Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning
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 m...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/14/1/37 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549085208739840 |
|---|---|
| author | Chunguang Bi Xinhua Bi Jinjing Liu He Chen Mohan Wang Helong Yu Shaozhong Song |
| author_facet | Chunguang Bi Xinhua Bi Jinjing Liu He Chen Mohan Wang Helong Yu Shaozhong Song |
| author_sort | Chunguang Bi |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-9a01e427d5394ae8a62cddabed378491 |
| institution | Kabale University |
| issn | 2223-7747 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj-art-9a01e427d5394ae8a62cddabed3784912025-01-10T13:19:33ZengMDPI AGPlants2223-77472024-12-011413710.3390/plants14010037Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine LearningChunguang Bi0Xinhua Bi1Jinjing Liu2He Chen3Mohan Wang4Helong Yu5Shaozhong Song6Institute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaCollege of Information Technology, Jilin Agricultural University, Changchun 130118, ChinaZhongnong Sunshine School-Enterprise R&D Centre, Jilin Agricultural University, Changchun 130118, ChinaInstitute for the Smart Agriculture, Jilin Agricultural University, Changchun 130118, ChinaSchool of Data Science and Artificial Intelligence, Jilin Engineering Normal University, Changchun 130052, ChinaThe 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.https://www.mdpi.com/2223-7747/14/1/37maize kernelsLF-NMRmulti-source dataSVMShapley valuegermplasm resource |
| spellingShingle | Chunguang Bi Xinhua Bi Jinjing Liu He Chen Mohan Wang Helong Yu Shaozhong Song Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning Plants maize kernels LF-NMR multi-source data SVM Shapley value germplasm resource |
| title | Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning |
| title_full | Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning |
| title_fullStr | Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning |
| title_full_unstemmed | Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning |
| title_short | Identification of Maize Kernel Varieties Using LF-NMR Combined with Image Data: An Explainable Approach Based on Machine Learning |
| title_sort | identification of maize kernel varieties using lf nmr combined with image data an explainable approach based on machine learning |
| topic | maize kernels LF-NMR multi-source data SVM Shapley value germplasm resource |
| url | https://www.mdpi.com/2223-7747/14/1/37 |
| work_keys_str_mv | AT chunguangbi identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT xinhuabi identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT jinjingliu identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT hechen identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT mohanwang identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT helongyu identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning AT shaozhongsong identificationofmaizekernelvarietiesusinglfnmrcombinedwithimagedataanexplainableapproachbasedonmachinelearning |