Klasifikasi Jenis Pupuk yang Tepat Berdasarkan Jenis Tanaman dan Kondisi Lahan Menggunakan Random Forest
DOI:
https://doi.org/10.65309/frecfb05Keywords:
Klasifikasi Pupuk, Random Forest, Kondisi Lahan, Pertanian Presisi, Data MiningAbstract
Penelitian ini bertujuan untuk mengembangkan model berbasis Random Forest untuk memberikan rekomendasi jenis pupuk yang tepat berdasarkan kondisi tanah dan jenis tanaman. Data yang digunakan mencakup informasi tentang pH tanah, kelembapan, tekstur tanah, serta kandungan unsur hara (N, P, K) dan jenis tanaman yang meliputi Jagung, Padi, Kacang Tanah, dan lainnya. Model yang dikembangkan diuji pada dataset yang terdiri dari 600 sampel, dengan 30% digunakan untuk data uji. Hasil penelitian menunjukkan bahwa model Random Forest mencapai akurasi 97,83% dengan precision dan recall yang sangat baik pada sebagian besar kelas. Namun, kesalahan klasifikasi terjadi pada kelas NPK, dengan nilai recall 81,82%, yang mengindikasikan adanya kesulitan model dalam mengklasifikasikan jenis pupuk ini. Meskipun demikian, model ini menunjukkan kinerja yang baik dalam memberikan rekomendasi pupuk yang sesuai, yang dapat membantu petani memilih pupuk yang tepat dan meningkatkan hasil pertanian. Penelitian ini juga menunjukkan bahwa faktor-faktor seperti pH tanah dan jenis tanaman merupakan variabel yang sangat penting dalam menentukan jenis pupuk yang sesuai.
References
Deshpande, R., & Golegaonkar, P. (2025). Machine learning platform for agricultural predictions and recommendations. In M. S. Uddin & J. C. Bansal (Eds.), Proceedings of International Joint Conference on Advances in Computational Intelligence (pp. 123–134). Springer. https://doi.org/10.1007/978-981-96-3762-1_9
Ding, Y., & Zhang, W. (2023). Quantitative analysis of fertilizer using laser-induced breakdown spectroscopy. Frontiers in Chemistry, 11, 1–9. https://www.frontiersin.org/journals/chemistry/articles/10.3389/fchem.2023.1123003/full
Goyal, A., & Sharma, S. (2024). Crop and fertilizer recommendation using machine learning. International Journal of Novel Research and Development, 9(4), 1–8. Retrieved from https://www.ijnrd.org/papers/IJNRD2404212.pdf
Haq, I., & Ahmad, S. (2023). Optimizing machine learning models for soil fertility analysis. DergiPark Journal, 8(5), 1–10. Retrieved from https://dergipark.org.tr/en/download/article-file/4459322
Lad, S., & Thilakarathne, R. (2022). Comparative analysis of supervised learning methods for crop recommendation. Engineering Proceedings, 58, 97. https://www.researchgate.net/publication/381281441
Montañez, J. J., & Sarmiento, J. (2024). Machine learning for the detection of soil pH, macronutrients, and micronutrients with crop and fertilizer recommendations. International Journal of Artificial Intelligence, 14(1), 439–446. https://doi.org/10.11591/ijai.v14.i1.pp439-446
Qi, J., & Zhang, T. (2024). Rapid classification of agricultural fertilizers by laser-induced breakdown spectroscopy and random forest. Spectrochimica Acta Part B: Atomic Spectroscopy, 149, 288–293. https://www.sciencedirect.com/science/article/pii/S0584854718301453
Reddy, V., & Varshini, V. (2023). Hybrid approaches in crop recommendation systems. International Journal of Research in Agronomy, 2(1), 7–11. https://doi.org/10.46632/eae/2/1/5
Reddy, V., & Varshini, V. (2023). Hybrid approaches in crop recommendation systems. International Journal of Research in Agronomy, 2(1), 7–11. https://doi.org/10.46632/eae/2/1/5
Rohan, V. N., & Chaitanya, J. (2024). A machine learning-based fertilizer recommendation system for sustainable crop yield. International Research Journal of Education and Technology, 6(12), 1777–1785. https://doi.org/10.46632/irjet/6/12/5
Senesi, G. S., & Romano, R. A. (2024). Laser-induced breakdown spectroscopy associated with multivariate analysis applied to discriminate fertilizers of different nature. Journal of Applied Spectroscopy, 84(5), 923–928. https://link.springer.com/article/10.1007/s10812-017-0566-4
Senesi, G. S., & Romano, R. A. (2024). Laser-induced breakdown spectroscopy associated with multivariate analysis applied to discriminate fertilizers of different nature. Journal of Applied Spectroscopy, 84(5), 923–928. https://link.springer.com/article/10.1007/s10812-017-0566-4
Shingade, S., & Pandit, S. (2025). An approach for crop recommendation with uncertainty estimation using machine learning. Journal of Agricultural Informatics, 16(1), 1–12. https://doi.org/10.1016/j.jagif.2025.01.001
Wetzel, W., & Workman, J. (2025). Revolutionizing fertilizer analysis: Raman spectroscopy and machine learning deliver precision and speed. Spectroscopy Online. Retrieved from https://www.spectroscopyonline.com/view/revolutionizing-fertilizer-analysis-raman-spectroscopy-and-machine-learning-deliver-precision-and-speed
Yang, X., & Zhang, Y. (2025). Improving soil pH prediction and mapping using anthropogenic data. Journal of Environmental Management, 248, 1–10. https://www.tandfonline.com/doi/full/10.1080/10106049.2025.2482699
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ayu Utari Nasution, P.P.P.A.N.W.Fikrul Ilmi R.H.Zer (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
