SavedAdd your journal

Journals / International Journal of Engineering and Geosciences / 2026 / Volume: 11 Issue: 1

Hybrid machine learning model and terrain variables for spatial modeling of topsoil physicochemical properties

Firas Aljanabi(SELCUK UNIVERSITY)0000-0002-5122-3699
Mert Dedeoglu(SELCUK UNIVERSITY)0000-0001-8611-3724
Pages
—
Publication Date
2025-10-01
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results showed that the hybrid RFK model outperformed other machine learning models in predicting soil properties, achieving the best CCC values and the lowest RMSE and MAE, while the performance of the other models remained relatively similar and weak.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Soil surveys and mapping using conventional methods are time consuming and costly, particularly for large areas, while the demand for detailed soil data continues to grow for applications in land management and precision agriculture.
📊
Key Findings & Data:The physicochemical properties of 119 soil samples collected from the study area were analyzed.
💡
Conclusion & Impact:The results showed that the hybrid RFK model outperformed other machine learning models in predicting soil properties, achieving the best CCC values and the lowest RMSE and MAE, while the performance of the other models remained relatively similar and weak.
🔬Design:Survey & Empirical Study
📍Scope:Comprehensive Sample
⚙️Variables:Hybrid model · Kriging · Random forest

Abstract

Soil surveys and mapping using conventional methods are time consuming and costly, particularly for large areas, while the demand for detailed soil data continues to grow for applications in land management and precision agriculture. In this study, a hybrid Random Forest Kriging (RFK) model combining the machine learning capabilities of Random Forest (RF) with the spatial prediction strength of the Kriging geostatistical model was employed alongside three other machine learning algorithms: Artificial Neural Networks (ANN), Gradient Boosting Machines (GBM), and K-Nearest Neighbor (KNN). These models were utilized to predict the spatial distribution of five soil physicochemical properties: potential of Hydrogen (pH), Electrical Conductivity (EC), Calcium Carbonate (CaCO₃), Bulk Density (BD), and Available Water Capacity (AWC) in a region located in Central Anatolia, Turkey. The physicochemical properties of 119 soil samples collected from the study area were analyzed. One of the objectives of this study was to evaluate the effectiveness of low-scale terrain variables as predictors for soil property estimation. For this purpose, three auxiliary terrain variables digital elevation model (DEM), slope, and topographic roughness index (TRI) were derived from remote sensing data and analyzed using GIS techniques. The predicted maps were evaluated utilizing three statistical metrics: Concordance Correlation Coefficient (CCC), root mean square error (RMSE), and mean absolute error (MAE). The results showed that the hybrid RFK model outperformed other machine learning models in predicting soil properties, achieving the best CCC values and the lowest RMSE and MAE, while the performance of the other models remained relatively similar and weak. Furthermore, the findings indicated that the hybrid model's ability to delineate the spatial patterns of soil properties was primarily influenced by elevation and slope, despite the moderate effectiveness of low-scale terrain variables as auxiliary inputs in digital soil mapping.

🔖

Cite This Article

Aljanabi, F., Dedeoglu, M. (2025). Hybrid machine learning model and terrain variables for spatial modeling of topsoil physicochemical properties. International Journal of Engineering and Geosciences, Volume: 11 Issue: 1. https://doi.org/10.26833/ijeg.1655607

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (57)

