Soil Organic Carbon Estimation from UAV Hyperspectral Data Using TOPSIS-Based Band Selection and Stacking Ensemble Learning
Remote Sensing · 06.11.2026 · 18 (21) · 3820
DOI: 10.3390/rs18213820 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.11.2026. Verfasst von Lingbo Wang und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shaanxi Province Natural Science Basic Research Program, Shaanxi Agricultural Science and Technology Innovation Project.
Abstract (Originalsprache)
Rapid and accurate soil organic carbon (SOC) quantification from UAV hyperspectral data is challenged by spectral redundancy and the limited generalization of individual models. This study proposes an RFE–TOPSIS–stacking method, a hybrid feature selection and stacking ensemble framework for SOC estimation using UAV hyperspectral data (350–1002 nm). Recursive feature elimination (RFE) based on XGBoost was first employed for preliminary band screening, retaining 19 bands. Then, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), a multi-criteria decision-making method, was applied to comprehensively evaluate these bands using mutual evaluation, integrating mutual information, entropy, random forest importance, the inverse coefficient of variation of reflectance, and band redundancy, and was then applied to select 12 SOC characteristic bands. A stacking regression model was subsequently constructed using a 1D-CNN, SVR, XGBoost, and PLSR as base learners and random forest as the meta-learner. The framework achieved an R2 of 0.85, an RMSE of 0.96 g/kg, and an RPD of 2.47 for the validation set, outperforming the individual model (1D-CNN: R2 = 0.78, RMSE = 1.05 g/kg, and RPD =2.26). Application to the three study areas revealed SOC contents (P10–P90) of 7.37–9.59, 7.52–11.01, and 9.98–15.43 g/kg; most validation sampling points had absolute residuals < 1 g/kg (max: 1.65 g/kg), and approximately 80% had relative errors within ±10%. The proposed framework provides a methodological basis for UAV-based field-scale SOC estimation and spatial mapping, with potential applications in precision agriculture and soil carbon assessment.
Förderung
- Shaanxi Province Natural Science Basic Research Program
- Shaanxi Agricultural Science and Technology Innovation Project
Zitieren
APA
Wang, L., Wang, Y., Liu, K., Liu, N., Yan, Q., & Hua, D. (2026). Soil Organic Carbon Estimation from UAV Hyperspectral Data Using TOPSIS-Based Band Selection and Stacking Ensemble Learning. Remote Sensing, 18(21), 3820. https://doi.org/10.3390/rs18213820
Vancouver
Wang L, Wang Y, Liu K, Liu N, Yan Q, Hua D. Soil Organic Carbon Estimation from UAV Hyperspectral Data Using TOPSIS-Based Band Selection and Stacking Ensemble Learning. Remote Sensing. 2026;18(21):3820. doi:10.3390/rs18213820
BibTeX
@article{Wang2026,
author = {Wang, Lingbo and Wang, Yufeng and Liu, Kai and Liu, Nan and Yan, Qing and Hua, Dengxin},
title = {Soil Organic Carbon Estimation from UAV Hyperspectral Data Using TOPSIS-Based Band Selection and Stacking Ensemble Learning},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {21},
pages = {3820},
doi = {10.3390/rs18213820}
}
EUVIMED