions with their accuracy rates. In response to reviewer feedback, the methodology was enhanced to include stratified 8-fold cross-validation, hyperparameter tuning for RF, GBM, and SVM, and the removal of the multicollinear AGE variable. The revised dataset comprised the following features: lactation period (LP), lactation milk yield (LDMY), age at first pregnancy (1stPregAge), and feed type. Model training and evaluation were conducted using Python 3.7 with Pandas, NumPy, Scikit-learn, and Matplotlib libraries. According to the updated findings, the GBM model outperformed others, achieving an average accuracy of 64.63%, weighted precision of 0.6578, recall of 0.6463, F1-score of 0.6311, and ROC AUC of 0.6625. While the predictive performance remains moderate, these results demonstrate the potential of advanced machine.

The aim of this study was to define the growth by using nonlinear functions in intensive feedlot system with XGBoost algorithm. To achieve this aim, five nonlinear functions were implemented. To implementation of the study, Brown Swiss (n=41) and Simental (n=95) breed were used. Each nonlinear functions were examined for each breed. According to the results of the nonlinear functions, logistic model was the best prediction model for defining the growth of each breed. In this study, the parameters in the best prediction model were calculated individually and the relationship of these parameters with body weight was evaluated with the XGBoost algorithm. Model comparison criteria such as standard deviation ratio (SDratio), Pearson’s correlation coefficient (PC), determination of coefficient (R2) and Akaike’s information criteria (AIC) were used to evaluate the XGBoost algorithm. In conclusion, the XGBoost algorithm can be an effective and optional approach that allows breeders to estimate live weight from growth parameters. This algorithm can operate on large data sets with high accuracy and speed, leading to significant improvements in agricultural productivity and animal health management. XGBoost enables more accurate predictions by analyzing the effects of various characteristics (e.g., nutritional level, breed, age). Therefore, this method can be used to determine critical parameters such as body weight in animal breeding practices, serving as a powerful support tool for operational decisions.

The main purpose of this research is to obtain a prediction model for milk yield by using Multivariate Adaptive Regression Splines (MARS) and Bagging MARS algorithms as a non-parametric regression technique. For this purpose, the effects on milk yield of 305 days were investigated by using lactation parameters in dairy cattle. In the study, 9337 lactation milk yield records belonging to 37 animals belonging to the 2022-2023 period were used and the data set was created by randomly ordering the animals. Data on milk yield results were analyzed with MARS and Bagging MARS algorithms. For dairy cattle; it was modeled with explanatory variables such as lactation month (month), service period (SP), last 7 days average milk yield (L7DMMY), animal's first birth age (FP), animal's age (Age), number of lactations (LN).Correlation coefficient (r), coefficient of determination (R2), Adjusted R2, Root of Square Mean Error (RMSE), standard deviation ratio (SD ratio), mean absolute percent error (MAPE), mean absolute for MARS algorithm estimating total average milk yield deviation (MAD) and Akaike Information Criteria (AIC) values are 0.9986, 0.997, 0.977, 0.142, 0.052, 0.2389, 0.086 and -88, respectively. Similar statistics for the Bagging MARS algorithm are 0.754, 0.556, 0.453, 1.8, 0.666, 3.96, 1.47, and 115, respectively. It has been observed that MARS and Bagging MARS algorithms provide correct results according to the goodness of fit statistics. In this study, it was revealed that MARS algorithm gave better results in milk yield modeling of 305-day lactation.

In this study, seasonal milk yield estimation will be made using multivariate adaptive regression spline (MARS) algorithm for multiple continuous responses in dairy cattle (Holstein hybrid). For the research, milking records for the years 2020-2021 were collected from 157 dairy animals using Holstein hybrid dairy cattle from a research farm in Konya, Türkiye. The amount of feed given in this experiment was not changed and the effect of the season on the estimation of milk yield was investigated in the study. The analyzed independent variables used in the study were pregnancy status (PS), number of days milked (MDN), Lactation Number (LN), age of cows (months), average seven-day milk yield (7-Day Average Milk-SDMY), last lactation milk yield (last_MY), number of inseminations (IN), peak yield (Pik_Yield) and target variables were calculated as (YieldAutumn/winter/spring/summer (kg) = Mean milk mean of season. In this context, the ehaGoF package was used to measure the prediction performance of the simultaneous MARS model established with the earth package for MARS analysis. MARS estimation equations obtained simultaneously for four dependent variables (multiple responses) are given. By looking at the MARS equation, the MARS model estimation equation was determined for the optimum milk yield, the threshold values, the three threshold values determined in the model were determined as MDN, Age, Peak_Yield, and the corresponding values were respectively; 159 days, 39.6 (months) and 37.1 kg/day. Considering the estimation equation, it is seen that the independent variables MDN, SDMY and LN are the most important variables in determining the estimation equation. It is seen that the best fitting value for the estimation equation of the dependent variables is the YieldWinter variable.

