EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Application of Vis–NIR Spectroscopy and Machine Learning for Assessing Soil Organic Carbon in the Sierra Nevada de Santa Marta, Colombia

Marlon Jose Yacomelo Hernández, William Ipanaqué Alama, Andrea C. Montenegro, Oscar de Jesús Córdoba, Darío Castañeda Sanchez, Cesar Vargas García, Elias Flórez Cordero, Jim Castillo Quezada, Carlos Pacherres Herrera, Luis Fernando Prado-Castillo, Oscar Casas Leuro

Sustainability · 04.01.2026 · 18 (1) · 513

DOI: 10.3390/su18010513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sustainability, online erschienen am 04.01.2026. Verfasst von Marlon Jose Yacomelo Hernández und 10 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Colombian Agricultural Research Corporation, Ministry of Sciences, Ecopetrol, Sustainable Landscape Approach to the Production of Premium “Sierra Nevada” Cocoa in PDET Municipalities in the Departments of Magdalena and La Guajira.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soil organic carbon (SOC) is an essential indicator of soil fertility, health, and carbon sequestration capacity. Its proper management improves soil structure, productivity, and resilience to climate change, making rapid and reliable SOC assessment essential for sustainable agriculture. Visible and near-infrared (Vis–NIR) spectroscopy offers a non-destructive and cost-effective alternative to conventional laboratory analyses, allowing for the simultaneous estimation of multiple soil properties from a single spectrum. This study aimed to predict SOC content using machine learning techniques applied to Vis–NIR spectra of 860 soil samples collected in the Sierra Nevada de Santa Marta, Colombia. The spectra (400–2500 nm) were acquired using a NIR spectrophotometer, and the soil organic carbon (SOC) content was quantified using a wet oxidation method that employs dichromate in an acidic medium. A hybrid modeling framework combining Random Forest (RF) with support vector regression (SVR) and XGBoost was implemented. Spectral pretreatments (Savitzky–Golay first derivative, MSC, and SNV) were compared, and spectral bands were selected every 10 nm. The 30 most relevant wavelengths were identified using RF importance analysis. Data were divided into training (80%) and test (20%) subsets using stratified random sampling, and five-fold cross-validation was applied for parameter optimization and overfitting control. The RF–XGBoost (R2 = 0.86) and RF–SVR (R2 = 0.85) models outperformed the individual RF and SVR models (R2 < 0.7). The proposed hybrid approach, optimized through features, and advanced spectral preprocessing demonstrate a robust and scalable framework for rapid prediction of SOC and sustainable soil monitoring.

Förderung

  • Colombian Agricultural Research Corporation
  • Ministry of Sciences, Ecopetrol
  • Sustainable Landscape Approach to the Production of Premium “Sierra Nevada” Cocoa in PDET Municipalities in the Departments of Magdalena and La Guajira

Zitieren

APA

Hernández, M. J. Y., Alama, W. I., Montenegro, A. C., Córdoba, O. D. J., Sanchez, D. C., García, C. V., Cordero, E. F., Quezada, J. C., Herrera, C. P., Prado-Castillo, L. F., & Leuro, O. C. (2026). Application of Vis–NIR Spectroscopy and Machine Learning for Assessing Soil Organic Carbon in the Sierra Nevada de Santa Marta, Colombia. Sustainability, 18(1), 513. https://doi.org/10.3390/su18010513

Vancouver

Hernández MJY, Alama WI, Montenegro AC, Córdoba ODJ, Sanchez DC, García CV, et al. Application of Vis–NIR Spectroscopy and Machine Learning for Assessing Soil Organic Carbon in the Sierra Nevada de Santa Marta, Colombia. Sustainability. 2026;18(1):513. doi:10.3390/su18010513

BibTeX
@article{Hernndez2026,
  author = {Hernández, Marlon Jose Yacomelo and Alama, William Ipanaqué and Montenegro, Andrea C. and Córdoba, Oscar de Jesús and Sanchez, Darío Castañeda and García, Cesar Vargas and Cordero, Elias Flórez and Quezada, Jim Castillo and Herrera, Carlos Pacherres and Prado-Castillo, Luis Fernando and Leuro, Oscar Casas},
  title = {Application of Vis–NIR Spectroscopy and Machine Learning for Assessing Soil Organic Carbon in the Sierra Nevada de Santa Marta, Colombia},
  journal = {Sustainability},
  year = {2026},
  volume = {18},
  number = {1},
  pages = {513},
  doi = {10.3390/su18010513}
}
Kostenlos starten →