Perbandingan Model Decision Tree dan Random Forest untuk Penentuan Kesesuaian Lahan Budidaya Cabai dan Terong
DOI:
https://doi.org/10.30865/jurikom.v12i5.8672Keywords:
Land Suitability, Random Forest, Decision Tree, Chili and Eggplant Cultivation, Kesesuaian Lahan, Budidaya Cabai dan TerongAbstract
Kabupaten Aceh Barat memiliki potensi besar dalam budidaya tanaman hortikultura seperti cabai dan terong, meskipun karakteristik tanah gambut dengan tingkat keasaman tinggi dan variabilitas lingkungan menjadi tantangan utama. Penentuan kesesuaian lahan yang akurat memerlukan analisis berbagai variabel seperti pH tanah, kelembaban tanah dan udara, curah hujan, serta tekstur tanah. Penelitian ini bertujuan mengembangkan model klasifikasi kesesuaian lahan menggunakan algoritma Decision Tree dan Random Forest untuk tanaman cabai dan terong di wilayah tersebut. Data lingkungan dan karakteristik tanah dianalisis menggunakan kedua metode tersebut untuk mengevaluasi performa klasifikasi. Hasil penelitian menunjukkan bahwa algoritma Random Forest unggul dengan akurasi mencapai 99% pada klasifikasi lahan cabai, serta nilai precision dan recall yang lebih tinggi dibandingkan Decision Tree. Untuk klasifikasi lahan terong, kedua algoritma menunjukkan performa sempurna dengan akurasi dan metrik evaluasi mencapai 1.00 tanpa kesalahan klasifikasi. Keunggulan Random Forest terletak pada kemampuannya menangani variabel input yang kompleks dan mengurangi risiko overfitting melalui ensemble pohon keputusan, sehingga menghasilkan prediksi yang lebih stabil dan andal. Dengan demikian, Random Forest sangat cocok digunakan dalam sistem klasifikasi kesesuaian lahan berbasis data lingkungan di Aceh Barat, mendukung pengambilan keputusan budidaya yang lebih optimal dan berkelanjutan. Penelitian ini memberikan kontribusi penting dalam penerapan teknologi machine learning untuk meningkatkan efisiensi dan hasil produksi pertanian di wilayah dengan karakteristik tanah gambut yang menantang.
Abstract. Kabupaten Aceh Barat has great potential for cultivating horticultural crops such as chili peppers and eggplants, despite the challenges posed by peat soil characteristics with high acidity levels and environmental variability. Accurate land suitability determination requires analysis of various variables such as soil pH, soil and air moisture, rainfall, and soil texture. This study aims to develop land suitability classification models using Decision Tree and Random Forest algorithms for chili and eggplant crops in the region. Environmental data and soil characteristics were analyzed using both methods to evaluate classification performance. The results show that the Random Forest algorithm outperforms with an accuracy of up to 99% in chili land classification, as well as higher precision and recall values compared to Decision Tree. For eggplant land classification, both algorithms demonstrated perfect performance with accuracy and evaluation metrics reaching 1.00 without any misclassification. The advantage of Random Forest lies in its ability to handle complex input variables and reduce the risk of overfitting through ensemble decision trees, resulting in more stable and reliable predictions. Therefore, Random Forest is highly suitable for use in land suitability classification systems based on environmental data in West Aceh, supporting more optimal and sustainable cultivation decision-making. This study makes an important contribution to the application of machine learning technology to improve agricultural efficiency and production outcomes in regions with challenging peat soil characteristics.
References
[1] S. Jailani, R. Ratnawaty, N. Nasruddin, F. Faisal, and I. Ismadi, “Respon Tanaman Terung (Solanum melongena L.) Pada Berbagai Media Tanaman dan Dosis Pupuk NPK,” J. Agrium, vol. 16, no. 2, p. 151, 2019, doi: 10.29103/agrium.v16i2.5867.
