EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting Soil Organic Carbon in Lower Depths from Surface Soil Features Using Machine Learning Methods

Lawrence Aula, Milena Maria Tomaz de Oliveira, Amanda C. Easterly, Cody F. Creech

Agronomy · 04.04.2026 · 16 (7) · 758

DOI: 10.3390/agronomy16070758 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Agronomy, online erschienen am 04.04.2026. Verfasst von Lawrence Aula und 3 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Topsoil features within a depth of 0–10 cm are vital for making soil management decisions that affect crop production. However, the use of these soil features to predict soil organic carbon (SOC) at 10–20 cm requires further investigation. The study aims to predict SOC at 10–20 cm using total nitrogen (total N), pH, cation exchange capacity (CEC), and SOC at 0–10 cm and select a suitable model for predicting SOC. This study was conducted using data from a long-term tillage, winter wheat (Triticum aestivum L.)-fallow experiment established in autumn 1970. Treatments included moldboard plow, stubble mulch, no-till, and native sod, each replicated three times. Soil samples were collected from each plot at depths of 0–10 cm and 10–20 cm in April of 2010 and 2011. Models were fit using ordinary least squares (OLS), least absolute shrinkage and selection operator (LASSO), random forests, and Bayesian additive regression trees (BART). Using root mean square error (RMSE), SOC was predicted with an accuracy of 1.44 g kg−1 or relative RMSE (rRMSE) of 13.5%. This was achieved with the OLS model that used total N, pH, and CEC as predictors. The good performance of the OLS model over more flexible machine learning approaches suggests that the information predictors provide about the response variable (SOC) is approximately linear. As the agricultural dataset was small (n = 24), the less complex model reduced the chances of overfitting while keeping the variance relatively low. Random forests and BART had an rRMSE greater than 21%. Statistical models could be used to estimate SOC at 10–20 cm and reduce destructive soil analysis methods.

Zitieren

APA

Aula, L., Oliveira, M. M. T. D., Easterly, A. C., & Creech, C. F. (2026). Predicting Soil Organic Carbon in Lower Depths from Surface Soil Features Using Machine Learning Methods. Agronomy, 16(7), 758. https://doi.org/10.3390/agronomy16070758

Vancouver

Aula L, Oliveira MMTD, Easterly AC, Creech CF. Predicting Soil Organic Carbon in Lower Depths from Surface Soil Features Using Machine Learning Methods. Agronomy. 2026;16(7):758. doi:10.3390/agronomy16070758

BibTeX
@article{Aula2026,
  author = {Aula, Lawrence and Oliveira, Milena Maria Tomaz de and Easterly, Amanda C. and Creech, Cody F.},
  title = {Predicting Soil Organic Carbon in Lower Depths from Surface Soil Features Using Machine Learning Methods},
  journal = {Agronomy},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {758},
  doi = {10.3390/agronomy16070758}
}
Kostenlos starten →