ANALYSIS OF MACHINE LEARNING ALGORITHM PERFORMANCE IN PREDICTING ULTISOL SOIL NUTRIENTS BASED ON IMPEDANCE VALUES
DOI:
https://doi.org/10.22437/jop.v9i2.32564Keywords:
Soil Nutrients, Soil Impedance, Machine Learning, Linear Model, K-Nearest Neighbors, Decision Tree, Random ForestAbstract
A study comparing the performance of machine learning algorithms to predict soil nutrient values based on soil impedance has been conducted. The algorithm models used include Linear Model, K-Nearest Neighbors (K-NN) with n-neighbors 3, 18, 21, 24, 27, and 30, Decision Tree with max depth 3, and Random Forest with n-estimators 6 and 21. During the training phase, 10 model variations with the best performance were found, including Linear Model, K-NN (n-neighbors), Decision Tree (max depth 3), and Random Forest (n-estimators 6 and 21). In the testing phase, Random Forest (n-estimator 21) showed the best performance with MAE = 0.15%, MSE = 0.09%, RMSE = 0.31%, and accuracy = 99.85%. Regression analysis indicated an R-squared value of 0.924, indicating that most of the variations in soil impedance values can be explained by variations in soil nutrient values. A regression value approaching 1 indicates that the regression model used has a very good ability to explain the variations observed in the data. This indicates that most of the variations in the dependent variable (the variable being predicted, which is the nutrient values) can be explained by the independent variable (the predictor variable, which is the soil impedance values) in the model. Correlation analysis resulted in a strong negative correlation between impedance and Al, Fe, K, Ca, Zn, Ni, Ta, V, Cr, and Mn (values -0.81 to -0.99), while a positive correlation occurred with Mg, Si, S, Cl, Ti, Zr, and Ga (values 0.65 to 0.99). This indicates that an increase in impedance values is generally followed by an increase in nutrient values.
Downloads
References
Ambarwari, A., Adrian, Q.J. and Herdiyeni, Y. 2020. Analysis of the effect of data scaling on the performance of the machine learning algorithm for plant identification. Jurnal RESTI (Rekayasa Sistem And Teknologi Informasi). 4(1) : 117-122.
Azzyati, F., Seniari, N.M. and Citarsa, I.B.F. 2019. Analisis Perbandingan Nilai Impeandsi Pentanahan Berdasarkan Panjang Elektroda Grounding Dengan Three Point Metho. Dielektrika. 6(1) : 45-54.
Bouslihim, Y., Rochdi, A. and Paaza, N.E.A. 2021. Machine learning approaches for the prediction of soil aggregate stability. Heliyon. 7(3).
Fashoto, S.G., Mbunge, E., Ogunleye, G. and den Burg, J.V. 2021. Implementation of machine learning for predicting maize crop yields using multiple linear regression and backward elimination. Malaysian Journal of Computing (MJoC). 6(1) : 679-697.
Hou, D., Guo, K., and Liu, C. 2020. Asymmetric effects of grazing intensity on macroelements and microelements in grassland soil and plants in Inner Mongolia Grazing alters nutrient dynamics of grasslands. Ecology and Evolution. 10(16) : 8916–8926.
Ifadah, N.F., Syarof, Z.N., Al Jauhary, M.R. and Musyaffa, H.J. 2021. Dasar-Dasar Manajemen Kesuburan Tanah. Malang : Universitas Brawijaya Press.
Kasno, A. 2019. Perbaikan tanah untuk meningkatkan efektivitas and efisiensi pemupukan berimbang and produktivitas lahan kering masam. Jurnal Sumberdaya Lahan. 13(1) : 27-40.
Sang, A.I., Sutoyo, E. and Darmawan, I. 2021. Analisis Data Mining Untuk Klasifikasi Data Kualitas Udara DKI Jakarta Menggunakan Algoritma Decision Tree And Support Vector Machine. Journal of Engineering. 8(5) : 8954-8963.
Subardja. D.S., S. ritung, M. Anda, Sukarman, E. Suryani, and R.E. Subandiono. 2014. Petunjuk Teknis Klasifikasi Tanah Nasional. Bogor : Balai Besar Litbang Sumberdaya Lahan Pertanian
Umaternate, G.R., Abidjulu, J. and Wuntu, A.D. 2014. Uji metode Olsen and Bray dalam menganalisis kandungan fosfat tersedia pada tanah sawah di Desa Konarom Barat Kecamatan Dumoga Utara. Jurnal MIPA. 3(1) : 6-10.
