Perbandingan Model Spasial Kesesuaian Lahan Kelapa Sawit di Pulau Sumatera Menggunakan Algoritma Machine Learning

Ferdy Hardiansyah; Ratu Mutiara Siregar; Muhammad Akbar Syahbana Pane; Andi Prayogi

doi:10.56427/jcbd.v5i2.987

Authors

Ferdy Hardiansyah Institut Teknologi Sawit Indonesia
Ratu Mutiara Siregar Institut Teknologi Sawit Indonesia
Muhammad Akbar Syahbana Pane Universitas Negeri Medan
Andi Prayogi Institut Teknologi Sawit Indonesia

DOI:

https://doi.org/10.56427/jcbd.v5i2.987

Keywords:

kesesuaian lahan, kelapa sawit, decision tree, K-nearest Neighbor, FAO

Abstract

Pulau Sumatera merupakan salah satu wilayah utama pengembangan kelapa sawit di Indonesia dengan karakteristik biofisik yang kompleks. Pemanfaatan lahan yang tidak mempertimbangkan kesesuaian biofisik berpotensi menurunkan produktivitas dan meningkatkan degradasi lingkungan. Penelitian ini bertujuan mengintegrasikan pendekatan berbasis aturan FAO dengan metode machine learning untuk memodelkan kesesuaian lahan kelapa sawit secara lebih interpretatif. Algoritma Decision Tree digunakan untuk mempelajari pola klasifikasi dari kriteria FAO dan dibandingkan dengan K-Nearest Neighbor (KNN). Variabel penelitian meliputi kemiringan lereng, curah hujan, suhu udara, pH tanah, tekstur tanah, kedalaman tanah, dan tutupan lahan. Dataset diperoleh dari ekstraksi data raster ke format tabular dengan pembagian data latih dan uji sebesar 80:20. Hasil penelitian menunjukkan kelas S2 mendominasi wilayah penelitian sebesar 61,06%, diikuti S3 sebesar 18,46%, S1 sebesar 14,26%, dan N sebesar 6,22%. Evaluasi cross-validation menunjukkan akurasi Decision Tree sebesar 88,94% dan KNN sebesar 87,18%. Decision Tree memiliki performa lebih stabil dan mudah diinterpretasikan. Penelitian ini menunjukkan integrasi FAO dan machine learning dapat mendukung perencanaan penggunaan lahan yang lebih objektif, transparan, dan berkelanjutan.

Downloads

Download data is not yet available.

References

[1] Food and Agriculture Organization (FAO), “A Framework for Land Evaluation,” Rome, 1976. Accessed: Oct. 27, 2025. [Online]. Available: https://www.fao.org/3/x5310e/x5310e00.htm

[2] Y. Cao and L. Jiang, “Machine Learning based Suggestion Method for Land Suitability Assessment and Production Sustainability,” Nat. Eng. Sci., vol. 9, no. 2, pp. 55–72, 2024, doi: 10.28978/nesciences.1569166.

[3] A. A. Gharaibeh, M. A. Jaradat, and L. M. Kanaan, “A Machine Learning Framework for Assessing Urban Growth of Cities and Suitability Analysis,” Land (Basel)., vol. 12, no. 1, Jan. 2023, doi: 10.3390/land12010214.

[4] Balai Besar Sumber Daya Lahan Pertanian, “Petunjuk Teknis Klasifikasi Tanah Nasional. Kementerian Pertanian Republik Indonesia.,” Balai Besar Litbang Sumberdaya Lahan Pertanian, 2016. [Online]. Available: https://repository.pertanian.go.id/items/fe953d9a-006a-48e1-bf6d-ac050bc4c605

[5] F. A. Prasetya and A. Wibowo, “Analisis Spasial Tingkat Kesesuaian Lahan Permukiman Berdasarkan Kemiringan Tanah di Kota Tangerang,” Geodika: Jurnal Kajian Ilmu dan Pendidikan Geografi, vol. 8, no. 2, pp. 136–146, 2024, doi: 10.29408/geodika.v8i2.26065.

[6] E. P. Rahmamnsyah and R. M. Siregar, “Persepsi Masyarakat Mengenai Isu Penghapusan Kelas Bpjs Menggunakan K-Nearest Neighbor,” Jurnal Edukasi Citra Olahraga, vol. 6, no. 1, pp. 202–213, Feb. 2026, doi: 10.38048/jor.v6i1.6588.

