Keywords:
- soil humus
- nutrient content
- artificial intelligence models
- remote sensing
- soil fertility
- modeling
Abstract
This article explores the use of artificial intelligence (AI) technologies for analyzing soil humus and nutrient content (mobile forms of phosphorus and potassium) using machine learning models and remote sensing data. Four datasets, combining archive and recent data with spectral indices, were used to evaluate model performance. The Ridge Classifier and Logistic Regression achieved the highest accuracy (75.0%) for humus prediction, while Random Forest proved most effective for phosphorus (66.7%) and potassium (54.7%). Results show that AI models, particularly when incorporating both historical and recent data, provide accurate and scalable solutions for soil analysis, offering significant potential for precision agriculture and sustainable land management.
References
McBratney, A.B., Santos, M.M., & Minasny, B. (2003). On digital soil mapping. Geoderma, 117 (1-2), 3-52. https://doi.org/10.1016/S0016-7061(03)00223-4.
Minasny, B., McBratney, A.B., Malone, B.P., & Wheeler, I. (2013). Digital mapping of soil carbon. In: Sparks, D.L. (Ed.), Advances in Agronomy, 118, 1-47. Academic Press. https://doi. org/10.1016/B978-0-12-405942-9.00001-7.
Hengl, T., Heuvelink, G.B.M., Kempen, B., Leenaars, J.G.B., Walsh, M.G., Shepherd, K.D., et al. (2015). Mapping soil properties of Africa at 250 m resolution: Random forests significantly improve current predictions. PLoS One, 10(6), e0125814. https://doi.org/10.1371/ journal.pone.0125814.
Malone, B.P., McBratney, A.B., Minasny, B., & Laslett, G. (2009). Mapping continuous depth functions of soil carbon storage and available water capacity. Geoderma, 154(1-2), 138-152. https://doi.org/10.1016/j.geoderma.2009.10.020.
Lacoste, M., Minasny, B., McBratney, A.B., Michot, D., Viaud, V., & Walter, C. (2014). High resolution 3D mapping of soil organic carbon in a heterogeneous agricultural landscape. Geoderma, 213, 296-311. https://doi.org/10.1016/j.geoderma.2013.07.002.
Wälder, K., Wälder, O., Rinklebe, J., & Menz, J. (2008). Estimation of soQil properties with geostatistical methods in floodplains. Archives of Agronomy and Soil Science, 54(3), 275-295. https://doi.org/10.1080/03650340801900617.
Taghizadeh-Mehrjardi, R., Minasny, B., Sarmadian, F., & Malone, B.P. (2014). Digital mapping of soil salinity in Ardakan region, central Iran. Geoderma, 213, 15-28. https://doi.org/10.1016/j. geoderma.2013.07.020.
Pahlavan-Rad, M.R., & Akbarimoghaddam, A. (2018). Spatial variability of soil texture fractions and pH in a flood plain (case study from eastern Iran). Catena, 160, 275-281. https://doi.org/10.1016/j.catena.2017.10.024.
Taghizadeh-Mehrjardi, R., Nabiollahi, K., & Kerry, R. (2016). Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma, 266, 98-110. https://doi.org/10.1016/j.geoderma.2016.03.017.