The objective of our study was to evaluate the predictive ability of a multi-trait genomic prediction model that accounts for interactions between marker effects to estimate heritability and genetic correlations of traits including 305-day milk yield, milk fat percentage, milk protein percentage, milk lactose percentage, and milk dry matter percentage in the Polish Holstein Friesian cow population. For this aim, 14,742 SNP genotype records for 586 Polish Holstein Friesian dairy cows from Poland were used. Single-Trait-ssGBLUP (ST) and Multi-Trait-ssGBLUP (MT) methods were used for estimation. We examined 305-day milk yield (MY, kg), milk fat percentage (MF, %), milk protein percentage (MP, %), milk lactose percentage (ML, %), and milk dry matter percentage (MDM, %). The results showed that the highest marker effect rank correlation was found between milk fat percentage and milk dry matter. The weakest marker effect rank correlation was found between ML and all other traits. Obtained accuracies of this study were between 0.770 and 0.882, and 0.773 and 0.876 for MT and ST, respectively, which were acceptable values. All estimated bias values were positive, which is proof of underestimation. The highest heritability value was obtained for MP (0.3029) and the lowest heritability value was calculated for ML (0.2171). Estimated heritability values were low for milk yield and milk composition as expected. The strongest genetic correlation was estimated between MDM and MF (0.4990) and the weakest genetic correlation was estimated between MY and ML (0.001). The genetic relations with milk yield were negative and can be ignored as they were not significant. In conclusion, multi-trait genomic prediction can be more beneficial than single-trait genomic prediction.

Green fodder plants have an important place in animal nutrition in terms of meeting the nutritional needs of animals and increasing appetite. Especially in dairy cattle breeding, green feeds are needed for milk yield and quality. In order to meet the green feed needs of ruminant animals, the scarcity of agricultural areas, water use, environmental and climate factors can cause negative effects. The increase in the prices of green feeds, which cannot be sustained throughout the year, increases the tendency to soilless agriculture. The increase in feed prices due to many reasons in soil-dependent agriculture may cause the breeder to ignore the nutritional needs of the animal and cause the feeding not to be done correctly. For this purpose, it is thought that with hydroponic production, which is one of the soilless farming systems, the negative conditions related to the environment and soil can be eliminated and the feed costs can be reduced by ensuring the continuity of green feed throughout the year. Although there is a disease-free growing environment with hydroponic production, the digestibility of the products to be obtained will increase and feed efficiency will increase. In addition, with hydroponic production, the digestibility, crude protein values, vitamin and mineral contents of feeds with high cellulose content (such as barley, wheat, maize) increase. Meat, milk yield and quality, animal performance and health will also be positively affected by the increase in feed utilization. In addition to all these, it also allows the plants with a long growing period to benefit in a short time. Especially the feeds obtained by hydroponic production are used to obtain green feed of 18-20 cm in 6-7 days, and to feed animals with the obtained feed root.

Deep learning algorithms can now be used to identify, locate, and count items in an image thanks to advancements in image processing technology. The successful application of image processing technology in different fields has attracted much attention in the field of agriculture in recent years. This research was done to ascertain the number of indigestible cereal grains in animal feces using an image processing method. In this study, a regression-based way of object counting was used to predict the number of cereal grains in the feces. For this purpose, we have developed two different neural network architectures based upon Fully Convolutional Regression Networks (FCRN) and U-Net. The images used in the study were obtained from three different dairy cows enterprises operating in Nigde Province. The dataset consists of the 277 distinct dropping images of dairy cows in the farm. According to findings of the study, both models yielded quite acceptable prediction accuracy with U-Net providing slightly better prediction with a MAE value of 16.69 in the best case, compared to 23.65 MAE value of FCRN with the same batch.