  1. Asgarova, M. (2023). The assessment and management of soil fertility using GIS and remote sensing. Advanced Land Management, 3(2), 97-106.
  2. Pereira, G.W., Valente, D.S.M., de Queiroz, D.M., Santos, N.T., & Fernandes-Filho, E.I. (2022). Soil mapping for precision agriculture using support vector machines combined with inverse distance weighting. Precision Agriculture, 23(4), 1189-1204.
  3. Moral, F.J., Rebollo, F.J., & Serrano, J.M. (2020). Delineating site-specific management zones on pasture soil using a probabilistic and objective model and geostatistical techniques. Precision Agriculture, 21(3), 620-636.
  4. Wadoux, A.M.J.C., Minasny, B., & McBratney, A.B. (2020). Machine learning for digital soil mapping: Applications, challenges and suggested solutions. Earth-Science Reviews, 210, 103359. doi:https://doi.org/10.1016/j.earscirev.2020.103359
  5. Khaledian, Y. & Miller, B.A. (2020). Selecting appropriate machine learning methods for digital soil mapping. Applied Mathematical Modelling, 81, 401-418. doi:https://doi.org/10.1016/j.apm.2019.12.016
  6. Zhang, M., Shi, W., & Xu, Z. (2020). Systematic comparison of five machine-learning models in classification and interpolation of soil particle size fractions using different transformed data. Hydrology and Earth System Sciences, 24(5), 2505-2526.
  7. Sekulić, A., Kilibarda, M., Heuvelink, G.B., Nikolić, M., & Bajat, B. (2020). Random forest spatial interpolation. Remote Sensing, 12(10), 1687.
  8. Türk, S.T. & Balçık, F. (2023). Rastgele orman algoritması ve Sentinel-2 MSI ile fındık ekili alanların belirlenmesi: Piraziz Örneği. Geomatik, 8(2), 91-98.
  9. Pierdicca, R. & Paolanti, M. (2022). GeoAI: a review of artificial intelligence approaches for the interpretation of complex geomatics data. Geoscientific Instrumentation, Methods and Data Systems Discussions, 2022, 1-35.
  10. Efe, E. & Algancı, U. (2023). Çok zamanlı Sentinel 2 uydu görüntüleri ve makine öğrenmesi tabanlı algoritmalar ile arazi örtüsü değişiminin belirlenmesi. Geomatik, 8(1), 27-34.
  11. García Pereira, A., Ojo, A., Curry, E., & Porwol, L. (2020). Data acquisition and processing for GeoAI models to support sustainable agricultural practices.
  12. Mendes, W.d.S., Demattê, J.A.M., Barros, A.S.e., Salazar, D.F.U., & Amorim, M.T.A. (2020). Geostatistics or machine learning for mapping soil attributes and agricultural practices. Revista Ceres, 67(4), 330-336.
  13. Mariano, C. & Monica, B. (2021). A random forest-based algorithm for data-intensive spatial interpolation in crop yield mapping. Computers and Electronics in Agriculture, 184, 106094.
  14. Aljanabi, F., Dedeoğlu, M., & Şeker, C. (2024). Environmental monitoring of Land Use/Land Cover by integrating remote sensing and machine learning algorithms. Journal of Engineering and Sustainable Development, 28(4), 455-466.
  15. Abdikan, S., Sekertekin, A., Madenoglu, S., Ozcan, H., Peker, M., Pinar, M.O., Koc, A., Akgul, S., Secmen, H., Kececi, M., Tuncay, T., & Balik Sanli, F. (2023). Surface soil moisture estimation from multi-frequency SAR images using ANN and experimental data on a semi-arid environment region in Konya, Turkey. Soil and Tillage Research, 228, 105646. doi:https://doi.org/10.1016/j.still.2023.105646
  16. Soil Survey Staff. (1996). Keys to Soil Taxonomy (U.S.G.P. Office Ed. Seventh Edition ed.). Washington D.C.: USDA Natural Resources Conservation Services.
  17. Yakar, M., & Yilmaz, H. M. (2011). Determination of erosion on a small fairy chimney. Experimental Techniques, 35(5), 76-81.
  18. Kang, E., Li, Y., Zhang, X., Yan, Z., Wu, H., Li, M., Yan, L., Zhang, K., Wang, J., & Kang, X. (2021). Soil pH and nutrients shape the vertical distribution of microbial communities in an alpine wetland. Science of The Total Environment, 774, 145780. doi:https://doi.org/10.1016/j.scitotenv.2021.145780
  19. Jones, J. (2018). Soil analysis handbook of reference methods: CRC press.
  20. Shrivastava, P. & Kumar, R. (2015). Soil salinity: A serious environmental issue and plant growth promoting bacteria as one of the tools for its alleviation. Saudi journal of biological sciences, 22(2), 123-131. doi:https://doi.org/10.1016/j.sjbs.2014.12.001
