Prediction of Soil Available Phosphorus Using Machine Learning Algorithms Based on Physicochemical Properties
DOI:
https://doi.org/10.5281/zenodo.20792211Keywords:
Soil Available Phosphorus, machine learning, Feature İmportance, Precision Agriculture, Calcareous Soils.Abstract
Toprakta bulunan kullanılabilir fosfor (P) miktarını tahmin etmek, gübre kullanımını optimize etmek ve tarımsal sürdürülebilirliği artırmak için çok önemlidir. Bununla birlikte, kullanılabilirliği, geleneksel modelleme yaklaşımlarını zorlayan karmaşık, etkileşimli fizikokimyasal faktörler tarafından yönetilir. Bu çalışma, rutin olarak ölçülen toprak özelliklerine (pH, elektriksel iletkenlik, organik madde, kalsiyum karbonat ve doku fraksiyonları) dayanarak toprakta bulunan kullanılabilir P miktarını tahmin etmede dört makine öğrenme algoritmasının -Rastgele Orman (RF), Aşırı Gradyan Artırma (XGBoost), Destek Vektör Regresyonu (SVR) ve Gradyan Artırma Makinesi (GBM)- performansını değerlendirdi. Yoğun olarak işlenmiş kireçli tarım alanlarından toplam 56 yüzey toprağı örneği (0-20 cm) toplandı. Rastgele Orman modeli, 0,673'lük bir belirleme katsayısı (R²), 0,717 kg da⁻¹'lik bir kök ortalama kare hatası (RMSE) ve 0,588 kg da⁻¹'lik bir ortalama mutlak hata (MAE) ile en yüksek tahmin doğruluğunu elde etti. SHAP tabanlı özellik önem analizi, tüm modellerde en etkili değişkenler olarak elektriksel iletkenliği ve toprak organik maddesini belirleyerek, toprak kimyasal ortamının ve biyokimyasal süreçlerin P kullanılabilirliğini kontrol etmedeki rolünün altını çizmiştir. Sonuçlar, özellikle RF olmak üzere, topluluk ağacı tabanlı yöntemlerin, kireçli tarım sistemlerinde doğrusal olmayan toprak P dinamiklerini yakalamak için sağlam araçlar olduğunu göstermektedir. Bu çalışma, benzer tarımsal ekolojik bağlamlarda hassas fosfor yönetimini desteklemek ve besin kullanım verimliliğini artırmak için pratik, veri odaklı bir çerçeve sunmaktadır.
References
Alganci, U., Sertel, E., Ozdogan, M., & Ormeci, C. (2013). Parcel-level identification of crop types using different classification algorithms and multi-resolution imagery in Southeastern Turkey. Photogrammetric Engineering & Remote Sensing, 79(11), 1053–1065.
Bol, R., Julich, D., Brödlin, D., Siemens, J., Kaiser, K., Dippold, M. A., Spielvogel, S., Zilla, T., Mewes, D., von Blanckenburg, F., Puhlmann, H., & Holzmann, S. (2016). Dissolved and colloidal phosphorus fluxes in forest ecosystems—An almost blind spot in ecosystem research. Journal of Plant Nutrition and Soil Science, 179(4), 425–438.
Bouyoucos, G. J. (1962). Hydrometer method improved for making particle size analyses of soils. Agronomy Journal, 54(5), 464–465.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247–1250.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM.
El Bilali, A., Taleb, A., & Brouziyne, Y. (2021). Groundwater quality forecasting using machine learning algorithms for irrigation purposes. Agricultural Water Management, 245, 106625. https://doi.org/10.1016/j.agwat.2020.106625
Freedman, D. A. (2009). Statistical models: Theory and practice. Cambridge University Press.
Friedman, J., Hastie, T., & Tibshirani, R. (2001). The elements of statistical learning. Springer.
Frost, J. (2019). Regression analysis: An intuitive guide for using and interpreting linear models. Statistics By Jim Publishing.
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote Sensing of Environment, 202, 18–27.
Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2019). Multivariate data analysis (8th ed.). Cengage Learning.
Hinsinger, P. (2001). Bioavailability of soil inorganic P in the rhizosphere as affected by root-induced chemical changes: A review. Plant and Soil, 237(2), 173–195.
Jackson, M. L. (1973). Soil chemical analysis (2nd ed.). Prentice Hall.
Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202.
Mountrakis, G., Im, J., & Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247–259.
Nelson, R. E. (1982). Carbonate and gypsum. In A. L. Page (Ed.), Methods of soil analysis. Part 2: Chemical and microbiological properties (pp. 181–197). ASA–SSSA.
Olsen, S. R., Cole, C. V., Watanabe, F. S., & Dean, L. A. (1954). Estimation of available phosphorus in soils by extraction with sodium bicarbonate. USDA Circular No. 939.
Sahani, N., & Ghosh, T. (2021). GIS-based spatial prediction of recreational trail susceptibility in protected area of Sikkim Himalaya using logistic regression, decision tree and random forest model. Ecological Informatics, 64, 101352.
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222.
Vance, C. P., Uhde-Stone, C., & Allan, D. L. (2003). Phosphorus acquisition and use: Critical adaptations by plants for securing a nonrenewable resource. New Phytologist, 157(3), 423–447.
Walkley, A., & Black, I. A. (1934). An examination of the Degtjareff method for determining soil organic matter and a proposed modification of the chromic acid titration method. Soil Science, 37(1), 29–38.
Weng, L.-C., Elsawah, A. M., & Fang, K.-T. (2021). Cross-entropy loss for recommending efficient fold-over technique. Journal of Systems Science and Complexity, 34(1), 402–439.
Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79–82.
Wu, L., Peng, Y., Fan, J., Wang, Y., & Huang, G. (2021). A novel kernel extreme learning machine model coupled with K-means clustering and firefly algorithm for estimating monthly reference evapotranspiration in parallel computation. Agricultural Water Management, 245, 106624.
Ying, B., & Sayed, A. H. (2017). Diffusion gradient boosting for networked learning. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2512–2516). IEEE. https://doi.org/10.1109/ICASSP.2017.7952594
Zhang, Y., Li, X., Šimůnek, J., Shi, H., Chen, N., Hu, Q., & Tian, T. (2021). Evaluating soil salt dynamics in a field drip-irrigated with brackish water and leached with freshwater during different crop growth stages. Agricultural Water Management, 244, 106601.
Zuur, A. F., Ieno, E. N., & Smith, G. M. (2010). Analysing ecological data. Springer.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 ICONTECH INTERNATIONAL JOURNAL
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
