A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network
Accurate estimation of wheat leaf nitrogen concentration (LNC) is critical for characterizing ecosystem and plant physiological processes; it can further guide fertilization and other field management operations, and promote the sustainable development of agriculture. In this study, a wheat LNC test...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/13/9/2387 |
| _version_ | 1797581673376776192 |
|---|---|
| author | Jinyan Ju Zhenyang Lv Wuxiong Weng Zongfeng Zou Tenghui Lin Yingying Liu Zhentao Wang Jinfeng Wang |
| author_facet | Jinyan Ju Zhenyang Lv Wuxiong Weng Zongfeng Zou Tenghui Lin Yingying Liu Zhentao Wang Jinfeng Wang |
| author_sort | Jinyan Ju |
| collection | DOAJ |
| description | Accurate estimation of wheat leaf nitrogen concentration (LNC) is critical for characterizing ecosystem and plant physiological processes; it can further guide fertilization and other field management operations, and promote the sustainable development of agriculture. In this study, a wheat LNC test method based on multi-source spectral data and a convolutional neural network is proposed. First, interpolation reconstruction was performed on the wheat spectra data collected by different spectral instruments to ensure that the number of spectral channels and spectral range were consistent, and multi-source spectral data were constructed using interpolated, reconstructed imaging spectral data and non-imaging spectral data. Afterwards, the convolutional neural network DshNet and machine learning methods (PLSR, SVR, and RFR) were compared under various scenarios (non-imaging spectral data, imaging spectral data, and multi-source spectral data). Finally, the competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to optimize the LNC detection model. The results show that the model based on DshNet has the highest test accuracy. The CARS method is more suitable for DshNet model optimization than SPA. In the modeling scenario with non-imaging spectral, imaging spectral, and multi-source spectral, the optimized R<sup>2</sup> is 0.86, 0.82, and 0.82, and the RMSE is 0.29, 0.31, and 0.31, respectively. The LNC visualization results show that DshNet modeling using multi-source spectral data is conducive to the visualization expansion of non-imaging spectral data. Therefore, the method presented in this paper provides new considerations for spectral data from different sources and is helpful for related research on the chemometric task of multi-source spectral data. |
| first_indexed | 2024-03-10T23:07:53Z |
| format | Article |
| id | doaj.art-caf84814b718429cacc49d7a52132245 |
| institution | Directory Open Access Journal |
| issn | 2073-4395 |
| language | English |
| last_indexed | 2024-03-10T23:07:53Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj.art-caf84814b718429cacc49d7a521322452023-11-19T09:11:34ZengMDPI AGAgronomy2073-43952023-09-01139238710.3390/agronomy13092387A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural NetworkJinyan Ju0Zhenyang Lv1Wuxiong Weng2Zongfeng Zou3Tenghui Lin4Yingying Liu5Zhentao Wang6Jinfeng Wang7School of Mechanical Engineering, Heilongjiang University of Science and Technology, Harbin 150022, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaYantai Agricultural Technology Popularization Center, Yantai 261400, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaXinbin Manchu Autonomous County Shangjiahe Town Comprehensive Affairs Service Center, Fushun 113000, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaCollege of Engineering, Northeast Agricultural University, Harbin 150030, ChinaAccurate estimation of wheat leaf nitrogen concentration (LNC) is critical for characterizing ecosystem and plant physiological processes; it can further guide fertilization and other field management operations, and promote the sustainable development of agriculture. In this study, a wheat LNC test method based on multi-source spectral data and a convolutional neural network is proposed. First, interpolation reconstruction was performed on the wheat spectra data collected by different spectral instruments to ensure that the number of spectral channels and spectral range were consistent, and multi-source spectral data were constructed using interpolated, reconstructed imaging spectral data and non-imaging spectral data. Afterwards, the convolutional neural network DshNet and machine learning methods (PLSR, SVR, and RFR) were compared under various scenarios (non-imaging spectral data, imaging spectral data, and multi-source spectral data). Finally, the competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were used to optimize the LNC detection model. The results show that the model based on DshNet has the highest test accuracy. The CARS method is more suitable for DshNet model optimization than SPA. In the modeling scenario with non-imaging spectral, imaging spectral, and multi-source spectral, the optimized R<sup>2</sup> is 0.86, 0.82, and 0.82, and the RMSE is 0.29, 0.31, and 0.31, respectively. The LNC visualization results show that DshNet modeling using multi-source spectral data is conducive to the visualization expansion of non-imaging spectral data. Therefore, the method presented in this paper provides new considerations for spectral data from different sources and is helpful for related research on the chemometric task of multi-source spectral data.https://www.mdpi.com/2073-4395/13/9/2387hyperspectralconvolution neural networkinterpolation reconstructionmulti-source spectral dataleaf nitrogen content |
| spellingShingle | Jinyan Ju Zhenyang Lv Wuxiong Weng Zongfeng Zou Tenghui Lin Yingying Liu Zhentao Wang Jinfeng Wang A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network Agronomy hyperspectral convolution neural network interpolation reconstruction multi-source spectral data leaf nitrogen content |
| title | A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network |
| title_full | A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network |
| title_fullStr | A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network |
| title_full_unstemmed | A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network |
| title_short | A Method for Determining the Nitrogen Content of Wheat Leaves Using Multi-Source Spectral Data and a Convolution Neural Network |
| title_sort | method for determining the nitrogen content of wheat leaves using multi source spectral data and a convolution neural network |
| topic | hyperspectral convolution neural network interpolation reconstruction multi-source spectral data leaf nitrogen content |
| url | https://www.mdpi.com/2073-4395/13/9/2387 |
| work_keys_str_mv | AT jinyanju amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zhenyanglv amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT wuxiongweng amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zongfengzou amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT tenghuilin amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT yingyingliu amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zhentaowang amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT jinfengwang amethodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT jinyanju methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zhenyanglv methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT wuxiongweng methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zongfengzou methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT tenghuilin methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT yingyingliu methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT zhentaowang methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork AT jinfengwang methodfordeterminingthenitrogencontentofwheatleavesusingmultisourcespectraldataandaconvolutionneuralnetwork |