NADYA SURATIKA, NPM 2209100086 (2026) SEGMENTASI WILAYAH PERTANIAN BERBASIS MACHINE LEARNING DENGAN METODE K-MEANS. Skripsi thesis, Universitas Labuhanbatu.
![[img]](http://repository.ulb.ac.id/style/images/fileicons/text.png) |
Text
COVER.pdf Download (1MB) |
|
Text
BAB I.pdf Download (431kB) |
|
Text
BAB II.pdf Download (858kB) |
|
Text
BAB III.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB IV.pdf Restricted to Registered users only Download (1MB) |
|
Text
BAB V.pdf Download (429kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (544kB) |
Abstract
Segmentasi wilayah pertanian diperlukan untuk mengidentifikasi kelompok wilayah yang memiliki karakteristik produksi padi yang relatif serupa. Penelitian ini bertujuan mengelompokkan kabupaten/kota di Provinsi Sumatera Utara berdasarkan data luas panen, produktivitas, dan produksi padi tahun 2023. Data yang digunakan bersumber dari Badan Pusat Statistik dan terdiri atas 32 kabupaten/kota yang memiliki data lengkap. Penelitian menggunakan pendekatan kuantitatif deskriptif dengan algoritma K-Means clustering. Jumlah cluster ditetapkan sebanyak tiga untuk membentuk kategori kapasitas produksi padi relatif rendah, menengah, dan tinggi. Perhitungan dilakukan menggunakan Euclidean Distance dengan centroid awal yang berasal dari Nias, Mandailing Natal, dan Tapanuli Utara, serta diverifikasi menggunakan Python pada Google Colab. Proses K-Means mencapai konvergensi pada iterasi keempat karena tidak terdapat lagi perpindahan anggota cluster. Hasil akhir menunjukkan bahwa Cluster 1 terdiri atas 18 wilayah dengan kapasitas produksi padi relatif rendah, Cluster 2 terdiri atas 12 wilayah dengan kapasitas produksi padi relatif menengah, dan Cluster 3 terdiri atas 2 wilayah dengan kapasitas produksi padi relatif tinggi, yaitu Deli Serdang dan Serdang Bedagai. Hasil segmentasi ini dapat digunakan sebagai informasi awal untuk mendukung penentuan prioritas pengembangan pertanian berdasarkan karakteristik kapasitas produksi setiap wilayah. Kata kunci: Segmentasi Wilayah, Pertanian, Machine Learning, K-Means Clustering, Produksi Padi =============================================================== Agricultural area segmentation is needed to identify groups of regions with relatively similar rice production characteristics. This study aims to group regencies and cities in North Sumatra Province based on harvested area, productivity, and rice production data for 2023. The data were obtained from Statistics Indonesia and consisted of 32 regencies and cities with complete records. This study employed a descriptive quantitative approach using the K Means clustering algorithm. The number of clusters was set to three to represent relatively low, medium, and high rice-production capacity. The calculation used Euclidean Distance with initial centroids selected from Nias, Mandailing Natal, and North Tapanuli, and the results were verified using Python in Google Colab. The K-Means process converged in the fourth iteration because no region changed cluster membership. The final results show that Cluster 1 consists of 18 regions with relatively low rice-production capacity, Cluster 2 consists of 12 regions with medium rice-production capacity, and Cluster 3 consists of 2 regions with relatively high rice-production capacity, namely Deli Serdang and Serdang Bedagai. The segmentation results can serve as preliminary information to support agricultural development priorities according to the production capacity characteristics of each region. Keywords: Regional Segmentation, Agriculture, Machine Learning, K-Means Clustering, Rice Production
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Segmentasi Wilayah, Pertanian, Machine Learning, K-Means Clustering, Produksi Padi==============Regional Segmentation, Agriculture, Machine Learning, K-Means Clustering, Rice Production |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases |
| Divisions: | Fakultas Sains Dan Teknologi > Sistem Informasi |
| Depositing User: | Unnamed user with email repository@ulb.ac.id |
| Date Deposited: | 19 Oct 2026 02:58 |
| Last Modified: | 19 Oct 2026 02:58 |
| URI: | http://repository.ulb.ac.id/id/eprint/2918 |
Actions (login required)
 |
View Item |
