Penerapan Metode Clustering Dengan K-Means Untuk Memetakan Potensi Tanaman Padi di Sumatera

Abstract

Rice plants are the primary source of rice, the staple food for the majority of the Indonesian population. Despite the presence of other food alternatives, rice remains irreplaceable for those accustomed to consuming rice. According to data from the Food and Agriculture Organization of the United Nations (FAO) in 2018, Indonesia is the third-largest rice producer in the world, with a total production of 59.2 million tons. However, urban and agricultural spatial planning is not yet fully integrated, resulting in often conflicting decisions in land use planning for agriculture and urban development. To meet the rice demand in Sumatra, efforts are needed to increase rice production in each province. Therefore, this research aims to map the potential for rice cultivation in Sumatra based on production and harvest results from 1993 to 2020. The method used in this study is K-Means, which allows the grouping of rice potential areas into three categories: high, medium, and low. The research results produced three clusters, evaluated using the Davies Bouldin Index (DBI) with a value of 0.3943. The clustering results indicate that Cluster 0 contains 92 areas with a high success rate, Cluster 2 comprises 84 areas with a medium success rate, and Cluster 1 consists of 48 areas with a low success rate. The category of low success rate is found in Cluster 1 with 48 areas. Cluster 0 includes Aceh, North Sumatra, West Sumatra, South Sumatra, and Lampung within certain time periods. Cluster 1 encompasses other areas with different characteristics. Cluster 2 includes the provinces of Riau, Jambi, and Bengkulu.

Implementasi Data Mining dengan K-Means Clustering untuk Memprediksi Pengadaan Obat

“…Iterasi algoritma ini akan terus berjalan sampai keadaan dimana pusat cluster tidak berubah. Secara umum, cara kerja dari algoritma K-Means clustering adalah sebagai berikut [17] a. Menentukan k sebagai jumlah kluster yang diinginkan. b. Menentukan nilai random untuk pusat centroid (cluster awal) sebanyak k.…”