  21. Junior, E.C., Gonçalves Jr, A.C., Seidel, E.P., Ziemer, G.L., Zimmermann, J., Oliveira, V.H.D.d., Schwantes, D., & Zeni, C.D. (2020). Effects of liming on soil physical attributes: a review. Journal of Agricultural Science, 12(10), 278. doi:https://doi.org/10.5539/jas.v12n10p278
  22. Hamza, M. & Anderson, W.K. (2005). Soil compaction in cropping systems: A review of the nature, causes and possible solutions. Soil and tillage research, 82(2), 121-145. doi:https://doi.org/10.1016/j.still.2004.08.009
  23. Blake, G. & Hartge, K. (1986). Particle density. Methods of soil analysis: Part 1 physical and mineralogical methods, 5, 377-382. doi:https://doi.org/10.2136/sssabookser5.1.2ed.c14
  24. Shahadha, S.S., Al-Dharob, M., Al-Jubouri, M., & Salih, R. (2023). The impact of compost and expanded perlite on soil physical properties and water productivity under different irrigation practices. Journal of Aridland Agriculture, 9, 92-98. doi:https://doi.org/10.25081/jaa.2023.v9.8654
  25. Huang, Z., Liu, Y., Tian, F.-P., & Wu, G.-L. (2020). Soil water availability threshold indicator was determined by using plant physiological responses under drought conditions. Ecological Indicators, 118, 106740. doi:https://doi.org/10.1016/j.ecolind.2020.106740
  26. Klute, A. (1986). Water retention: laboratory methods. Methods of soil analysis: part 1 physical and mineralogical methods, 5, 635-662. doi:https://doi.org/10.2136/sssabookser5.1.2ed.c26
  27. Altunel, A.O. (2023). The effect of DEM resolution on topographic wetness index calculation and visualization: An insight to the hidden danger unraveled in Bozkurt in August, 2021. International Journal of Engineering and Geosciences, 8(2), 165-172. doi:https://doi.org/10.26833/ijeg.1110560
  28. Pavlů, L., Kodešová, R., Vašát, R., Fér, M., Klement, A., Nikodem, A., & Kapička, A. (2022). Estimation of the stability of topsoil aggregates in areas affected by water erosion using selected soil and terrain properties. Soil and Tillage Research, 219, 105348. doi:https://doi.org/10.1016/j.still.2022.105348
  29. Kowalska, J.B., Zaleski, T., & Mazurek, R. (2020). Micromorphological features of soils formed on calcium carbonate–rich slope deposits in the Polish Carpathians. Journal of Mountain Science, 17(6), 1310-1332. doi:https://doi.org/10.1007/s11629-019-5829-5
  30. Guo, J., Fan, Y., Li, Y., Bi, Y., Wang, S., Hu, Y., Zhang, L., & Song, W. (2024). Topography Dominates the Spatial and Temporal Variability of Soil Bulk Density in Typical Arid Zones. Sustainability, 16(22), 9670. (Accession No. doi:10.3390/su16229670)
  31. Ünel, F. B., Kuşak, L., Yakar, M., & Doğan, H. (2023). Coğrafi bilgi sistemleri ve analitik hiyerarşi prosesi kullanarak Mersin ilinde otomatik meteoroloji gözlem istasyonu yer seçimi. Geomatik, 8(2), 107-123.
  32. Kalaiselvi, B., Chakraborty, R., Dharumarajan, S., Kumar, K.A., & Hegde, R. (2024). Spatial prediction of soil organic carbon and its stocks using digital soil mapping ". In Remote Sensing of Soils (pp. 411-428): Elsevier.
  33. Miheretu, B.A. & Yimer, A.A. (2018). Spatial variability of selected soil properties in relation to land use and slope position in Gelana sub-watershed, Northern highlands of Ethiopia. Physical Geography, 39(3), 230-245. doi:https://doi.org/10.1080/02723646.2017.1380972
  34. Yilmaz, H. M., Yakar, M., Mutluoglu, O., Kavurmaci, M. M., & Yurt, K. (2012). Monitoring of soil erosion in Cappadocia region (Selime-Aksaray-Turkey). Environmental Earth Sciences, 66(1), 75-81.
  35. Rakesh, C.J., Govindaraju, Lokanath, S., & Kishor Kumar, A. (2023). Geospatial and AHP technique in assessment of groundwater potential zones—a case study of Boranakanive reservoir catchment in India. Arabian Journal of Geosciences, 16(12), 664. doi:https://doi.org/10.1007/s12517-023-11780-9
  36. Hengl, T., Heuvelink, G.B.M., & Rossiter, D.G. (2007). About regression-kriging: From equations to case studies. Computers & Geosciences, 33(10), 1301-1315. doi:https://doi.org/10.1016/j.cageo.2007.05.001