[2] R. Wirosoedarmo et al., “101338-None-E82914Wirosoedarmo, R., Sutanhaji, A. T., Kurniati, E., Gdwd, V., Ehuxsd, D., Nolpdwrorjl, G., Dk, Z., Kdvlo, G. D. Q., Odsdqjdq, S., & Vlidw, W. (2011). 101338-None-E82914Ba. 31(1).Ba,” vol. 31, no. 1, 2011.
[3] P. D. Wijaya, “Evaluasi Kesesuaian Lahan untuk Pengembangan Budidaya Udang Windu ( Penaeus Monodon ) Sistem Silvofishery di Kecamatan Seruway,” vol. 13, no. 2, pp. 111–119, 2024.
[4] F. Fatkurahman, M. A. Azis, Y. Rahim, R. Rahman, and S. Apriliani, “Evaluasi Kesesuaian Lahan untuk Tanaman Jagung (Zea mays L.) di Kecamatan Taluditi, Kabupaten Pohuwato,” J. Lahan Pertan. Trop., vol. 2, no. 1, pp. 72–80, 2023, doi: 10.56722/jlpt.v2i1.20601.
[5] U. Hasanah, Khusrizal, Muliana, H. Akbar, and Yusra, “Determinasi Kesesuaian Lahan Tanaman Padi Sawah Irigasi Pendahuluan Metode Penelitian,” J. Ilm. Mhs. Agroekoteknologi, vol. 1, no. 4, pp. 81–86, 2022.
[6] S. Nurwahdani, R. S. Handayani, L. Nazirah, and A. Inayatillah, “Perbandingan pertumbuhan dan hasil berbagai varietas bawang merah (,” vol. 11, pp. 68–75, 2024.
[7] A. Amir et al., “Mapping Agricultural Land Use in Aceh Barat By Using Gis,” Communnity Dev. J., vol. 5, no. 2, pp. 3302–3307, 2024.
[8] F. Al Farikhi and R. W. D. Pramono, “Perbandingan algoritma classification and regression tree (cart) dan random forest (rf) untuk klasifikasi penggunaan lahan pada google earth engine,” J. Spat. Wahana Komun. dan Inf. Geogr., vol. 23, no. 2, pp. 170–179, 2023, doi: 10.21009/spatial.232.09.
[9] V. F. Rodriguez-Galiano, B. Ghimire, J. Rogan, M. Chica-Olmo, and J. P. Rigol-Sanchez, “An assessment of the effectiveness of a random forest classifier for land-cover classification,” ISPRS J. Photogramm. Remote Sens., vol. 67, no. 1, pp. 93–104, Jan. 2012, doi: 10.1016/J.ISPRSJPRS.2011.11.002.
[10] T. M. Berhane et al., “Decision-tree, rule-based, and random forest classification of high-resolution multispectral imagery for wetland mapping and inventory,” Remote Sens., vol. 10, no. 4, 2018, doi: 10.3390/rs10040580.
[11] A. D. Purwanto, K. Wikantika, A. Deliar, and S. Darmawan, “Decision Tree and Random Forest Classification Algorithms for Mangrove Forest Mapping in Sembilang National Park, Indonesia,” Remote Sens., vol. 15, no. 1, 2023, doi: 10.3390/rs15010016.
[12] B. A. Ganati, “Predicting Land Suitability for Wheat and Barley Crops using Machine Learning Techniques,” pp. 1–19, 2025.
[13] I. Khosravi, “Towards sustainable agriculture in Iran using a machine learning-driven crop mapping framework,” Eur. J. Remote Sens., vol. 58, no. 1, Dec. 2025, doi: 10.1080/22797254.2025.2490787.
