ANALYSIS OF OIL PALM PLANT NUTRIENT PREDICTION USING THE RANDOM FOREST REGRESSION METHOD
DOI:
https://doi.org/10.53840/ejpi.v12i5.322Keywords:
Palm Oil Nutrition; Remote Sensing; Random Forest Regression; MultispectralAbstract
Palm oil is an important commodity for the Indonesian economy, with a major role in the export sector and labor absorption. Monitoring and management of nutrition in oil palm plantations is essential to ensure optimal productivity and yield quality. This study aims to develop a nutrient prediction system for oil palm plants using multispectral drone photo-based remote sensing technology, which includes the elements nitrogen (N), phosphorus (P), potassium (K), and magnesium (Mg). By utilizing the Random Forest Regression (RFR) method, this study can identify plant nutrient deficiencies more efficiently and accurately. The results showed that the RFR model was able to provide nutrient predictions with an adequate level of accuracy, where the R-squared (R²) values for nitrogen, phosphorus, potassium, and magnesium nutrients reached 0.641, 0.601, 0.558, and 0.765, respectively. This study concludes that remote sensing methods and RFR models are effective alternatives for monitoring plant nutrition broadly, so that they can help plantations in making more efficient and sustainable fertilization decisions.
Downloads
References
Arini, D., Sari, S. M., & Driptufany, D. M. (2022). The Use of Landsat 8 Imagery to Detect the Health Level of Oil Palm Plants Using the Normalized Difference Vegetation Index (NDVI) Method in Bengkalis Regency, Mandau District. El-Jughrafiyah, 2(2), 50. https://doi.org/10.24014/jej.v2i2.18744
Ariyanto, M. H., Prilianti, K. R., & ... (2022). Method of Rapid Measurement of Nutrient Content of Oil Palm Plants with Remote Sensing and Artificial Intelligence Methods. National Seminar on the Environment..., September, 3218–3228.
Armita, D., Wahdaniyah, W., Hafsan, H., & Al Amanah, H. (2022). Visual diagnosis of essential nutrient problems in different types of plants. Technoscience: Science and Technology Information Media, 16(1), 139–150. https://doi.org/10.24252/teknosains.v16i1.28639
Evrilia, N. (2020). Analysis of the level of productivity and health of oil palm using multi-species and lidar aerial photo data (Case Study: Batin XXIV District, Jambi Province).
Hakim, A. R., Atmaja, D. M. U., Basri, A., & Syafii, M. (2023). Implementation of Random Forest Algorithm on Palm Oil Price Data. Journal Of Tech- E, 6(2), 34–42. http://bsti.ubd.ac.id/e-jurnal
Kurnia, D., & Yulianandha, A. (2019). The use of NDVI (Normalized Difference Vegetation Index) and SAVI (Soil Adjusted Vegetation Index) methods to determine the availability of green open space to meet oxygen needs (Case Study: Yogyakarta City).
Li, Y., Zou, C., Berecibar, M., Nanini-Maury, E., Chan, J. C. W., van den Bossche, P., Van Mierlo, J., & Omar, N. (2018). Random forest regression for online capacity estimation of lithium-ion batteries. Applied Energy, 232(September), 197–210. https://doi.org/10.1016/j.apenergy.2018.09.182
Lillo-Bravo, I., Vera-Medina, J., Fernandez-Peruchena, C., Perez-Aparicio, E., Lopez-Alvarez, J. A., & Delgado-Sanchez, J. M. (2023). Random Forest model to predict solar water heating system performance. Renewable Energy, 216(July), 119086. https://doi.org/10.1016/j.renene.2023.119086
Mustajab, R. (2022). The area of Indonesia's oil palm plantations is almost 15 million hectares in 2022. https://dataindonesia.id/agribisnis-kehutanan/detail/luas-kebun%02sawit-indonesia-hampir-15-juta-hektare-pada-2022
Nasution, S. H., Hanum, C., & Ginting, J. (2014). Growth of Oil Palm Seedlings (Elaeis guineensis Jacq.) On Various Comparisons of Solid Decanter Planting Media and Empty Oil Palm Bunches in the Single Stage System. Online Journal of Agrotechnology, 2(2), 691–701.
Pahan, I. (2021). A Guide to Oil Palm Cultivation for Plantations. Self-Sustaining Spreader.
Pangestu, N. H. A., & Banowati, G. (2023). Mapping of oil palm plantation health based on the value of the Normalized Difference Vegetation Index (NDVI) using Landsat-8 imagery in the plantation of PT. Utility Potential. Agriprima: Journal of Applied Agricultural Sciences, 7(1), 40–49. https://doi.org/10.25047/agriprima.v7i1.513
Samuel, Prilianti, K. R., Setiawan, H., Mimboro, P., & Correspondence, P. (2022). Oil Palm Plantation Using Convolutional Neural Network (CNN) Model in Information System Software The Method of Automatic Tree Detection on Oil Palm Plantation Images Using Convolutional Neural Network (CNN) Model Using. Journal of Information Technology and Computer Science (JTIIK), 9(7), 1689–1698. https://doi.org/10.25126/jtiik.202296772
Wahyudi, B. (2022). Predict App Rank on Google Play Using the Random Forest Method. National Journal of Computer Technology, 2(1), 38–47. https://doi.org/10.61306/jnastek.v2i1.25
Wijaya, N. A., & Silalahi, D. D. (2018). Identification Nutrional Deficiencies In Oil Palm Plantations PT. Smart Tbk., Using Remote Sensing. JOM UR, 5(2).
Wulandari, N. (2020). The use of ndvi (Normalized Difference Vegetation Index) and Savi (Soil Adjusted Vegetation Index) methods to determine the availability of open space.... ITM Civil Engineering Journal. http://eprints.itn.ac.id/4597/
Xie, X., Wu, T., Zhu, M., Jiang, G., Xu, Y., Wang, X., & Pu, L. (2021). Comparison of random forest and multiple linear regression models for estimation of soil extracellular enzyme activities in agricultural reclaimed coastal saline land. Ecological Indicators, 120, 106925. https://doi.org/10.1016/j.ecolind.2020.106925
Yuniasih, B., & Adjie, A. R. P. (2022). Evaluation of Oil Palm Plantation Conditions Using NDVI Index from Sentinel 2 Satellite Imagery. Journal of Technocracy, 16(2), 127. https://doi.org/10.24198/jt.vol16n2.10
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 e-Jurnal Penyelidikan dan Inovasi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