[7] R. M. Siregar, B. Mulyara, R. Dian, M. Maisarah, M. A. S. Pane, and A. Prayogi, “Design Of Control System And Temperature In Coffee Dryer Arduino Based Automatic Using FuzzY,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 10, no. 3, pp. 634–642, Feb. 2025, doi: 10.33480/jitk.v10i3.6166.

[8] R. M. Siregar, B. Satria, A. Prayogi, M. A. S. Pane, E. E. Awal, and Y. R. Sari, “Identification of Tajweed Recognition using Wavelet Packet Adaptive Network based on Fuzzy Inference Systems (WPANFIS),” Internet of Things and Artificial Intelligence Journal, vol. 4, no. 1, pp. 32–41, 2024.

[9] M. Tiftikci, A. Özgür, Y. He, and J. Hur, “Machine learning-based identification and rule-based normalization of adverse drug reactions in drug labels,” BMC Bioinformatics, vol. 20, Dec. 2019, doi: 10.1186/s12859-019-3195-5.

[10] P. Cascante-Bonilla, F. Tan, Y. Qi, and V. Ordonez, “Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning,” 2021. [Online]. Available: www.aaai.org

[11] M. Zlobin and V. Bazylevych, “A Data-Driven Approach for Balancing Overfitting and Underfitting in Decision Tree Models,” Central Ukrainian Scientific Bulletin. Technical Sciences, vol. 1, no. 11(42), pp. 14–26, Mar. 2025, doi: 10.32515/2664-262X.2025.11(42).1.14-26.

[12] C. Md.Sharafat, R. Md.Naimur, S. Md.Sujon, S. Md.Abu, K. H. Mahmud, and B. Hafsa, “GIS-based landslide susceptibility mapping using logistic regression, random forest and decision and regression tree models in Chattogram District, Bangladesh,” Heliyon, vol. 10, no. 1, Jan. 2024, doi: 10.1016/j.heliyon.2023.e23424.

[13] A. Nurkholis, I. S. Sitanggang, Annisa, and Sobir, “Spatial decision tree model for garlic land suitability evaluation,” IAES International Journal of Artificial Intelligence, vol. 10, no. 3, pp. 666–675, Sep. 2021, doi: 10.11591/ijai.v10.i3.pp666-675.

[14] R. Amalia Aras, “Fundamental and Applied Management Journal A Comparative Study of Decision Tree and Gradient Boosted Tree Algorithms for Predicting College Enrollment Based on Academic and Socioeconomic Attributes of High School Students,” Journal of Embedded System Security and Intelligent Systems, vol. 7, no. 1, 2026, doi: 10.59562/jessi.v7i1.2601. [Online]. Available: https://journal.technolabs.co.id/index.php/jotechcom/article/view/86

[15] L. Astri Nadita, S. J. Nur, S. Hidayati, M. Syahputra Novelan, M. Teknologi informasi, and U. Pembangunan Panca Budi, “A Comparative Study of Decision Tree and Neural Network Algorithms for Stroke Risk Prediction,” Journal of Technology and Computer (JOTECHCOM), vol. 3, no. 1, pp. 85–93, 2024.

[16] A. Pratama, A. Adiyatma Wicaksana, and A. Razi, “Analisa Kesesuaian Lahan Tanah Untuk Tanaman Padi (Oryza Sativa L.) Dengan Metode Decision Tree Berbasis Web (Studi Kasus : Kabupaten Aceh Utara),” Jurnal Informatika Kaputama, vol. 6, no. 1, 2022. [Online]. Available: https://scispace.com/pdf/analisa-kesesuaian-lahan-tanah-untuk tanaman-padi-oryza-24e3qlzc.pdf

[17] L. Somantri, “Pemetaan mobilitas penduduk di kawasan pinggiran Kota Bandung,” Majalah Geografi Indonesia, vol. 36, no. 2, pp. 95, Jun. 2022, doi: 10.22146/mgi.70636.

[18] Y. Fatimah and R. Meiyanti, “Klasifikasi Jenis Tanah Yang Sesuai Terhadap Tanaman Pangan Menggunakan Metode Random Forest Di Kabupaten Mandailing Natal,” in Prosiding Seminar Nasional Teknologi dan Teknik Informatika, 2024. [Online]. Available: https://proceedings.unimal.ac.id/senastika/article/view/868