[14] A. F. Azmi, “Prediksi Churn Nasabah Bank Menggunakan Klasifikasi Random Forest Dan Decision Tree Dengan Evaluasi Confusion Matrix,” Komputa J. Ilm. Komput. dan Inform., vol. 13, no. 1, pp. 111–119, 2024, [Online]. Available: https://ojs.unikom.ac.id/index.php/komputa/article/view/12639
[15] H. L. Smith, P. J. Biggs, N. P. French, A. N. H. Smith, and J. C. Marshall, “Lost in the Forest: Encoding categorical variables and the absent levels problem,” Data Min. Knowl. Discov., vol. 38, no. 4, pp. 1889–1908, 2024, doi: 10.1007/s10618-024-01019-w.
[16] J. Quinlan, “C4.5 Programs for Machine Learning,” Morgan Kaufmann Publishers, United States. Accessed: May 24, 2025. [Online]. Available: https://www.scirp.org/reference/referencespapers?referenceid=2554378
[17] S. Bishnoi and B. K. Hooda, “Decision Tree Algorithms and their Applicability in Agriculture for Classification,” J. Exp. Agric. Int., vol. 44, no. 7, pp. 20–27, 2022, doi: 10.9734/jeai/2022/v44i730833.
[18] F. Fadhila and P. S. Hasugian, “Application of C4.5 Algorithm to Prediction Sales at PT. Sumber Sayur Segar,” J. Intell. Decis. Support Syst., vol. 5, no. 1, pp. 10–19, 2022, doi: 10.35335/idss.v5i1.45.
[19] D. Istiawan and L. Khikmah, “Implementation of C4.5 Algorithm for Critical Land Prediction in Agricultural Cultivation Areas in Pemali Jratun Watershed,” Indones. J. Artif. Intell. Data Min., vol. 2, no. 2, p. 67, 2019, doi: 10.24014/ijaidm.v2i2.7569.
[20] I. Rahmayuni, “Perbandingan Performansi Algoritma C4.5 dan Cart Dalam Klasifikasi Data Nilai Mahasiswa Prodi Teknik Komputer Politeknik Negeri Padang,” Teknoif, vol. 2, no. 1, pp. 40–46, 2014.
[21] Kusrini and Luthfi E.T, Algoritma Data Mining. Yogyakarta: CV Andi Offset. Yogyakarta: CV Andi Offset, 2009.
[22] E. Prasetyo, Data Mining Mengolah data Menjadi Informasi Menggunakan Matlab. Yogyakarta: ANDI. 2014.
[23] J. W. Yuda, H. Audytra, and N. Mahmudah, “Sistem Klasifikasi Tingkat Kerusakan Kunci Motor Menggunakan Random Forest dengan Hyperparameter Tuning,” JURIKOM (Jurnal Ris. Komputer), vol. 12, no. 2, pp. 84–94, 2025, doi: 10.30865/jurikom.v12i2.8517.
[24] N. G. Ramadhan, F. D. Adhinata, A. Jala, T. Segara, and D. Putra, “Deteksi Berita Palsu Menggunakan Metode Random Forest dan Logistic Regression,” JURIKOM (Jurnal Ris. Komputer), vol. 9, no. 2, pp. 251–256, 2022, doi: 10.30865/jurikom.v9i2.3979.
[25] N. G. Ramadhan and A. Romadhony, “Preprocessing Handling to Enhance Detection of Type 2 Diabetes Mellitus based on Random Forest,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 7, pp. 223–228, 2021.
[26] S. Pareeth, P. Karimi, M. Shafiei, and C. De Fraiture, “Mapping Agricultural Landuse Patterns from Time Series of Landsat 8 Using Random Forest Based Hierarchial Approach,” 2019, doi: 10.3390/rs11050601.
[27] A. Pang, M. W. L. Chang, and Y. Chen, “Evaluation of Random Forests ( RF ) for Regional and Local-Scale Wheat Yield Prediction in Southeast Australia,” pp. 1–19, 2022.
[28] F. Bolikulov, R. Nasimov, A. Rashidov, F. Akhmedov, and Y. I. Cho, “Effective Methods of Categorical Data Encoding for Artificial Intelligence Algorithms,” Mathematics, vol. 12, no. 16, 2024, doi: 10.3390/math12162553.
