Diffusion Probabilistic Models for NIR Spectral Data Augmentation in Precision Agriculture
Agronomy · 19.11.2025 · 15 (11) · 2648
DOI: 10.3390/agronomy15112648 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agronomy, online erschienen am 19.11.2025. Verfasst von Changxu Hu und 11 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shanxi Key Project—Research on Intelligent Decision-making System for Precision Agriculture.
Abstract (Originalsprache)
Near-infrared (NIR) spectroscopy is a rapid, non-destructive tool widely used in agriculture, but limited labeled spectra often constrain model robustness. To address this, we propose using denoising diffusion probabilistic models (DDPMs) for NIR data augmentation. Leveraging the SpectraFood leek dataset, a conditional MLP-DDPM was trained to generate realistic synthetic spectra guided by dry matter content. Incorporating 1000 generated spectra into the training set improved the predictive performance of PLSR, RF, and XGBoost models, demonstrating enhanced generalization and robustness. Compared with WGAN, DDPM offered higher stability and fidelity, effectively expanding the calibration space without introducing unrealistic patterns. Future work will explore conditional and hybrid diffusion frameworks, integrating environmental and physiological covariates, and cross-domain spectral transfer, extending the applicability of DDPMs for diverse crops and precision agriculture scenarios.
Förderung
- Shanxi Key Project—Research on Intelligent Decision-making System for Precision Agriculture
Zitieren
APA
Hu, C., Wang, H., Hou, P., Nan, J., Che, X., Wang, Y., Bai, Y., Chen, B., Miao, Y., Zhang, W., Li, F., & Han, J. (2025). Diffusion Probabilistic Models for NIR Spectral Data Augmentation in Precision Agriculture. Agronomy, 15(11), 2648. https://doi.org/10.3390/agronomy15112648
Vancouver
Hu C, Wang H, Hou P, Nan J, Che X, Wang Y, et al. Diffusion Probabilistic Models for NIR Spectral Data Augmentation in Precision Agriculture. Agronomy. 2025;15(11):2648. doi:10.3390/agronomy15112648
BibTeX
@article{Hu2025,
author = {Hu, Changxu and Wang, Huihui and Hou, Pengzhi and Nan, Jiaxuan and Che, Xiaoxue and Wang, Yaqi and Bai, Yangfan and Chen, Bingjun and Miao, Yuyuan and Zhang, Wuping and Li, Fuzhong and Han, Jiwan},
title = {Diffusion Probabilistic Models for NIR Spectral Data Augmentation in Precision Agriculture},
journal = {Agronomy},
year = {2025},
volume = {15},
number = {11},
pages = {2648},
doi = {10.3390/agronomy15112648}
}
EUVIMED