Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression
This paper’s novel focus is predicting the leaf nitrogen content of rice during growing and maturing. A multispectral image processing-based prediction model of the Radial Basis Function Neural Network (RBFNN) model was proposed. Moreover, this paper depicted three primary points as the following: F...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8626 |
| _version_ | 1827643728349626368 |
|---|---|
| author | Yawen Wu Saba J. Al-Jumaili Dhiya Al-Jumeily Haiyi Bian |
| author_facet | Yawen Wu Saba J. Al-Jumaili Dhiya Al-Jumeily Haiyi Bian |
| author_sort | Yawen Wu |
| collection | DOAJ |
| description | This paper’s novel focus is predicting the leaf nitrogen content of rice during growing and maturing. A multispectral image processing-based prediction model of the Radial Basis Function Neural Network (RBFNN) model was proposed. Moreover, this paper depicted three primary points as the following: First, collect images of rice leaves (RL) from a controlled condition experimental laboratory and new shoot leaves in different stages in the visible light spectrum, and apply digital image processing technology to extract the color characteristics of RL and the morphological characteristics of the new shoot leaves. Secondly, the RBFNN model, the General Regression Model (GRL), and the General Regression Method (GRM) model were constructed based on the extracted image feature parameters and the nitrogen content of rice leaves. Third, the RBFNN is optimized by and Partial Least-Squares Regression (RBFNN-PLSR) model. Finally, the validation results show that the nitrogen content prediction models at growing and mature stages that the mean absolute error (<i>MAE</i>), the Mean Absolute Percentage Error (<i>MAPE</i>), and the Root Mean Square Error (<i>RMSE</i>) of the RFBNN model during the rice-growing stage and the mature stage are 0.6418 (%), 0.5399 (%), 0.0652 (%), and 0.3540 (%), 0.1566 (%), 0.0214 (%) respectively, the predicted value of the model fits well with the actual value. Finally, the model may be used to give the best foundation for achieving exact fertilization control by continuously monitoring the nitrogen nutrition status of rice. In addition, at the growing stage, the RBFNN model shows better results compared to both GRL and GRM, in which <i>MAE</i> is reduced by 0.2233% and 0.2785%, respectively. |
| first_indexed | 2024-03-09T18:01:05Z |
| format | Article |
| id | doaj.art-7e696f73ee604b71b4abc6002ab3b63e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:01:05Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7e696f73ee604b71b4abc6002ab3b63e2023-11-24T09:53:11ZengMDPI AGSensors1424-82202022-11-012222862610.3390/s22228626Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares RegressionYawen Wu0Saba J. Al-Jumaili1Dhiya Al-Jumeily2Haiyi Bian3Faculty of Electronic Information Engineering, Huaiyin Institute of Technology, Huai’an 223003, ChinaLaboratory of Climate-Smart Food Crop Production, Institute of Tropical Agriculture and Food Security, Universiti Putra Malaysia (UPM), Serdang 43400, Selangor, MalaysiaSchool of Computer Science and Mathematics, Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool L3 5UX, UKFaculty of Electronic Information Engineering, Huaiyin Institute of Technology, Huai’an 223003, ChinaThis paper’s novel focus is predicting the leaf nitrogen content of rice during growing and maturing. A multispectral image processing-based prediction model of the Radial Basis Function Neural Network (RBFNN) model was proposed. Moreover, this paper depicted three primary points as the following: First, collect images of rice leaves (RL) from a controlled condition experimental laboratory and new shoot leaves in different stages in the visible light spectrum, and apply digital image processing technology to extract the color characteristics of RL and the morphological characteristics of the new shoot leaves. Secondly, the RBFNN model, the General Regression Model (GRL), and the General Regression Method (GRM) model were constructed based on the extracted image feature parameters and the nitrogen content of rice leaves. Third, the RBFNN is optimized by and Partial Least-Squares Regression (RBFNN-PLSR) model. Finally, the validation results show that the nitrogen content prediction models at growing and mature stages that the mean absolute error (<i>MAE</i>), the Mean Absolute Percentage Error (<i>MAPE</i>), and the Root Mean Square Error (<i>RMSE</i>) of the RFBNN model during the rice-growing stage and the mature stage are 0.6418 (%), 0.5399 (%), 0.0652 (%), and 0.3540 (%), 0.1566 (%), 0.0214 (%) respectively, the predicted value of the model fits well with the actual value. Finally, the model may be used to give the best foundation for achieving exact fertilization control by continuously monitoring the nitrogen nutrition status of rice. In addition, at the growing stage, the RBFNN model shows better results compared to both GRL and GRM, in which <i>MAE</i> is reduced by 0.2233% and 0.2785%, respectively.https://www.mdpi.com/1424-8220/22/22/8626image processingpredicationartificial neural networkrice leaves |
| spellingShingle | Yawen Wu Saba J. Al-Jumaili Dhiya Al-Jumeily Haiyi Bian Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression Sensors image processing predication artificial neural network rice leaves |
| title | Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression |
| title_full | Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression |
| title_fullStr | Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression |
| title_full_unstemmed | Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression |
| title_short | Prediction of the Nitrogen Content of Rice Leaf Using Multi-Spectral Images Based on Hybrid Radial Basis Function Neural Network and Partial Least-Squares Regression |
| title_sort | prediction of the nitrogen content of rice leaf using multi spectral images based on hybrid radial basis function neural network and partial least squares regression |
| topic | image processing predication artificial neural network rice leaves |
| url | https://www.mdpi.com/1424-8220/22/22/8626 |
| work_keys_str_mv | AT yawenwu predictionofthenitrogencontentofriceleafusingmultispectralimagesbasedonhybridradialbasisfunctionneuralnetworkandpartialleastsquaresregression AT sabajaljumaili predictionofthenitrogencontentofriceleafusingmultispectralimagesbasedonhybridradialbasisfunctionneuralnetworkandpartialleastsquaresregression AT dhiyaaljumeily predictionofthenitrogencontentofriceleafusingmultispectralimagesbasedonhybridradialbasisfunctionneuralnetworkandpartialleastsquaresregression AT haiyibian predictionofthenitrogencontentofriceleafusingmultispectralimagesbasedonhybridradialbasisfunctionneuralnetworkandpartialleastsquaresregression |