ABSTRACT
Morphometric characterization is an essential tool for identifying, classifying, and conserving animal genetic resources, involving quantitative and qualitative descriptions of various populations, breeds, and their production systems. This study aims to estimate the morphometric characteristics of different rabbit breeds at the University of Benin Farm Project. It delves into determining the weight and morphological traits of specific breeds, analyzing variations in morphometric characteristics across breeds, modeling body weight and morphometrics using machine learning, and quantifying body morphometrics through Principal Component Analysis (PCA). The research highlights the importance of morphometric characterization for selecting and breeding rabbits with desirable traits, estimating body weight, and understanding the effects of age and breed on morphometric parameters.
Data on body weight and body morphometrics were measured, recorded and subjected to statistical analysis using machine learning. Table 4.1 shows that most parameters, such as BL, TL, HL, HL,HG exhibit variations across different age groups. For example, Figure 4.1 presents the results of clustering analyses performed on various morphological traits of different rabbit breeds. The elbow method, a technique used to determine the optimal number of clusters, was applied to the data. Several figures display scatter plots visualizing the clustering patterns observed for different traits, including tail characteristics, body length, hind limb traits, and ear length. The scatter plots reveal distinct clusters of breeds exhibiting varying levels of trait variability within each cluster. Some clusters appear more compact, indicating lower variability in the specific trait among breeds within that group. In contrast, other clusters are more dispersed, suggesting higher variability in the analyzed trait across those breed populations.Outliers representing breeds with exceptionally divergent trait values compared to the majority of the data are also identified in certain plots. The elbow method plots guide the selection of the optimal number of clusters, typically ranging from 2 to 3 clusters for the presented traits. These clustering analyses provide insights into the patterns of morphological variation across different dog breeds, potentially reflecting underlying genetic differences or selective breeding practices targeting specific morphological attributes
