An Optimized Multi-Stage Framework for Soil Organic Carbon Estimation in Citrus Orchards Based on FTIR Spectroscopy and Hybrid Machine Learning Integration

Yingying Wei, Xiaoxiang Mo, Shengxin Yu, Saisai Wu, He Chen, Yuanyuan Qin and Zhikang Zeng ()
Additional contact information
Yingying Wei: Guangxi Academy of Agricultural Sciences, Nanning 530007, China
Xiaoxiang Mo: Guangxi Academy of Agricultural Sciences, Nanning 530007, China
Shengxin Yu: Guangxi Vocational & Technical Institute of Industry, Nanning 530001, China
Saisai Wu: Guangxi Academy of Agricultural Sciences, Nanning 530007, China
He Chen: Guangxi Academy of Agricultural Sciences, Nanning 530007, China
Yuanyuan Qin: Guangxi Academy of Agricultural Sciences, Nanning 530007, China
Zhikang Zeng: Guangxi Academy of Agricultural Sciences, Nanning 530007, China

Agriculture, 2025, vol. 15, issue 13, 1-21

Abstract: Soil organic carbon (SOC) is a critical indicator of soil health and carbon sequestration potential. Accurate, efficient, and scalable SOC estimation is essential for sustainable orchard management and climate-resilient agriculture. However, traditional visible–near-infrared (Vis–NIR) spectroscopy often suffers from limited chemical specificity and weak adaptability in heterogeneous soil environments. To overcome these limitations, this study develops a five-stage modeling framework that systematically integrates Fourier Transform Infrared (FTIR) spectroscopy with hybrid machine learning techniques for non-destructive SOC prediction in citrus orchard soils. The proposed framework includes (1) FTIR spectral acquisition; (2) a comparative evaluation of nine spectral preprocessing techniques; (3) dimensionality reduction via three representative feature selection algorithms, namely the Successive Projections Algorithm (SPA), Competitive Adaptive Reweighted Sampling (CARS), and Principal Component Analysis (PCA); (4) regression modeling using six machine learning algorithms, namely the Random Forest (RF), Support Vector Regression (SVR), Gray Wolf Optimized SVR (SVR-GWO), Partial Least Squares Regression (PLSR), Principal Component Regression (PCR), and the Back-propagation Neural Network (BPNN); and (5) comprehensive performance assessments and the identification of the optimal modeling pathway. The results showed that second-derivative (SD) preprocessing significantly enhanced the spectral signal-to-noise ratio. Among feature selection methods, the SPA reduced over 300 spectral bands to 10 informative wavelengths, enabling efficient modeling with minimal information loss. The SD + SPA + RF pipeline achieved the highest prediction performance (R 2 = 0.84, RMSE = 4.67 g/kg, and RPD = 2.51), outperforming the PLSR and BPNN models. This study presents a reproducible and scalable FTIR-based modeling strategy for SOC estimation in orchard soils. Its adaptive preprocessing, effective variable selection, and ensemble learning integration offer a robust solution for real-time, cost-effective, and transferable carbon monitoring, advancing precision soil sensing in orchard ecosystems.

Keywords: Fourier Transform Infrared Spectroscopy (FTIR); soil organic carbon (SOC); multi-stage modeling framework; variable selection; machine learning integration; citrus orchard (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/13/1417/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/13/1417/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:13:p:1417-:d:1691812

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().