<![CDATA[Livestock feed availability plays a crucial role in livestock production and regional food security. This study aims to map the potential of sub-districts in Pati Regency based on livestock feed availability from 2020 to 2024 using multivariate clustering with the K-Means algorithm. Secondary data were obtained from the Pati Regency Agriculture Office and used to classify 21 sub-districts according to similarities in annual feed availability, measured in tons of feed per year, which provides the quantitative basis for assessing livestock carrying capacity. The analysis included missing-value checking, outlier detection, data standardisation, dimensionality reduction using principal component analysis, and determination of the optimal number of clusters using the Silhouette Coefficient. Among the non-degenerate solutions (k ≥ 3), three clusters yielded the highest silhouette score (0.4383), and this solution was stable across initialisations and robust to the exclusion of the most extreme observation. Cluster 1 represents sub-districts with moderate feed availability, Cluster 2 represents areas with very high and fluctuating feed availability, and Cluster 3 represents sub-districts with high and stable feed availability. These clusters reveal distinct regional characteristics that can support strategic decision-making in livestock development. Areas with moderate availability require policy intervention, regions with high and stable availability have strong potential for sustainable development, and areas with very high but fluctuating availability require careful resource management. This study demonstrates that the K-Means algorithm is effective for mapping livestock feed availability and supporting regional planning for livestock sector development in Pati Regency.]]>
Copyrights © 2026
