Determination of Organic Carbon Content of the Soils within the Greenhouses Built on Pyroclastic Deposits in Isparta Settlement Area

Year 2025, Volume: 8 Issue: 1, 7 - 8

Sinan Demir , Mehmet Emre Çağ

https://doi.org/10.47115/bsagriculture.1565025

Abstract

Soil organic carbon (SOC) is an important indication of soil health and helps to sustain soil fertility. As a result, determining its composition and the factors that influence it is critical for long-term soil nutrient management, especially in controlled conditions such as greenhouses. This study utilizes machine learning to classify SOC content in greenhouses built on pyroclastic deposits in the Isparta region. A dataset of 276 samples and eight variables—clay (%), silt (%), sand (%), soil electrical conductivity (EC), pH, elevation, slope, and aspect—were used to model SOC values. SOC content was classified into five classifications: very low (<0.6%), low (0.6-1.2%), medium (1.2-1.8%), good (1.8-2.3%), and high (>2.3%). In this study, five machine learning models—Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF)—were evaluated using cross-validation to determine their classification accuracy, precision, recall, F-score, and ROC area. Random Forest (RF) and Decision Tree (DT) outperformed the other models, with RF achieving the highest overall accuracy (76.4%), precision (77.3%), and AUC (0.904), followed by DT at 75.4% and AUC of 0.874. This study shows the practicality of machine learning models in categorizing SOC content, highlighting their importance for long-term soil health and fertility control in greenhouse conditions. To improve model efficacy, future studies should include more auxiliary variables, such as soil physical and chemical qualities and lithological data, as well as a wider range of soil types.

Keywords

Soil organic carbon (SOC), Machine learning, Greenhouses, Classification models, Topography, Soil properties, Volcanic materials

Ethical Statement

This study did not involve human subjects, human material, or human data; therefore, ethical approval and informed consent are not applicable. Furthermore, the research did not involve animals or cell lines. Not applicable.

Supporting Institution

This work was supported by the Research Project Support Programme for Undergraduate Students (2209-A) of the Scientific and Technological Research Council of Türkiye (TUBITAK) under project number 1919B012209637. The funding body had no role in the design of the experiment, the collection, analysis, and interpretation of data, or in the writing of the manuscript. The relevant website for TUBITAK is https://tubitak.gov.tr/en/scholarships/lisans-onlisans/destek-programlari/2209-research-project-su

Project Number

1919B012209637

Thanks

This study is based on data derived from the project numbered 1919B012209637, supported by the Research Project Support Programme for Undergraduate Students (2209-A) of the Scientific and Technological Research Council of Türkiye (TUBITAK). I would like to express my sincere gratitude to TUBITAK for their generous funding and support, which enabled this research. I would also like to acknowledge the contributions of individuals who provided invaluable assistance throughout the project.

References

• Agaba S, Ferré C, Musetti M, Comolli R. 2024. Mapping soil organic carbon stock and uncertainties in an alpine valley (Northern Italy) using machine learning models. Land, 13(1): 62-78. https://doi.org/10.3390/land13010078
• Alaboz P, Dengiz O, Demir S. 2021. Barley yield estimation performed by ANN integrated with the soil quality index modified by biogas waste application. Zemdirbyste, 108(3): 217-226. https://doi.org/10.13080/z-a.2021.108.028