  37. Avcı, C., Budak, M., Yağmur, N., & Balçık, F. (2023). Comparison between random forest and support vector machine algorithms for LULC classification. International Journal of Engineering and Geosciences, 8(1), 1-10. doi:https://doi.org/10.26833/ijeg.987605
  38. Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5-32. doi:https://doi.org/10.1023/A:1010933404324
  39. Buscema, M. (2002). A Brief Overview And Introduction To Artificial Neural NetworkS. Substance Use & Misuse, 37(8-10), 1093-1148. doi:https://doi.org/10.1081/JA-120004171
  40. Fantappiè, M., L'Abate, G., Schillaci, C., & Costantini, E.A.C. (2023). Digital soil mapping of Italy to map derived soil profiles with neural networks. Geoderma Regional, 32, e00619. doi:https://doi.org/10.1016/j.geodrs.2023.e00619
  41. Kalambukattu, J.G., Kumar, S., & Arya Raj, R. (2018). Digital soil mapping in a Himalayan watershed using remote sensing and terrain parameters employing artificial neural network model. Environmental Earth Sciences, 77(5), 203. doi:https://doi.org/10.1007/s12665-018-7367-9
  42. Friedman, J.H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
  43. Appelhans, T., Mwangomo, E., Hardy, D.R., Hemp, A., & Nauss, T. (2015). Evaluating machine learning approaches for the interpolation of monthly air temperature at Mt. Kilimanjaro, Tanzania. Spatial Statistics, 14, 91-113. doi:https://doi.org/10.1016/j.spasta.2015.05.008
  44. Zhang, S. & Li, J. (2021). KNN classification with one-step computation. IEEE Transactions on Knowledge and Data Engineering, 35(3), 2711-2723.
  45. Yakar, M., Yilmaz, H. M., & Yurt, K. (2010). The effect of grid resolution in defining terrain surface. Experimental Techniques, 34(6), 23-29.
  46. Geng, Z., Zhang, C., Ren, Y., Zhu, M., Chen, R., & Cheng, H. (2023). A Kriging-Random Forest Hybrid Model for Real-time Ground Property Prediction during Earth Pressure Balance Shield Tunneling. arXiv preprint arXiv:2305.05128.
  47. manian, H., Shirkhani, H., Mohammadian, A., Hiedra Cobo, J., & Payeur, P. (2023). Spatial interpolation of soil temperature and water content in the land-water interface using artificial intelligence. Water, 15(3), 473.
  48. Mammadov, E., Nowosad, J., & Glaesser, C. (2021). Estimation and mapping of surface soil properties in the Caucasus Mountains, Azerbaijan using high-resolution remote sensing data. Geoderma Regional, 26, e00411.
  49. Webster, R. & Oliver, M.A. (2007). Geostatistics for environmental scientists: John Wiley & Sons.
  50. Gallant, J.C. & Austin, J.M. (2015). Derivation of terrain covariates for digital soil mapping in Australia. Soil Research, 53(8), 895-906.
  51. Pásztor, L., Takács, K., Mészáros, J., Szatmári, G., Árvai, M., Tóth, T., Barna, G., Koós, S., Kovács, Z.A., & László, P. (2023). Indirect prediction of salt affected soil indicator properties through habitat types of a natural saline grassland using unmanned aerial vehicle imagery. Land, 12(8), 1516.
  52. Xu, L., Du, H., & Zhang, X. (2019). Spatial distribution characteristics of soil salinity and moisture and its influence on agricultural irrigation in the Ili River Valley, China. Sustainability, 11(24), 7142.
  53. Guo, P.-T., Li, M.-F., Luo, W., Tang, Q.-F., Liu, Z.-W., & Lin, Z.-M. (2015). Digital mapping of soil organic matter for rubber plantation at regional scale: An application of random forest plus residuals kriging approach. Geoderma, 237-238, 49-59. doi:https://doi.org/10.1016/j.geoderma.2014.08.009
  54. Han, H. & Suh, J. (2024). Spatial Prediction of Soil Contaminants Using a Hybrid Random Forest–Ordinary Kriging Model. Applied Sciences, 14(4), 1666.
  55. Hattar, B.I., Taimeh, A.Y., & Ziadat, F.M. (2010). Variation in soil chemical properties along toposequences in an arid region of the Levant. CATENA, 83(1), 34-45. doi:https://doi.org/10.1016/j.catena.2010.07.002
  56. eddia, M.B., Vieira, S.R., Villela, A.L.O., Mota, L.d.S., Anjos, L.H.C.d., & Carvalho, D.F.d. (2009). Topography and spatial variability of soil physical properties. Scientia Agricola, 66, 338-352.
  57. Yakar, M., Yilmaz, H. M., & Yurt, K. (2010). The effect of grid resolution in defining terrain surface. Experimental Techniques, 34(6), 23-29.