Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning
Plants · 26.12.2024 · 14 (1) · 37
DOI: 10.3390/plants14010037 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 26.12.2024. Verfasst von Chunguang Bi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Science and Technology Development Programme: Key R&D Project: 'Cloud Brain' Technology and Platform for Unmanned Corn Operation, National Key Research and Development Project: Key Technology Research and Component Creation of unmanned land Finishing Operation, Jilin Provincial Science and Technology Development Programme.
Abstract (Originalsprache)
The precise identification of maize kernel varieties is essential for germplasm resource management, genetic diversity conservation, and the optimization of agricultural production. To address the need for rapid and non-destructive variety identification, this study developed a novel interpretable machine learning approach that integrates low-field nuclear magnetic resonance (LF-NMR) with morphological image features through an optimized support vector machine (SVM) framework. First, LF-NMR signals were obtained from eleven maize kernel varieties, and ten key features were extracted from the transverse relaxation decay curves. Meanwhile, five image morphological features were selected using the recursive feature elimination (RFE) algorithm. Before modeling, principal component analysis (PCA) was used to determine the distribution features of the internal components for each maize variety. Subsequently, LF-NMR features and image morphological data were integrated to construct a classification model and the SVM hyperparameters were optimized using an improved differential evolution algorithm, achieving a final classification accuracy of 96.36%, which demonstrated strong robustness and precision. The model’s interpretability was further enhanced using Shapley values, which revealed the contributions of key features such as Max Signal and Signal at Max Curvature to classification decisions. This study provides an innovative technical solution for the efficient identification of maize varieties, supports the refined management of germplasm resources, and lays a foundation for genetic improvement and agricultural applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, China.
- College of Information Technology, Jilin Agricultural University, Changchun 130118, China.
- Zhongnong Sunshine School-Enterprise R&D Centre, Jilin Agricultural University, Changchun 130118, China.
- School of Data Science and Artificial Intelligence, Jilin Engineering Normal University, Changchun 130052, China.
ORCID-Profile: Helong Yu
Förderung
- Jilin Provincial Science and Technology Development Programme: Key R&D Project: 'Cloud Brain' Technology and Platform for Unmanned Corn Operation
- National Key Research and Development Project: Key Technology Research and Component Creation of unmanned land Finishing Operation
- Jilin Provincial Science and Technology Development Programme
- National Key Research and Development Project
Zitieren
APA
Bi, C., Bi, X., Liu, J., Chen, H., Wang, M., Yu, H., & Song, S. (2024). Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning. Plants, 14(1), 37. https://doi.org/10.3390/plants14010037
Vancouver
Bi C, Bi X, Liu J, Chen H, Wang M, Yu H, et al. Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning. Plants. 2024;14(1):37. doi:10.3390/plants14010037
BibTeX
@article{Bi2024,
author = {Bi, Chunguang and Bi, Xinhua and Liu, Jinjing and Chen, He and Wang, Mohan and Yu, Helong and Song, Shaozhong},
title = {Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning},
journal = {Plants},
year = {2024},
volume = {14},
number = {1},
pages = {37},
doi = {10.3390/plants14010037}
}
EUVIMED