EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A novel and computationally efficient chunk-wise fully connected deep learning model for non-destructive protein prediction using NIR spectroscopy

Naseeb Singh, Simardeep Kaur, Siddhant Ranjan Padhi, Racheal John, Shruti, Amit Kumar, Kuldeep Tripathi, Gayacharan, Rakesh Singh, Rakesh Bhardwaj, Amritbir Riar

Smart Agricultural Technology · 2026-08 · 14 · 102025

DOI: 10.1016/j.atech.2026.102025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2026-08. Verfasst von Naseeb Singh und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Department of Biotechnology, Ministry of Science and Technology, India, Indian Council of Agricultural Research, Direktion für Entwicklung und Zusammenarbeit.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has emerged as a powerful approach for predicting biochemical traits from spectral data, providing rapid, high-throughput, and non-destructive alternatives to conventional laboratory analyses. Although architectures such as one-dimensional Convolutional Neural Networks (1D-CNNs) and Transformers have shown strong predictive capability, they often require substantial computational resources and large training datasets. In agricultural applications; however, computational efficiency and model generalizability are equally important. To address this need, the present study developed a chunk-wise fully connected neural network that progressively integrates spectral features in fixed-size segments. The proposed architecture was evaluated alongside standard 1D-CNN and Transformer-based models for seed protein prediction using near-infrared reflectance spectroscopy (NIRS) data from three crops: chickpea (n=795), cowpea (n=472), and rice (n=985). The chunk-wise model achieved predictive accuracy comparable to that of the Transformer model, with R 2 values ranging from 0.90 to 0.97, and outperformed the 1D-CNN in both accuracy and Residual Prediction Deviation (RPD). Relative to the Transformer, it required approximately 78% fewer parameters and nearly fourfold less training time. The chunk-wise network also showed consistent performance across all three crops, indicating its applicability across datasets with differing spectral and compositional characteristics. Overall, the proposed model provides a computationally efficient and scalable solution for NIR-based prediction of biochemical traits, with strong potential for integration into portable screening tools and high-throughput breeding pipelines, particularly for large-scale germplasm evaluation.

Förderung

  • Department of Biotechnology, Ministry of Science and Technology, India
  • Indian Council of Agricultural Research
  • Direktion für Entwicklung und Zusammenarbeit

Zitieren

APA

Singh, N., Kaur, S., Padhi, S. R., John, R., Shruti, Kumar, A., Tripathi, K., Gayacharan, Singh, R., Bhardwaj, R., & Riar, A. (2026). A novel and computationally efficient chunk-wise fully connected deep learning model for non-destructive protein prediction using NIR spectroscopy. Smart Agricultural Technology, 14, 102025. https://doi.org/10.1016/j.atech.2026.102025

Vancouver

Singh N, Kaur S, Padhi SR, John R, Shruti, Kumar A, et al. A novel and computationally efficient chunk-wise fully connected deep learning model for non-destructive protein prediction using NIR spectroscopy. Smart Agricultural Technology. 2026;14:102025. doi:10.1016/j.atech.2026.102025

BibTeX
@article{Singh2026,
  author = {Singh, Naseeb and Kaur, Simardeep and Padhi, Siddhant Ranjan and John, Racheal and Shruti and Kumar, Amit and Tripathi, Kuldeep and Gayacharan and Singh, Rakesh and Bhardwaj, Rakesh and Riar, Amritbir},
  title = {A novel and computationally efficient chunk-wise fully connected deep learning model for non-destructive protein prediction using NIR spectroscopy},
  journal = {Smart Agricultural Technology},
  year = {2026},
  volume = {14},
  pages = {102025},
  doi = {10.1016/j.atech.2026.102025}
}
Kostenlos starten →