Marginal Contribution Spectral Fusion Network for Remote Hyperspectral Soil Organic Matter Estimation

Gorde:

Xehetasun bibliografikoak
Argitaratua izan da:	Remote Sensing vol. 17, no. 16 (2025), p. 2806-2825
Egile nagusia:	Tang Jiaze
Beste egile batzuk:	Liu, Dan, Wang Qisong, Li, Junbao, Liao Jingxiao, Sun Jinwei
Argitaratua:	MDPI AG
Gaiak:	China Carbon cycle Accuracy Deep learning Agricultural production Remote sensing Organic matter Unmanned aerial vehicles Spatial distribution Soil organic matter Sustainable agriculture Agriculture Machine learning Preprocessing Soil sciences Soils Spectrum analysis Soil fertility Methods Information processing Airborne sensing
Sarrera elektronikoa:	Citation/Abstract Full Text + Graphics Full Text - PDF
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

Deskribapena
Laburpena:	Soil organic matter (SOM) is a fundamental indicator of soil health and a major component of the global carbon cycle; its accurate quantification is essential for sustainable agriculture. Conventional chemical assays yield only point-based soil measurements and miss the spatial distribution of soil elements; airborne hyperspectral remote sensing has emerged as a promising approach for the quantitative measurement and characterization of SOM. Inversion models translate hyperspectral data into quantitative SOM estimates. However, existing models rely solely on a single preprocessing pathway, limiting their ability to fully exploit available spectral information. We address these limitations by developing a marginal contribution-driven spectral fusion network (MC-SFNet) that conducts feature-level fusion of heterogeneous preprocessing outputs within a physics-guided deep architecture. Moreover, the combination of data-driven fusion and the Kubelka–Munk (KM) model yields more physically interpretable spectral features, advancing beyond prior purely data-driven methods. We validated MC-SFNet on a self-constructed remote sensing, high-throughput hyperspectral dataset comprising 200 black soil samples from Northeastern China (400–1000 nm, 256 bands). Experimental results show that our network reduces the RMSE by 10.7% relative to the prevailing generalized hyperspectral soil-inversion model. The proposed method provides a novel preprocessing pathway for forthcoming airborne high-throughput hyperspectral missions to extract soil-specific spectral information more effectively and further enhance large-scale SOM retrieval accuracy.
ISSN:	2072-4292
DOI:	10.3390/rs17162806
Baliabidea:	Advanced Technologies & Aerospace Database